# Research Papers — 2026-08 · bundle page 59 of 240 > Full-text markdown of papers #2901–2950 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/59 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/58.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/60.md) ### Memory-Efficient Training-Free Acceleration of Diffusion Transformers with BaryCache Authors: Chengjie Lu, Tianchi Deng, Zhengqi He, Zhijian Gao, Huisi Wu, Xueliang Li Published: 2026-08-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28670v1 Diffusion Transformers achieve high-fidelity image and video generation, but their iterative sampling remains expensive, for each denoising step requires large matrix operations. Existing cache-based acceleration reduces redundant computation yet increases the VRAM footprint by storing intermediate states, which can directly constrain inference batch size. In this work, we propose a training-free acceleration method that performs stepwise forecasting for DiT sampling using a Barycentric Extrapolator. By leveraging barycentric extrapolation, our predictor is numerically stable and alleviates oscillatory artifacts analogous to the Runge phenomenon during forward forecasting. Across extensive experiments on both image and video generation, our approach provides a favorable trade-off between memory usage and perceptual quality, while delivering up to 3.30x end-to-end sampling speedup compared with baseline DiT inference. --- ### MIRAGE-CAD: Construction-Mediated Multimodal Generation of Executable CAD Programs Authors: Jizong Zhan Published: 2026-08-24 Categories: cs.CV, cs.PL, cs.SE arXiv: https://arxiv.org/abs/2608.28669v1 Recovering an executable parametric CAD program from an observed object is fundamentally ambiguous, because the same final geometry can result from different construction procedures. We study this problem from four types of input: natural-language descriptions, rendered images, point clouds, and STEP/B-Rep geometry. MIRAGE-CAD maps each input to a shared construction representation and mediates program generation through an explicit construction-plan interface. The resulting Python CAD code is executed by an OpenCASCADE kernel to build the solid and export it as STEP. On 2,500 held-out queries per modality, the system achieves 55.4-70.0% build success and 52.3-66.2% STEP export success without retrieval at inference. Controlled comparisons show that strong reconstruction does not depend on expressing the construction representation as text: a decoder conditioned directly on the continuous representation also reconstructs strongly, while an exposure-matched plan-based decoder shows no detected material loss in per-part geometric fidelity. The explicit plan instead provides a readable and separately measurable intermediate representation whose agreement with the reference construction is informative about downstream execution success. Finally, we show that executable validity, geometric fidelity, and parametric responsiveness can diverge substantially and should therefore be evaluated separately. --- ### GreenBench: Benchmarking Energy Efficiency and Carbon Footprint of Open-Source LLM Inference on Apple Silicon Authors: Rajeswari Kannan, Raj Firke, Shreya Bengle, Srushti Deshmukh Published: 2026-08-24 Categories: cs.CL, cs.AI, cs.PF arXiv: https://arxiv.org/abs/2608.28667v1 The rapid proliferation of Large Language Models (LLMs) has raised concerns about their environmental impact during inference. While Green AI research has focused on datacenter GPUs and embedded platforms, the energy profile of LLM inference on Apple Silicon, with its unified memory architecture, remains unstudied. This paper presents GreenBench, a benchmarking framework that evaluates the energy efficiency, throughput, and carbon footprint of five open-source LLMs (3-9B parameters) across three NLP tasks on an Apple M4 Pro with 48 GB unified memory. Using macOS powermetrics for direct power measurement and Ollama's nanosecond-precision timing, we find that the M4 Pro draws only 0.47 W of CPU+GPU package power during sustained inference, with total system power of 8-12 W, achieving 30-40x better energy efficiency per token than datacenter GPUs in single-user deployment. Smaller models (3-3.8B) deliver 2.6-4.2x higher throughput and up to 62% less energy per token than larger models (7-9B). Pareto analysis identifies Qwen 2.5 (7B) as the optimal accuracy-efficiency trade-off at 57% MMLU and 59 tokens/s, while Llama 3.2 (3B) suits latency-critical applications at 175 tokens/s. We provide per-token energy at package and system levels with CO2 estimates for India and US grids. --- ### A Reranker for Orchestrating Heterogeneous Speech and Text Retrievers Authors: Inho Kim, Sumyeong Ahn Published: 2026-08-24 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2608.26194v1 Retrieval-Augmented Generation (RAG) systems have attracted significant interest for their ability to mitigate hallucinations in Large Language Models (LLMs). Although knowledge databases for RAG are increasingly diversifying to include various modalities such as speech and text, research on handling such multi-modal database scenarios remains limited. In this paper, we propose STeReO (Speech and Text Reranking Orchestrator), a reranker based on speech and text retrievers that aggregates disparate modality databases. To address the lack of specialized training data, we first curate a dataset comprising queries, mixed-modality evidence, and their corresponding relevance ranks. We then train the reranker and evaluate its effectiveness in both single-modality and mixed-modality scenarios. Our results demonstrate that the proposed algorithm excels at selecting the most relevant evidence, thereby significantly improving downstream question-answering performance. --- ### AffectOmni: RL-Verifiable People-Centric Grounded Affective Reasoning for Social and Art-Related Scenes Authors: Yibo Wang, Rui Yang, Jisheng Dang, Bimei Wang, Yitao Wu, Pengfei Cao, Wencan Zhang, Hong Peng, Bin Hu, Tat-Seng Chua Published: 2026-08-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.26193v1 Multimodal large language models (MLLMs) achieve strong performance on VQA and scene understanding, yet affective reasoning remains vulnerable to shortcut behavior. Models may predict correct answers while neglecting people-centric cues such as micro expressions and body language, which weakens traceability and external verification. Prior reinforcement learning approaches mainly reward context or logical coherence without explicitly enforcing attention to human evidence. In addition, LLM as a Judge scoring often suffers from score clustering, which reduces reward discriminability. We propose AffectOmni, a GRPO trained framework for verifiable affective reasoning. AffectOmni introduces People Focus and Temporal Order rewards to encourage people-centric evidence selection and temporally structured reasoning, and it adopts within-group comparative scoring to produce more stable and discriminative reward signals. For verification, a Thinking Summarizer converts free form rationales into executable evidence instructions, which are grounded into pixel level evidence regions via SAM3 to provide an externally auditable interface outside the training loop. Experiments on IntentBench, Daily Omni, and WorldSense show consistent improvements over open source 7B scale baselines, including gains of 4.66% on emotion recognition and +14.29% on temporally sensitive tasks. Code is available at https://github.com/eliot127825-rgb/AffectOmni_nobody. --- ### Comparing Chunking and Embedding Strategies for Turkish RAG Systems Authors: Mustafa Sertaç Türkel, Fatma Nur Korkmaz, Ahmet Tuğrul Bayrak Published: 2026-08-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.26192v2 Retrieval-Augmented Generation conditions a language model on chunks retrieved from a document collection. Its accuracy is therefore limited by the chunking and embedding stages that determine what can be retrieved. We compare Turkish document question answering across three chunking strategies (fixed-length, semantic, and layout-aware Docling), five embedding models, and two LLMs, over three documents with contrasting layouts. Every configuration answers the same question set, which allows component effects to be separated by paired testing rather than inferred from separate benchmarks. The fully crossed design yields 9{,}000 graded question-answer evaluations, each scored by an independent judge model, and component comparisons are tested by paired McNemar tests under Holm correction. The three leading embedding models are statistically indistinguishable, so language specialization yields no measurable retrieval advantage. The faster LLM is not the more accurate one. The preferred configuration depends on content type, since layout-aware chunking helps table-heavy documents far more than text-heavy ones. --- ### Structured Evidence Routing for Incident Risk Prediction from Multimodal Longitudinal EHRs Authors: Animesh Agarwal, Meysam Ghaffari, Nina Fatehi, Carlos Morato Published: 2026-08-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.26191v1 Incident risk prediction from longitudinal electronic health records (EHRs) is challenging because relevant signals are multimodal, weak in isolation, and distributed across irregular patient histories. We propose structured evidence routing, a router-predictor-reviewer workflow that separates full-record access from disease-specific assessment. The router organizes the complete pre-index EHR into a compact summary and targeted evidence slices; the predictor uses this evidence to form an evidence-linked risk assessment, which the reviewer critiques. For comparison with supervised EHRSHOT baselines, we pair the routed evidence summaries with a supervised classifier readout. Across five 1-year incident diagnosis tasks, our method reaches the AUROC range of established supervised EHRSHOT baselines and remains competitive on AUPRC, while exposing a patient-specific evidence trail. Internal pre-readout ablations further suggest that routing, laboratory evidence, task guidance, and review each contribute to performance. --- ### Beyond Tokens: Probing Higher-Order Epistasis in Learned Protein Representations Authors: Maryam Rahimimovassagh, Ivan Garibay, Niloofar Yousefi Published: 2026-08-24 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2608.24953v1 Protein fitness landscapes contain nonlinear interactions in which mutation effects depend on other residues. We introduce ORBIT, an Order-Resolved Benchmarking of Interaction Transformations framework that separates interaction presence, representation accessibility, and functional recovery. ORBIT first validates Walsh-based diagnostics on synthetic landscapes with known interaction order, then analyzes the experimentally measured GB1 fitness landscape under the FLIP 2-vs-rest setting. We compare ridge regression, a standard MLP, independent tokens, nonlinear independent tokens, and Residual Interaction Tokenization (RIT). Across 20 paired training seeds, the primary two-hidden-layer comparison found no significant architecture differences in FLIP test R^2, third- or fourth-order functional recovery, or final-layer third- or fourth-order accessibility. However, RIT significantly increased pairwise accessibility at the token stage relative to both independent-token controls (Delta A_tok,2 = 0.2468, d_z = 1.67, Holm-adjusted p = 1.14 x 10^-5), without a detectable downstream higher-order advantage. A pre-specified depth/capacity analysis showed that deeper MLPs improved FLIP prediction, third-order functional recovery, and final-layer third-order accessibility; fourth-order accessibility also improved relative to the shallow MLP but remained below zero in absolute held-out R^2. ORBIT therefore reveals representation-level changes hidden by conventional prediction metrics and distinguishes early interaction-aware encoding from higher-order structure constructed by downstream nonlinear capacity. --- ### The Dialect Tax: Dialectal Biases Persist throughout the Language Modeling Pipeline Authors: Elle Published: 2026-08-24 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.24952v1 Systematic dialectal performance gaps in language models (LMs) are well documented, but the source of these disparities within the modern language modeling pipeline remains unclear. Our study traces this "dialect tax" across the natural language processing pipeline. Using parallel English dialect corpora that hold meaning fixed while varying surface form, we first confirm that LMs recognize matched Standard American English (SAE) and dialectal texts as semantically equivalent. However, we discover further representational gaps corresponding to downstream performance gaps. Across model families and generations, modern LMs still encode dialectal texts unequally during tokenization, pre-training, post-training, and inference. Strikingly, bypassing traditional subword segmentation via a character-level counterfactual tokenizer removes neither input and output asymmetries nor dialectal accuracy gaps. During pre-training, dialect pairs induce more divergent gradient updates than pairs of entirely unrelated SAE documents, indicating that models find semantically equivalent dialectal content harder to learn from than unrelated SAE documents. During post-training, reward models show contextual, unstable dialect preferences, assigning higher values to isolated AAVE-exclusive tokens than to SAE-exclusive tokens, while full reasoning contexts receive task- and model-dependent dialect penalties. Overall, our findings suggest that the dialect tax is encoded and accumulated not by any one step in isolation, but at every step of the language modeling process. --- ### Demystifying Reinforcement Learning Post-Training of Language Models Authors: Donovan Clay, Saket Gollapudi, Sankar Harilal, Min Jang, Jacob Morrison, Sewoong Oh, Natasha Jaques Published: 2026-08-24 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.24949v2 Reinforcement learning (RL) post-training has emerged as a powerful framework for enhancing the capabilities of large language models (LLMs), enabling impressive reasoning, math, and coding capabilities. Yet for many researchers and practitioners, the principles behind classical RL remain a "black box". In this work, we deconstruct the RL post-training algorithm, investigating each step to clarify what is actually happening beneath the surface. By isolating the mechanics of RL with Verifiable Rewards in a controlled and simplified environment, we examine how RL outcomes are shaped by the base model's prior distribution, the granularity of the reward signal, the diversity of the prompt distribution, and model scale. We use the entropy of the policy's output distribution as a lens to compare the distributions learned through pretraining, SFT, and RL post-training, revealing how each stage shapes model certainty. Our investigation sheds light on how these choices interact to affect post-training success. For example, we show that the effect of so-called 'spurious rewards' depends on the prompt distribution used for post-training. We also provide insight into why the success of RL post-training depends on whether the base model already places sufficient probability mass on the desired behavior, linking it to the classical concept of exploration in RL. Ultimately, we provide this primer as a resource to those in the NLP community wishing to incorporate RL as a tool in their toolbox. --- ### CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery Authors: Mahir Shahriar Tamim, Sharjil Khan, Md. Samiul Alim, Tanvir Ahmed Khan, Shafin Rahman, Nabeel Mohammed Published: 2026-08-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.24947v3 End-to-end training of multimodal neural networks often exhibits unstable neural dynamics characterized by three coupled failure modes that degrade learning: (i) modality imbalance, where one branch dominates gradient-based optimization; (ii) unstable gating, where noisy confidence cues induce erratic modality selection; and (iii) fusion interference, where modality-specific gradients conflict at the shared fusion layer. We propose CAT-GS (Calibrated, Adaptive, Thresholded Gating with Fusion Surgery), a neural dynamics-based optimization controller for intelligent computing applications. CAT-GS operates during backpropagation without modifying model architectures, fusion modules, or task losses. Through calibration of teacher-derived reliability via temperature scaling and EMA smoothing, CAT-GS stabilizes neural dynamics using a margin-thresholded policy to switch between warm-up dropout, weak-modality prioritization, and weak-biased blending, stabilizes gradient magnitudes under aggressive gating via capped gradient-budget renormalization, and applies fusion-only PCGrad to reduce destructive cross-modal interference at the primary shared bottleneck. We evaluate CAT-GS on audio--visual multimodal pattern recognition benchmarks (CREMA-D, AV-MNIST, and VGGSound), a tri-modal setting (UR-FUNNY), controlled synthetic data (CG-MNIST), and additional cross-domain benchmarks (AVE and CMU-MOSI). CAT-GS improves or matches fused multimodal accuracy against strong imbalance-aware baselines (including OGM-GE, G$^2$D, and UMT) across settings, and yields smoother gating behavior with fewer conflicting fusion gradients. --- ### MacroAgent: Regularity-Aware Macro Legalization with LLM-Agent-Designed Contour Algorithms Authors: Jiaxi Jiang, Xufeng Yao, Yuxuan Zhao, Yuntao Lu, Peiyu Liao, Zuodong Zhang, Yibo Lin, Bei Yu Published: 2026-08-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.24946v1 Macros constitute a large part of the core area in modern very large-scale integration (VLSI) designs. Moreover, macro positions have a significant impact on the final quality of result (QoR), and macro legalization is typically the final step in determining the macro positions. However, existing approaches related to macro legalization either lack robustness or incur substantial computational costs or neglect the regularity between macros. To address these limitations, we introduce MacroAgent. The novel framework is a four-stage approach: clustering, contour generation, template matching, and inter-cluster refinement. We propose leveraging Large Language Models (LLMs) to discover multiple, effective heuristic regularity-aware contour algorithms. This framework successfully generates robust and effective algorithmic solutions for macro legalization. Compared with state-of-the-art macro legalization works, experimental results on TILOS and Chipyard benchmarks demonstrate a 2 to 8 fold improvement in layout regularity, a 3% to 5% reduction in routed wirelength with comparable congestion after global routing, and significantly better robustness with an acceptable runtime. Furthermore, end-to-end evaluation through Cadence Innovus place-and-route confirms that the regularity improvements translate into tangible PPA gains, including 2.9% lower routed wirelength and 68.3% TNS improvement over the DREAMPlace macro legalization baseline; it also achieves 1.8% lower routed wirelength when integrated into the Innovus macro placement flow. --- ### FAMPWQ: Fisher Information-based Adaptive Mixed Precision Weight Quantization for Effective LLM Inference Authors: Gongwei Lee, Ji Liu, Juncheng Jia, Ji Wu Published: 2026-08-24 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2608.24945v2 Recent years have witnessed remarkable achievements of Large Language Models (LLMs) in multiple domains, while the excessive resource requirements of LLMs hinder the deployment on resource-constrained devices. Although model quantization stands out as an effective approach, conventional quantization approaches typically incur severe performance degradation due to uniform bit-width or simple heuristic sensitivity evaluation. In this paper, we propose a novel Fisher information-based Adaptive Mixed Precision Weight Quantization approach, i.e., FAMPWQ, which performs layer-adaptive weight quantization for effective LLM inference on commodity GPUs. First, we propose a system model with a novel Fisher information metric to measure the layer-wise sensitivity to quantization. Second, we propose a reinforcement learning-based bit-width allocator in FAMPWQ, which generates an adaptive bit-width allocation strategy based on the Fisher information sensitivity metric. Extensive experiments on 7 models and 5 benchmarks demonstrate that FAMPWQ significantly outperforms 7 baseline approaches in terms of PPL (up to 3.39 smaller), accuracy (up to 6.87% higher), and LLM-as-a-judge comparison (up to 76% win rate). --- ### When Does Frequency Decomposition Benefit Physics-Informed Neural Networks? A Preliminary Ablation Study Authors: Shubham Rai Published: 2026-08-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.24940v1 Partial differential equations (PDEs) often have high-frequency and multi-scale features that neural networks struggle to approximate. Physics-Informed Neural Networks (PINNs) build the governing equations directly into training, but suffer from spectral bias: they learn low-frequency components faster than high-frequency ones. Techniques such as Fourier feature embeddings and sinusoidal activations address this, but most studies assume they help across the board without checking which spectral regimes actually benefit. We introduce a dual-branch, spectrally-gated architecture (DBSG-PINN) that splits low- and high-frequency components into separate subnetworks joined by an adaptive gate, and use it to run a partially controlled ablation of frequency decomposition and spectral routing. We test this on five one-dimensional benchmark PDEs, ranging from smooth, single-scale problems to oscillatory, multi-scale ones. Frequency decomposition helps most on the spectrally complex benchmarks, cutting relative $L_2$ error by up to $59.2\%$ on a multimodal wave problem, but gives little benefit on smoother PDEs. On one benchmark (1D Wave), it performs substantially worse than a simpler fixed-combination variant. The gate's benefit scales with how spectrally rich the target solution is: the full model's advantage over the ablations is largest on multi-scale benchmarks and smallest (or negative) on single-scale ones, consistent with the gate exploiting frequency structure rather than acting as noise,though we do not directly visualize or quantify its spatial activations in this study. All results come from a single training seed across five 1D benchmarks, so we present this as an exploratory study meant to raise questions rather than answer them, and outline the additional seeds and benchmarks needed to test whether the pattern holds. --- ### ExFold: Unified Expert Folding for Training-Free MoE Prefill-Decode Acceleration Authors: Juntong Wu, Yifei Liu, Junyi Chen, Siqi Fan, Chaoran Feng, Minghao Li, Liujie Zhang, Weihang Chen, Li Yuan Published: 2026-08-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.24938v1 Mixture-of-Experts (MoE) models scale capacity for strong quality while keeping per-token compute bounded through sparse expert activation. Yet low-latency MoE serving is increasingly challenging, because it spans two inference phases with fundamentally different bottlenecks: prefill is dominated by token-wise expert computation, whereas decode is constrained by memory traffic from the batch-wise activated expert set. However, existing training-free acceleration methods optimize only a single resource proxy, either the experts each token executes or the experts a batch activates, and either discard the excluded experts' contribution or leave it only implicitly approximated. In this paper, we propose ExFold, a unified training-free expert-folding framework for jointly accelerating MoE prefill and decode. ExFold casts both prefill and decode as one budgeted output-approximation problem: execute only a phase-specific constrained expert set while projecting the contribution of budget-excluded experts onto retained experts using calibrated scalar projectors. Motivated by the observation that many expert outputs are directionally aligned but differ in magnitude, ExFold calibrates a pairwise scalar-projector matrix on unlabeled data and uses it at inference time to fold excluded expert contributions into retained experts. Under this view, prefill acceleration becomes token-level Top-K folding, and decode acceleration becomes batch-level expert-pool folding. The two phases differ only in how retained experts are selected, while excluded contributions are recovered by one shared folding mechanism. We implement ExFold as a plug-and-play plugin in vLLM, with a lightweight expert-folding CUDA kernel, delivering up to 1.41x TTFT and 2.45x TPOT speedups while retaining about 99% of the original average quality. --- ### Multi-Modal Anomaly Detection: A Survey Authors: Xudong Mou, Zexin Wu, Chuan Luo, Shiru Chen, Xudong Liu, Chunming Hu, Renyu Yang Published: 2026-08-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.24937v1 Multi-Modal Anomaly Detection (MMAD) detects rare abnormal events from heterogeneous data sources and is increasingly used in safety- and reliability-critical applications such as industrial inspection and cybersecurity. Yet the literature is fragmented across domains and modality combinations, and existing surveys usually group methods by architecture rather than by how abnormality is defined and separated in multi-modal settings. We survey MMAD from an assumption-driven perspective. We formalize the problem, identify five intrinsic characteristics underlying its core challenges, and organize prior work into two complementary paradigms. The first, normality-assumption methods, models regularity via representation learning, cross-modal alignment, and knowledge enhancement. The second, anomaly-assumption methods, sharpens decision boundaries through coarse-grained, structural, and semantic anomaly injection. We also investigate how foundation models are reshaping MMAD through scalable pretraining, flexible cross-modal transfer, and emerging reasoning capabilities. Finally, we compile representative benchmarks and evaluation protocols across domains and highlight open problems and future directions for robust, adaptive, and interpretable MMAD systems. --- ### Conditional GraphGANFed: Optimizing Graph-Structured Molecule Generation in Federated Generative Adversarial Networks Authors: Daniel Manu, Abee Alazzwi Published: 2026-08-24 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2608.24610v1 Generative adversarial networks (GANs) have garnered considerable attention in molecular discovery for their ability to generate novel and high-quality molecules. To efficiently train a GAN model while preserving data privacy, GraphGANFed has been proposed to incorporate federated learning and graph convolutional networks into GAN. Yet, GraphGANFed cannot produce synthetic molecules that only optimize a user-defined metric(s) to facilitate the new drug discovery process. To address this issue, we introduce a novel extension to GraphGANFed, namely conditional GraphGANFed (cGraphGANFed), by incorporating the critic network to assess generated molecules using user-defined metric(s). The evaluation results from both the critic network and discriminator are integrated into the loss function of the generator, guiding it to generate novel molecules that maintain similar chemical properties to real ones while optimizing user-defined metrics. Extensive simulations are conducted in two scenarios. First, cGraphGANFed endeavors to optimize all seven commonly used metrics, and the results show that cGraphGANFed significantly outperforms GraphGANFed in Validity and LogP, with a slight advantage in QED, across different settings. Second, cGraphGANFed focuses solely on optimizing QED, and the results show that the synthetic molecules produced by cGraphGANFed can achieve more than 10% improvement in QED than GraphGANFed. Also, the results demonstrate cGraphGANFed has enhanced resilience against mode collapses and performance reduction caused by non-IID data. --- ### Data Mixing as Mixture Experiment: Response Surface Methodology and Optimal Design for Large Language Model Pretraining Authors: Yicheng Mao, Hongru Du Published: 2026-08-24 Categories: cs.AI, stat.ML arXiv: https://arxiv.org/abs/2608.23922v1 Data mixing is a central design problem in large language model pretraining: given a fixed token budget, practitioners must decide how much data to allocate to each domain. Recent proxy-based methods address this problem by training small models on candidate mixtures, fitting a response model, and using the response to select mixtures for larger-scale training. We show that this workflow has the structure of a classical mixture experiment. Under this view, data domains are mixture components, token shares are component proportions, proxy-training runs are experimental design points, and validation loss defines a response surface over the probability simplex. We develop this formulation using sparse second-order Scheffé response-surface models and construct model-robust $\mathcal{I}$-optimal designs for proxy data-mixing experiments. Using RegMix as an empirical case study, we demonstrate how the framework can both interpret observed mixture responses and design more efficient proxy experiments. The Scheffé analysis shows that domain value is strongly relational: several domains that are weak under additive effects become favourable through pairwise interactions, especially through combinations with web-derived text. The sparse Scheffé model preserves mixture rankings across model scales and remains competitive with a flexible machine-learning predictor while providing an explicit decomposition of additive and interaction effects. In a simulation study calibrated to observed proxy-training responses, model-robust $\mathcal{I}$-optimal designs recover the relevant mixture ordering after removing about 25\% of the original proxy runs. These results suggest that LLM data mixing should be treated not only as a prediction problem, but also as an experimental-design problem in which the proxy mixtures themselves can be chosen to improve statistical efficiency. --- ### HAP: Head-Adaptive Visual Token Pruning via Cross-Modal Alignment Authors: Yuanhao Sun, Huawei Ji, Yuan Jin, Cheng Deng, Luoyi Fu, Xinbing Wang Published: 2026-08-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.23921v1 Recent Vision-Language Models encode high-resolution images into long visual token sequences, incurring prohibitive prefill costs. To compress them, existing methods score each visual token by averaging text-to-visual attention uniformly across all heads, which assumes every head matches the query. However, our empirical analysis shows that misaligned heads dominate the average, amplifying background tokens and drowning out fine-grained cues. To address this, we propose PAQ (Prompt-Grounded Attention Quality), a metric quantifying how well each head aligns the prompt with image regions. Built on PAQ, our pruning proceeds in three stages. Given a target FLOPs budget, we first partition the transformer layers into groups and allocate a visual token budget to each. Within each group, we then aggregate per-head attention maps via PAQ-weighted softmax into a group-level matrix. Finally, we score visual tokens by this matrix's magnitude and retain the allocated budget per group. By weighting heads with PAQ, our method scores tokens by attention signals that more faithfully reflect prompt relevance, rather than diluting them through uniform averaging. Across 18 benchmarks, our method delivers state-of-the-art trade-offs. Specifically, on LLaVA-1.5-7B (9 tasks), retaining only \textbf{5.6\%} tokens preserves \textbf{99.1\%} of the original performance, surpassing the strongest baseline AutoPrune by 4.2 points. Code is available in https://github.com/baokou-fw2/HAP. --- ### Wontopos Tablet 2: Measuring Multilingual and Multimodal Memory Retrieval Without Lexical Matching Authors: Sunwoo Kim Published: 2026-08-24 Categories: cs.IR, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2608.23920v1 We measure tablet-2, a production long-term memory engine for language models, on the text benchmarks the field already uses and on cross-lingual retrieval of photographs stored with no text at all. Its retrieval path contains no lexical matching, no keyword scoring, and no language model of its own. On LongMemEval-S (500 questions) it scores 95.7% (93.4, 97.1); on BEAM-1M (700 questions, 2.21M stored memories) 67.5% (64.8, 70.2). Those are question-sampling intervals, not the run-to-run spread, which is an order of magnitude narrower. Most of the paper is about how little they mean alone. Holding engine, corpus, settings and judge fixed, changing only the reader moves LongMemEval-S by 2.0 points; changing only the re-ask budget moves BEAM-1M by 8.9. Neither is stated in the reports we compare against, and the second exceeds most gaps there, so we give that table as a placement and not a ranking. For the multimodal axis we run two controls. Against BM25, configured as strongly as we could, we reach 95.2% mean recall@5 over 70 store-and-query language cells where BM25 reaches 19.0% and is exactly zero in 54. On captionless photographs a lexical method has no document to score at all. Open dense baselines on 300 Crossmodal-3600 photographs in 14 languages show that density confers no language independence: one scores 91.0% on English and 4.7% on Russian from identical image vectors, and a multilingual variant collapses on Telugu and Swahili. Our spread across languages is 14.0 against their 27.5 and 27.7. Three results run against us and are reported at equal weight: low-resource languages degrade sharply (Swahili 53.0%, Telugu 64.0%), attaching captions lowers cross-lingual retrieval by 11.4 points, and one setting omitted into one stage of our own retrieval cost 37 points of Korean top-1 accuracy while leaving nine languages untouched. --- ### MARS: Multi-Specialist LLM Relay System for Competitive Programming Authors: Andrei Mikhailov, Mikhail Burtsev, Alsu Sagirova Published: 2026-08-24 Categories: cs.AI, cs.MA, cs.PL arXiv: https://arxiv.org/abs/2608.23918v1 Large Language Models excel at code generation, yet competitive programming exposes a persistent failure mode: existing multi-agent pipelines distribute work over generic planner, coder, and debugger roles and delegate the choice of algorithmic technique to the backbone alone. We present MARS (Multi-Agent Relay of Specialized LLMs), a prompt-only framework in which each agent is a topic specialist---dynamic programming, graphs, strings, geometry, and so on---grounded by retrieval-augmented generation over an algorithm-theory corpus. Given a problem, retrieval selects a small team of relevant specialists; a starter writes an initial C++17 solution, and each subsequent turn runs the candidate against public examples in a sandbox, lets the active specialist keep, repair, or hand off the draft, and forwards a structured packet to the next specialist. A single infrastructure-fixer pass normalizes boilerplate at the end. On the CodeContests test split with Gemma 4, MARS reaches $0.624 \pm 0.006$ pass rate at $2.3$ recorded pipeline stages per task ($+14.4$ percentage points over direct prompting), closing most of the gap to CodeSIM ($0.731$) at $3.3{\times}$ lower wall-clock cost and substantially smaller variance in per-task token spend. The source code is available on GitHub: https://github.com/fckand/mars. --- ### GATNextHop: A GAT for Shortest Path Routing with Cross-Topology Generalization Authors: Chia-Hong Chou, Katerina Potika Published: 2026-08-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.23917v1 Common shortest-path algorithms, such as Dijkstra's (SPF), that OSPF uses, provide exact routing solutions but must be recomputed for each network topology, limiting scalability in dynamic or large-scale networks. This paper proposes the GATNextHop model to determine whether a Graph Neural Network, namely the Graph Attention Network, can approximate shortest paths and generalize across topologies. By training on synthetic graphs and evaluating on real-world Internet Service Provider networks from the Internet Topology Zoo, we aim to benchmark our model's ability to learn routing heuristics that transfer across network structures. Performance will be evaluated in terms of accuracy, inference speed, and generalization, comparing the GNN against Dijkstra's algorithm to quantify trade-offs between learned and classical routing approaches. --- ### The Loss Floor of Denoising Score Matching: Fisher Geometry from Schrödinger Bridges Authors: Avinash Raju, Kai Zhang Published: 2026-08-24 Categories: cs.LG, cond-mat.stat-mech arXiv: https://arxiv.org/abs/2608.23916v1 Denoising score matching trains diffusion models by regressing onto a conditional score, although generation ultimately requires the marginal score. The two objectives share the same population minimizer, but the conditional target remains random at fixed noisy state and introduces an irreducible excess in the training loss. We isolate this excess and show that, for a general corruption kernel under mild regularity assumptions, it is exactly the trace of the Fisher--Rao metric of the conditional endpoint family, integrated along the diffusion trajectory. This gives an exact conditional-variance decomposition of the denoising objective and identifies the information geometry observed in diffusion latent spaces as an intrinsic component of the training loss. We derive the result from a Schr"odinger bridge variational principle, in which the ideal objective arises as excess path-space relative entropy. For corruption diffusions, the Fisher term is proportional to the rate at which the noisy state loses mutual information about the clean data, separating the loss floor into an information flow determined by the data and a weight determined by the corruption schedule and objective. In the Gaussian case, this yields a closed form for the floor, recovers reparametrization invariance of the continuous-time objective, and relates its high-SNR divergence to the information dimension of the data. Finally, we show that raw losses obtained with different noise ranges or weightings need not rank models consistently because they contain different additive floors, and contrast the second-order geometry seen by training with the third-order conditional statistics entering numerical sampling error. --- ### PROOF-Gen: From Optimized Data to Better Distillation Authors: Anh Ta, Junjie Zhu, Shahin Shayandeh Published: 2026-08-24 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.23911v1 Supervised fine-tuning on teacher-generated trajectories is the standard first stage for distilling tool-calling capabilities into deployable models. Post-training pipelines that drive shipped tool-calling agents re-run this stage on a daily or weekly cadence, paying the frontier-teacher cost each cycle, yet the mechanism is generate-and-filter (keep the teacher's passing trajectories, discard the rest) and each cycle leaves behind the same hard scenarios because failures supply no signal. On τ2-bench, 57% of teacher trials fail, two-thirds of them near-misses (most tool calls correct, undone by one decisive error). We introduce PROOF-Gen (Per-scenario Reflective Optimization to Overcome FailedGeneration), which recovers golden trajectories from these failures via per-scenario prompt optimization. For each failed task, a reflector analyzes the execution trace and evaluation feedback, then writes corrective guidance that steers the teacher to a passing trajectory. The guidance is stripped before training, so the student learns from clean demonstrations with no task-specific scaffold. On τ2-bench, per-scenario optimization recovers 93% of failed scenarios. Fine-tuned on the combined data, Qwen3-4B-Instruct-2507 improves from Pass^1=0.132 to 0.529 and Gemma 4 E4B-it gains +7.2pp on BFCL v4 multi-turn. In a deployed pipeline, the method lifts trajectory quality by +6.3pp goal completion and transfers to a deployed on-device model (+1.5pp goal completion; +1.7 to +5.0pp across response-quality metrics), with positive transfer in every locale (non-English average +1.48pp). --- ### Partial Optimal Transport on the Circle for All Transported Masses in O(N log N) Authors: Soheil Kolouri Published: 2026-08-24 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2608.23910v1 Partial optimal transport compares two measures while leaving part of the mass unmatched, which is what makes it robust to outliers, occlusion, and clutter. The quantity of interest is usually the whole profile - the optimal cost at every transported cardinality - because the right amount to transport is rarely known in advance, and on the real line the PAWL algorithm returns that profile in $O(N\log N)$. Much data is periodic rather than linear: angles, phases, orientations, time of day, hue, and every direction obtained by projecting onto a great circle. On the circle the same problem acquires a global circulation, or equivalently an optimized cut, which the naive exact method handles by running the line algorithm once per support gap, at $O(N^{2}\log N)$. We show that this factor $N$ is unnecessary. The line structure survives in cut-free form, and a free-gap invariant supplies, at every step, a cut at which all previous local updates remain valid line updates. This yields PAWC: an exact $O(N\log N)$ time, $O(N)$ memory algorithm returning all $K+1$ costs, nested active sets and plans in one run, together with a single gap that is simultaneously optimal for every cardinality. Slicing over great circles extends it to $\mathbb{S}^{d-1}$. Empirically the whole profile costs $0.56$ms at $N=4096$ against $1.5$s for a single transported fraction from a general solver; on occluded, cluttered mpeg-7 shapes, holding the descriptor fixed and varying only the cost, it retains $66\%$ of the clean-data retrieval score against $16\%$ for balanced circular OT, and on $\mathbb{S}^{2}$ it halves the fitting error of spherical sliced Wasserstein against contaminated targets, synthetic and real. Code is available at https://github.com/mint-vu/Partial_Wasserstein_on_Circles. --- ### Retrieval-augmented generation vs. deterministic tax computation in multi-agent financial advisory: A 2x2 factorial experiment Authors: Aryan Brar, Justin Du, Avery Lor, Kylie Seto, Eric Taylor Published: 2026-08-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.23908v1 Tax-loss harvesting demonstrates consistent benefits to long-term portfolio growth; yet implementing it efficiently often involves complex considerations that are specific to the holdings within that portfolio and the individual who owns it. We introduce a custom capital gains calculation engine and a RAG-retrieved vector store of market advisory reports to provide context for a multi-agent trade recommendation system. We investigate the effects of each context provider on the quality of recommendations, measured by relative capital gains incurred during portfolio liquidation. A 2x2 repeated-measures ANOVA revealed a significant main effect of the tax optimization engine ($F(1,29) = 9.17$, $p = .005$, $η^2_p = .240$): enabling the engine reduced tax savings by approximately 55 percentage points relative to the no-engine conditions. The RAG main effect was not significant ($p = .841$), nor was the interaction ($p = .553$). The RAG-only condition achieved the highest descriptive mean tax savings (47.7%), and the baseline condition performed second-best (30.6%), suggesting that the pre-trained language model's internalized financial knowledge may be sufficient for competent tax-loss harvesting recommendations without explicit tooling. These results indicate that augmenting LLM agents with domain-specific computation engines does not guarantee improved performance and may introduce conflicting optimization signals. --- ### Quantifying System-Level Harms from AI Adoption in Complex Sociotechnical Systems Authors: Paul Vautravers, Oliver Chalkley, Gabriel Downer, Kate S, Damian Ruck Published: 2026-08-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.23906v1 Artificial Intelligence (AI) is increasingly integrated into complex sociotechnical systems, including Critical National Infrastructure (CNI), where harms emerge from interactions between technical, human, and organisational elements. Yet current AI evaluation remains model-centric, offering little insight into how observed behaviours might translate into system-level risk. We propose a framework that links structured hazard analysis, component-level testing, and probabilistic system modelling to bridge this gap. By providing a traceable pathway from model behaviour to system-level outcomes, the framework enables practitioners to answer the "so what?" of AI failures, quantify their systemic impact, and move toward evidence-based and anticipatory governance of AI in complex systems. Applied to the UK's Real Time Gross Settlement (RTGS) system as an illustrative worked example, we derive AI-driven loss scenarios using Systems Theoretic Process Analysis (STPA) and examine adversarial manipulation of LLM-based trading as one such loss scenario. Component-level experiments show that simple adversarial inputs induce measurable behavioural shifts where AI recommendations are followed. Under the component-to-system mapping used here for a financial contagion model, these shifts alter system resilience, increasing bank failures and lowering the threshold at which shocks lead to cascading disruption, particularly under widespread or monopolistic AI adoption. --- ### Continual Visual Learning under Evolving Semantic Concept Shift Authors: Ismail Lamaakal, Chaymae Yahyati, Yassine Maleh, Khalid El Makkaoui, Ibrahim Ouahbi Published: 2026-08-24 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2608.23903v1 Visual foundation models are commonly adapted under the assumption that the appearance of incoming data may change while the semantic meaning of the prediction task remains fixed. In long-lived visual systems, however, taxonomies, policies, and concept definitions can themselves evolve, causing the same visual evidence to require a different interpretation. We study this setting as evolving semantic concept shift and introduce SemReWrite, a framework for selectively updating obsolete visual--semantic mappings while preserving knowledge that remains valid. SemReWrite represents changes between old and revised semantic specifications, combines semantic discrepancy with sparse revised supervision to localize affected visual regions, and uses an input-dependent low-rank rewriting mechanism together with structured semantic memory, preservation, and obsolete-decision suppression. We further introduce EvoShift-Bench, spanning ImageNet, iNaturalist, CUB-200-2011, and DomainNet, with semantic transitions including class split, merge, boundary revision, insertion, partial redefinition, recurrence, and mixed semantic--appearance shift. To explicitly evaluate selective semantic revision, we introduce Rewrite Accuracy (RA) and Preservation Accuracy (PA) for affected and unaffected regions, respectively, Obsolete Retention (OR) for measuring residual outdated semantic associations, and the Selective Revision Score (SRS), which jointly summarizes rewriting and preservation performance. Experiments show that SemReWrite achieves a stronger balance between learning revised semantics and retaining unaffected knowledge than prompt replacement, conventional fine-tuning, parameter-efficient adaptation, and continual-learning strategies. --- ### BenchBench-Protocol: Evaluating Real-World Wet-Lab Protocol Reasoning and Modification Authors: Aditya Sivakumar, Ashu Singhal, Nicholas Larus-Stone, Nithin Parsan Published: 2026-08-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.23898v1 We introduce BenchBench-Protocol, a benchmark for large language models of 149 protocol-modification tasks recovered from modifications that scientists made to published protocols during real experimental work. Adapting a published protocol to a new experiment is a routine task for a wet-lab scientist, and a correct modification requires accounting for prior choices and downstream steps. Recent life-science benchmarks have moved toward open-ended, rubric-graded tasks, but tasks are typically elicited from experts rather than reconstructed from real-world modifications. BenchBench-Protocol tasks are derived from differences between a published protocol and a version a scientist modified, which provides the basis for the query and the weighted rubric elements for a correct response. The benchmark draws from 96 source protocols across nine domains of wet-lab biology and only includes tasks rated highly after review by domain experts. We evaluate nine closed and open models; Claude Opus 5 scores highest at 59.2% normalized rubric score, with other models between 34.1% and 47.1%, and the benchmark remains unsaturated when taking the best of ten attempts. As models are increasingly helpful in life-sciences research, evaluating them on routine wet-lab tasks becomes correspondingly important. We present BenchBench-Protocol as both a grounded assessment of wet-lab reasoning and evidence for the utility of real-world experiments to construct benchmark tasks. --- ### Names Can Hurt: Spotting Slopsquatting Risks Caused by Package Name Hallucinations in Local Coding LLMs Authors: Akash Raj, Sargam Sahu Published: 2026-08-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.23897v1 When a code generating language model fabricates a Python package name, an adversary who has pre-registered that name on PyPI can convert that hallucination into a supply chain compromise. This event has been termed as 'slopsquatting'. We propose a two layer detector to counter this issue. The first layer performs a deterministic PyPI existence check. The second is a Random Forest classifier trained on ten features derived from the package name and its PyPI metadata. An import name reconciler bridges the two, resolving cases such as 'import cv2' versus 'pip install opencv-python' without a security bypass. The detector is embedded in a LangGraph state machine that retries at escalating temperatures and, on repeated failure, routes to a stronger fallback model. Across 300 curated prompts, the pipeline produces hallucination free code on 76% of runs. The primary exhausts its retry budget on 28.7%; intra model retries recover roughly a quarter of those, and cross model fallback recovers a further 16.5% of the remainder. Four findings have been observed. First, half of the flagged hallucinations are packages already registered on PyPI, as low quality lookalikes of well known projects, caught by the classifier rather than the deterministic layer (e.g., pil, faiss, tabula, haystack). Second, hallucination rate scales almost linearly with prompt adversariality, from 0 to 10% on routine coding to 40 to 73% on slopsquat baits. Third, the weaker primary refused 6 of 10 direct baits unaided, suggesting recent instruction tuning provides a baseline defense. Fourth, when primary and fallback share a model family, approximately 84% of primary failures recur on the fallback, motivating cross family pairing. A user study (n = 24) reports mean satisfaction 4.4 out of 5 and 21 of 24 stated adoption intent. --- ### Learning the Kohn-Sham map with neural operators for quasi-linear scaling density functional theory Authors: Danish Khan, Maurice D. Hanisch, Nikolai Argatoff, Evan Xie, Sandeep Sharma, Anima Anandkumar Published: 2026-08-24 Categories: physics.chem-ph, cs.AI arXiv: https://arxiv.org/abs/2608.23895v1 Kohn--Sham density functional theory (DFT) underpins electronic-structure simulations, but repeated orbital diagonalizations lead to cubic scaling, restricting quantum calculations to modest scales only. Eliminating these auxiliary orbitals while retaining Kohn--Sham accuracy is the central goal of orbital-free DFT, but both analytical and machine-learning methods have so far fallen short. Prior learning approaches either try to learn the variational kinetic-energy functionals, which are ill-conditioned, or directly predict the ground state, which extrapolate poorly to larger systems. Instead, we identify the Kohn--Sham map as the right learning target for orbital-free DFT. It maps a Kohn--Sham potential directly to the corresponding density and noninteracting kinetic energy, quantities otherwise obtained through an orbital diagonalization. Focusing on the density component in this work, a domain-invariant $\mathrm{SE}(3)$-equivariant Fourier neural operator learns to predict it from the potential as input on real-space grids, enabling stable quasi-linear scaling SCFs. Trained jointly on 8,504 molecules and solids, a single model generalizes to out-of-distribution organic molecules, insulators, and metals. For the first time, the same method converges SCFs across these systems without explicitly constructing Kohn--Sham orbitals, while reproducing densities, electronic spectra, and structural observables at Kohn--Sham DFT accuracy. Linear-scaling SCFs additionally allow converging magnesium dislocation densities containing up to 82,500 valence electrons on a single GPU. --- ### Provenance Guided Incremental Learning Under Evolving Concept Definitions Authors: Ismail Lamaakal Published: 2026-08-24 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.23893v1 Learning systems deployed over long periods must adapt not only to statistical changes in incoming data, but also to revisions of the definitions that generate their prediction targets. Conventional concept-drift methods typically infer such changes from observations or prediction errors, even when the underlying policy, rule, or query has been explicitly modified. This paper studies rule-induced concept shift, where the target-defining concept is revised directly, causing previously stored instances to acquire different semantic labels without requiring any change in their observed data. We introduce a provenance-guided incremental learning framework that compiles consecutive concept definitions into a structured rule delta, traces the changed components through historical provenance, certifies records whose previous labels remain valid, and restricts reevaluation to a localized candidate region. Executable revisions are relabeled automatically, ambiguous cases are handled through selective supervision, and the resulting changes are used for incremental predictor repair. A versioned concept memory further supports recurring definitions. We also introduce RuleShift-Bench, spanning financial, demographic, cybersecurity, and graph-structured data with threshold, predicate, logical, relational, recurring, and mixed concept revisions. Across the benchmark, provenance-guided repair attains 92.3% accuracy and 90.2% Macro-F1 while reprocessing 14.7% of the historical collection and retaining 94.6% of affected records. Its average update latency is 179s compared with 993s for complete relabeling and retraining. The results demonstrate that an explicit concept revision can be exploited as a data-maintenance signal, allowing learning systems to update the supervision and predictive state that depend on the change while preserving knowledge that remains valid. --- ### A Mathematical Theory of Interpretation: Rational Entropy, Spectral Readout, and Confusability as a Resource Authors: Blake Reynolds Published: 2026-08-24 Categories: cs.IT, cs.AI arXiv: https://arxiv.org/abs/2608.23892v1 This article presents the abridged core of \emph{A Mathematical Theory of Interpretation} (MTI), which treats interpretation as observer-relative spectral measurement under an access structure. MTI makes interpretation a method-design problem: access, query, utility, and medium determine what an observer can select, identify, communicate, or refuse. On a learning-invariant Hilbert realization, Rational Entropy measures residual uncertainty across knowledge, utility, and medium. In the finite-effective regime, we classify its zero set. Pairwise confusability is equivalent to uniform atomic collapse, while a unique utility maximum can select one atom even when other zero-cost states remain non-atomic. This reverses the usual zero-error role of confusability: agreement in at least one observer direction excludes unresolved multi-atom readings, while the joint label preserves identification. The corresponding free-design capacity is the product of all but the smallest direction budget. A four-condition certificate characterizes sharp, decodable, medium-faithful, and order-independent readout on a finite commuting code sector and returns typed obstructions when those guarantees fail. Together, these results establish MTI as a theoretical basis for constructing interpretation methods with explicit access assumptions, guarantees, and failure modes. --- ### Dimensionless Controls of Plasticity Under Alternating Tasks: From Evolutionary Biology to Continual Learning Authors: Owen Skriloff Published: 2026-08-24 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2608.23889v1 Plasticity under changing environments is central to both evolutionary biology and continual learning. Motivated by recent work on genotype--phenotype maps, we study a minimal deep-learning analogue where a network is trained alternately on two Boolean label sets, and ask which biological controls of plasticity survive the translation to gradient descent. Reinterpreting four proposed biological factors as quantities of training dynamics, we find the system reduces to two dimensionless controls: the task disagreement $r$, the fraction of disagreeing labels, and the reach $ηT$, the product of learning rate and switching period. We derive two bounds on plasticity: $r$ alone fixes an extremal geometric floor on the utopia distance, while $r$ and $ηT$ jointly bound forgetting. Across 9,720 trajectories, an ANOVA confirms that $r$, $η$, and $T$ dominate, while the effect of neutral-set size (emphasized in the biological setting) is negligible. The optimal reach itself follows an approximate inverse power law $ηT^{*}\propto r^{-1.18}$, yielding a heuristic that sets the optimal reach $ηT^*$ from the task disagreement alone. The analogy that survives is therefore dynamical rather than geometric, and our setting enables a view of plasticity through the lens of other driven systems in physics and engineering. --- ### A tale of perfect fit and phantom optima: how data-driven models can fail in real-time optimization Authors: Prithvi Dake, Rahul Bindlish, James B. Rawlings Published: 2026-08-24 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2608.23885v1 Real-time optimization (RTO) relies on process models to locate economically optimal operating conditions. Because developing first-principles models requires significant process knowledge, data-driven alternatives are increasingly attractive. Modern machine-learning models can fit historical plant data accurately and often pass standard validation tests. Whether such models can be trusted for economic optimization, however, remains unclear. We investigate this question using a vinyl acetate monomer benchmark process with a unique, well-conditioned economic optimum. We train a structured hybrid model that combines known mass balances and thermodynamics with a neural-network closure for unknown kinetics, and a fully data-driven neural ordinary differential equation (ODE) model. Both models reproduce plant measurements accurately and exhibit little variation in predictions across random initializations. Yet their economic optima differ substantially from that of the plant. Where the plant returns a single optimum on multistart search, the trained models return many phantom optima. We further show that the training optimizer alone can be yet another source of error. Even with noise-free data and initialization at weights that recover the plant optimum, stochastic gradient training can drift to weights that yield substantially worse RTO solutions. The identified model is thus an artifact of the training optimizer as well as the data. These results demonstrate that a good predictive fit of all available measurements does not guarantee reliable economic performance. A data-driven model for RTO should at least be required to recover the optimum on a decision-oriented benchmark like the one developed here before being considered for plant testing and application. --- ### Native-Space 3D CarveMix for Multi-Site T1w Stroke Segmentation Authors: Dexter Wen Jie Teo, Kumaradevan Punithakumar Published: 2026-08-24 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.23882v1 Segmenting ischemic stroke lesions on T1-weighted (T1w) MRI acquired across different scanners and protocols without intensity standardization is difficult because lesions are subtle and share intensity characteristics with cerebrospinal fluid. Standard deep learning architectures trained across multiple centers plateau around Dice 0.66, with acute lesions ($\le 7$ days post-stroke) performing substantially worse due to severe sample scarcity. We combine a MedNeXt-L ($k=5$) backbone with on-the-fly 3D CarveMix augmentation that pastes real lesion patches into healthy brain regions during training. By generating synthetic lesion placements dynamically within each fold with subject-level split isolation, the model sees more diverse lesion patterns without requiring pre-generated copies on disk. We evaluate on 1,453 native T1w scans from 55 clinical centers in the ISLES 2026 challenge. Our method achieves a mean 5-fold cross-validation Dice of 0.648 at 500 epochs, a +0.018 improvement over the MedNeXt-L backbone at a matched training budget (0.630) --- ### LG-GER: Language-Guided Group Emotion Recognition via Multimodal Evidence Distillation Authors: Ahmed Shehab Khan, Zhiyuan Li, Yan Tong Published: 2026-08-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.23880v1 Inferring the collective emotional state of a group of people from a single image, a task known as group emotion recognition (GER), requires integrating spatially distributed cues such as faces, poses, interactions, and scene context. Current methods rely on detector-driven multi-stream pipelines. These are trained with only image-level supervision that lacks guidance on which regions matter or how strongly each contributes. We propose LG-GER, a language-guided distillation framework that uses a multimodal large language model (MLLM) to generate dense, spatially grounded evidence, i.e., bounding boxes paired with emotion signals and confidence scores, for the training images. This structured evidence is distilled into a single vision-language model (VLM) backbone through four complementary losses: classification, region-text grounding, spatial emotion, and spatial confidence regression. At inference, LG-GER requires no detectors, no MLLM, and no multi-stream fusion, making GER practical for real-time and resource-constrained deployment. LG-GER has been evaluated on two benchmark GER datasets (GroupEmoW and GAF~3.0) and achieves competitive or superior results compared to state-of-the-art methods that require detection and multi-stream processing at inference. --- ### Spatiotemporal Distillation via Recurrent Bottlenecks for Aortic Tracking Authors: Dexter Wen Jie Teo, Nairouz Shehata, Herve Lombaert Published: 2026-08-24 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.23879v1 Cardiac cine-MRI serves as a direct visual indicator of cardiovascular hemodynamics by capturing the continuous wall motion of the aorta. Quantifying these dynamic structural changes across the cardiac cycle is essential for measuring aortic distensibility, a primary marker of arterial stiffness. However, standard 2D segmentation networks focus on each frame independently. Consequently, when rapid systolic flow temporarily obscures the aorta's boundaries, this lack of continuous context results in frame-to-frame tracking dropouts and boundary inconsistencies. Spatiotemporal ($2\text{D}+t$) networks can enforce temporal consistency across the sequence but suffer from a scarcity of expert annotations. To address this, we present a semi-supervised spatiotemporal ($2\text{D}$ to $2\text{D}+t$) knowledge distillation framework exploiting the cardiac cycle. The framework distills a spatial teacher's expertise into a spatiotemporal student network by executing a dynamic latent interception, pairing a recurrent spatiotemporal bottleneck with a residual spatial bypass. Our model selection strategy applies a baseline validation threshold ($\text{DSC} \ge 0.50$) prior to selecting the epoch that maximizes anatomical consistency. This strategy enables the spatiotemporal student model to achieve superior surface tracking accuracy ($\text{NSD@1mm} = 92.3\% \pm 0.2\%$) and high structural reliability ($\text{Frac}_{2\text{CC}} = 99.2\% \pm 0.6\%$), reducing population-wide structural anomalies by over 56\% compared to a 2D nnU-Net baseline. --- ### Every Layer Counts: An Exponential $L_2$ Depth Hierarchy for ReLU Networks Authors: Itay Safran Published: 2026-08-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.23877v2 We prove a depth hierarchy for ReLU neural networks in which every additional ReLU layer can save exponentially many neurons. For all $k\geq2$, we construct a globally $(0,1)$-valued, $1$-Lipschitz function realized by a depth-$(k+1)$ network of width $\mathcal{O}(d^4)$, whereas any depth-$k$ network with unrestricted weights and width at most $\frac{2^d}{2d(k-1)}$ has squared $L_2$ error at least $1/24$ under an absolutely continuous distribution supported at exponential distance from the origin. To the best of our knowledge, this is the first exponential hierarchy across all adjacent fixed depths, and the first exponential separation for ReLU networks between two fixed depths whose shallower network has depth at least $3$. The lower bound also immediately yields the corresponding hierarchy for exact computation. Moreover, the case $k=2$ gives a compactly supported separation between depths $3$ and $2$ with unrestricted shallow-network weights, answering a question raised by Safran, Eldan, and Shamir (2019). The distribution used in our construction nevertheless has all its mass at exponential radius, placing the hierarchy outside the regularity regime in which such a separation would imply major threshold-circuit lower bounds. We also prove an exact separation for a more regular target, which is globally $(0,1)$-valued and $\mathcal{O}(\sqrt d)$-Lipschitz and maps the unit hypercube onto $(0,1)$. It is computed by a polynomial-width depth-$4$ network, whereas any depth-$3$ network agreeing with it on the unit hypercube requires exponentially many first-layer neurons, even with unrestricted weights. --- ### AI Finds A Way Authors: Aaron Dharna, Cong Lu, Ryan Sullivan, Joel Lehman, Victoria Krakovna, Jeff Clune Published: 2026-08-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.23875v2 Artificial Intelligence (AI) algorithms frequently learn creative and unexpected solutions, surprising even expert researchers who develop and study them. They often astonish practitioners by discovering unanticipated behavior, exploiting loopholes in reward signals, or spontaneously uncovering previously unknown scientific phenomena. However, accounts of such unconventional behavior across machine learning are seldom formally documented. This work presents 26 curated firsthand anecdotes from various machine learning subfields representing the work of over 100 researchers. These anecdotes showcase the capability of modern AI systems to circumvent human-imposed design limitations and discover unexpected solutions to the tasks we train them on. Furthermore, these accounts are particularly important for the safety of future AI systems. They illustrate the fundamental challenge of aligning models with human values without diminishing their creativity, so they can make surprising discoveries without producing surprising, potentially harmful outcomes. The paper first details AI achieving superhuman success through reinforcement learning across many challenging domains. However, reward-driven optimization can fail when the model learns to hack an underspecified reward or unarticulated constraint. We then present case studies suggesting that harnessing internet-scale foundation models (FMs) has not resolved these fundamental challenges and, in fact, can supercharge them. Nevertheless, we argue that these same learning dynamics can be harnessed to accelerate scientific discovery. Finally, we hope this work provides a consolidated resource to inform future research and demonstrates that the tendency toward unexpected behaviors is commonplace in modern AI, highlighting the need to anticipate and manage AI's capacity for innovative, yet unpredictable, solutions. (abstract abridged) --- ### Differential Learning for Robust Prediction of Thermal Stability with Application to Energetic Materials Authors: Megan C. Davis, R. Seaton Ullberg, Jeremy N. Schroeder, Andrew H. Salij, Marc J. Cawkwell, Christopher J. Snyder, Ivana Matanovic, Wilton J. M. Kort-Kamp Published: 2026-08-24 Categories: physics.chem-ph, cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2608.23874v1 Predicting thermal stability during handling and storage is essential for the design of safe and reliable energetic materials. However, experimental measurements vary significantly across laboratories due to differences in protocols and analysis methods, making it difficult to train reliable predictive models. We address this challenge through differential learning. Rather than predicting absolute decomposition temperatures, we instead train message passing neural networks to predict relative differences between pairs of molecules. This approach reduces sensitivity to systematic experimental errors and achieves >85% accuracy in ranking compounds by thermal stability, outperforming conventional regression methods on the same heterogeneous dataset. To understand what drives these predictions, we compare neural network models with interpretable alternatives built from descriptors derived from ab initio calculations and cheminformatics software. This analysis identifies bond dissociation enthalpy as a key determinant of thermal stability rankings, providing further insight into the complex chemistry of thermal decomposition. The differential learning framework generalizes across model architectures, from graph neural networks to classical descriptor-based approaches. Our results demonstrate that learning relative properties rather than absolute values offers a practical solution for modeling noisy experimental data, with direct applications in materials design where thermal stability predictions inform safety protocols. --- ### Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors Authors: Joshua Penman Published: 2026-08-24 Categories: cs.AI, cs.CL, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.23873v3 Everything a language model sees is tokens. The serving stack knows what each span is -- user input, tool output, instructions -- but the model must keep track of that itself, and can lose track or be confused: text can be written to read like anything. Prompt injection is a natural exploit of this phenomenon. By scrambling the model's understanding of span identity, an attacker can induce unwanted and dangerous actions. Adding a non-textual channel to the model's input -- a way to communicate span identity beyond text -- mitigates this class of attack. We thus introduce a general steering technique called Semantic Overlays: small learned adapters applied at chosen prefill positions to a frozen model's residual stream. Laying an overlay over a span creates an out-of-band annotation channel that cannot be replicated by tokens. Unlike steering vectors, Semantic Overlays are trained, adaptable, and selectively applied. An overlay can encode complex semantics that reshape how the model perceives the marked span: asked to copy a code snippet under an overlay asserting a different programming language, the model rewrites the snippet in the asserted language. Overlays compose, allow transparent reading of underlying content, and can carry complex payloads -- including imperatives the model will follow. An overlay which marks a span as "non-executable" defends against the broad class of prompt injections that add instructions in untrusted context. We report strong results on five prompt injection benchmarks: SEP separation rises from 24.3% to 99.0% with utility unchanged (our scoring rule; we correct a defect in the published grader), TensorTrust attack success falls from 34.8% to 6.2%, AlpacaFarm from 99.0% to 0%, and the overlay beats every published PIArena defense that leaves the model able to answer -- while marked spans stay readable, all at >95% character similarity to the original. --- ### Granite.Trust Policy Tools: Shareable, Actionable Policies for Generative AI Applications Authors: Nathalie Baracaldo, Nicolas Mello, Kush R. Varshney, Heiko Ludwig, Kate Soule, David Cox Published: 2026-08-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.23870v1 When it comes to safety policies for generative AI, one size does not fit all. Each organization and use case needs to mitigate different risks depending on the application context, regulatory environment, organizational values, and user personas. Yet, existing policy specification approaches are designed for traditional access control and fail to capture the nuances of GenAI application: the enforcement of content-based constraints. We present two contributions to address this gap: (1) the Actionable Policy schema, a YAML-based format for specifying what model responses can and cannot contain. The schema enables exception-based policy governance, proposing exceptions to track policy violations; (2) synthetic data generation pipeline that produces policy-aligned training data for model alignment and testing, and a set of tools to help define the schema and enforce policy. Together, these enable organizations to specify policies once and enforce them throughout the GenAI application lifecycle: from model alignment to runtime monitoring. The Actionable Policy schema, example policies, and tools are available as open source: https://github.com/ibm-granite/granite.trust.policy-tools We welcome new ideas, contributions and feedback. --- ### Gen2Physics: Grounding Generated 3D Meshes in Physics via Multi-View Material Decomposition Authors: Mauro Comi, Jordi Serrano Berbel, Kevis-Kokitsi Maninis, Philipp Henzler, Manuel Sanchez Published: 2026-08-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.23869v1 While state-of-the-art generative models produce high-fidelity 3D meshes, these outputs lack the physical properties required for interactive simulation, gaming, or robotics. We introduce Gen2Physics, a unified and automated framework that grounds generated meshes in physics by automatically decomposing them into their constituent material components. Unlike prior approaches, which focus on volumetric representations incompatible with standard physics engines, Gen2Physics operates directly on meshes to produce immediately simulation-ready assets. Our pipeline integrates a fine-tuned Vision Transformer for dense material segmentation, a robust 2D-to-3D consistency projection, and a Vision-Language Model (VLM) guided refinement that leverages contextual reasoning to assign physical properties and infer internal geometry (solid vs. hollow). By converting surface patches into volumes with distinct densities, our method enables physically plausible dynamic simulations. Experimental results on the ABO-500 and PartNet-Material benchmarks demonstrate that Gen2Physics more than doubles the material segmentation accuracy of prior physics-grounding pipelines (15.6 to 48.3 mIoU), while matching the mass-estimation accuracy of volumetric methods and being the only approach to output watertight per-material sub-meshes. --- ### Markets, Not Planners: Decentralized Orchestration of LLM Agents with Private Information Authors: Xiao Liu, Haoyang Li, Songwei Li, Hongbo Fang, Fengli Xu, Feng Shi, James Evans Published: 2026-08-24 Categories: cs.MA, cs.CL arXiv: https://arxiv.org/abs/2608.23867v1 As LLM agents proliferate, built by different parties and with different capabilities and costs, orchestrating them is more like assembling labor across the economy than a computer calling a subroutine. Existing orchestration is typically centralized, with a single planner assigning every task, but this creates a bottleneck as agent pools grow, requires private information (e.g., agents' execution costs), and can easily be manipulated, such that a single inserted preference nearly doubles a favored agent's task share under a centralized LLM allocator. We introduce AgentLance, a repeated labor market in which agents bid on tasks using their private costs and self-maintained strategy notes, an allocator selects winners from bids and public reputation records, and a VCG-style payment rule rewards cost-aware bidding. Complex tasks are handled by hierarchical delegation: winning agents can decompose work and subcontract it through the same mechanism. Across mathematical reasoning, code generation, knowledge-intensive QA, and agentic tasks, AgentLance matches agents to their specializations, shifts work toward cheaper agents as cost sensitivity rises, and consistently outperforms single-model, centralized-orchestration, and market baselines. Diagnosing market failures, including inaccurate cost self-estimation and sub-optimal bidding, then correcting them in controlled experiments yields further gains, charting a path toward more efficient agent economies. --- ### AffineTok: Semantic Affine Consistency for Diffusion-Friendly Visual Tokenizer Authors: Junqiu Yu, Pandeng Li, Yikai Wang, Jiaxing Zhao, Yujie Wei, Kaixun Jiang, Quanhao Li, Hongtao Yu, Zhihang Liu, Zhaohe Liao, Junjie Zhou, Yun Zheng et al. Published: 2026-08-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.23864v1 Visual tokenizers increasingly inject semantic supervision into latent spaces to make downstream diffusion easier. Yet how these semantics should be organized to facilitate denoising remains underexplored. In this paper, we define the semantic recovery objective: the denoising process should recover the semantic content of the clean image from noisy latent, and a good tokenizer should make it easier. Existing approaches train a projector to predict the semantics directly from the noisy latent. We argue that this predicts the average of clean-image semantics, whereas what really needs to be aligned is the semantics of averaged clean latents. More importantly, we demonstrate that the semantic recovery error orthogonally decomposes into the error of the optimal semantic prediction directly from the noisy latent and the error between these two predictions. We therefore identify their consistency as the missing requirement and call it Semantic Affine Consistency (SAC). To examine whether this overlooked requirement is closely related to downstream generation, we introduce M_SAC, a tokenizer-side proxy for SAC. Across the evaluated tokenizers and diffusion model scales, M_SAC closely tracks generation quality, reaching a Pearson correlation of 0.960 with SiT-XL gFID, thereby motivating SAC-guided tokenizer training. We then introduce AffineTok, which promotes SAC through two complementary, training-only components. Global Semantic Coordination Token (GSCT) coordinates the semantic organization of clean latents, keeping semantic averaging meaningful, while Posterior-Mean Semantic Alignment (PMSA) predicts posterior-mean latents from noisy inputs and supervises their semantics. On ImageNet 256, compared with the baseline, AffineTok reduces gFID by 26% at 20 epochs and, with continued training, achieves a new state-of-the-art gFID of 1.21 without classifier-free guidance and 1.10 with guidance. --- ### Revelation Control Authors: Qinyou Wang Published: 2026-08-24 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2608.23860v1 Revelation Control is the problem of choosing priced interventions that reveal hidden state only insofar as the revealed distinctions can change a consequential decision, while accounting separately for any useful progress created by the intervention itself. We develop this theory for learning systems, where states equivalent under declared current information can respond differently to future training and favor different actions. The framework defines decision-sufficient revelation and revelation depth, separates pure information value from productive reuse, embeds static Bayes refinement into state-dependent continuation value, and gives an exact cost-adjusted factorization criterion: an additional shallow coordinate is decision-nonredundant only when states sharing a scalar summary lie on opposite sides of the priced Stop/Continue boundary. We also give a target-independent protocol for model-specific instantiation and prove that bounded stop-flip risk alone cannot certify positive expected utility under unrestricted severity. Across Qwen2.5-7B and Mistral-7B-v0.3, deeper future-learning probes have positive decision value and productive reuse yields strict equal-compute utility advantages. Qwen additionally provides evidence for a decision-nonredundant shallow revealability regime; in Mistral, a scalar continuation architecture fit only on an independent development panel retains positive familywise-adjusted lower bounds on a disjoint target panel, consistent with scalar decision sufficiency within the tested architecture family and resolution. The evidence supports structural rather than numerical transfer: the decision theory, cost accounting, continuation logic, and evaluation protocol transport, while empirical proxies, coefficients, thresholds, and even the required shallow state dimension may be system-specific. --- ### Beyond the Mandate: A Systematic Security Analysis of the Agent Payments Protocol (AP2) Authors: Avital Aviv, Parth A. Gandh, Ron Bitton, Asaf Shabtai Published: 2026-08-24 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.23858v1 The Agent Payments Protocol (AP2), introduced by Google, enables large language model (LLM)-driven shopping agents to authorize and execute payments on behalf of users. Its signed Checkout and Payment Mandates protect the integrity of transaction data after signing. Agent interactions and external inputs that shape a transaction before authorization remain outside that protection, including Agent-to-Agent Protocol (A2A) messages and Model Context Protocol (MCP) tool calls. Prior work identified replay and prompt-injection attacks in AP2 v0.1. AP2 v0.2 addresses some of these issues but adds capabilities and deployment assumptions that require renewed analysis. We present a systematic security analysis of AP2 v0.2 based on its roles, transaction lifecycle, deployment architectures, and trust boundaries. We divide the lifecycle into five phases and identify five deployment architectures. Using MAESTRO (Multi-Agent Environment, Security, Threat, Risk, Outcome), we model four threat actors, eleven attack surfaces, eighteen adversary capabilities, and six attacker goals. The resulting catalog contains 48 threats spanning five attack families. We score these threats with the Artificial Intelligence Vulnerability Scoring System (AIVSS), identifying eight that reach the High band in at least one architecture. Because no complete public AP2 deployment was available, we build a testbed spanning all five architectures and develop five proof-of-concept demonstrations covering all eight High-risk threats and their mitigations. We also develop a deployment-aware scanner that maps applicable threats to static, cross-role consistency, and adversarial checks. Our analysis shows that valid mandate signatures alone do not ensure that an agent-mediated transaction reflects the user's intent when its pre-authorization context is manipulated. --- ### UHI-Bench: Benchmarking Dual-Source Urban Heat Island Modeling Across Cities in Diverse Climate Regimes Authors: Wanyun Ling, Chenxi Liu, Yi Xie, Aopu Xu, Zhuoqi Zeng, Ziyue Li Published: 2026-08-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.23857v1 Urban heat islands (UHIs) are intensifying under climate change, exacerbating thermal exposure risks. Their two primary observations, land surface temperature UHI (LST-UHI) and near-surface air temperature UHI (AirT-UHI), capture physically distinct aspects of urban heat. However, most studies rely on a single source, and substituting one for the other can substantially bias the magnitude and spatial variability of human heat exposure. Accurate UHI modeling also requires dynamic meteorological drivers and static urban morphology features, but spatiotemporal incompatibilities hinder their alignment. Cloud gaps in LST observations and sparse AirT station networks further limit dual-source UHI modeling, motivating cross-city transfer across diverse climates. To bridge these gaps, we introduce UHI-Bench, the first UHI benchmark for dual-source UHI modeling that integrates dynamic and static environmental context. Following a unified signal, mechanism, and transfer framework, it evaluates over 20 baselines from four model families on five tasks across 20 cities and nine Köppen climate classes. Results show that no model is uniformly best, although foundation models remain consistently competitive and stable. Environmental covariates generally improve performance, but their utility varies across sources and tasks. Cross-city transferability is better explained by overlap in UHI regimes than by climate-zone similarity. With the dataset and standardized pipeline, our work provides practical guidance for urban heat modeling, promotes climate data equity, and supports future advances in climate research. --- ### In-Context Inpainting for Time Series Forecasting Authors: Thang Nguyen, Dung Nguyen, Romero Morais, Truyen Tran Published: 2026-08-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.23855v1 We propose ICI-Time, a novel framework that reframes time series forecasting as a visual inpainting task, leveraging the generalisation power of large vision models (LVMs). Unlike methods that require specialised temporal architectures and extensive domain-specific training, ICI-Time transforms time series into structured visual representations (area charts) and applies visual in-context learning, reformulating forecasting as pattern completion within a grid-structured prompt that pre-trained vision transformers can solve without fine-tuning or architectural modification. Temporal dependencies are represented through spatial layout, with a consistent, invertible mapping between numerical and visual domains. Extensive experiments across epidemiology, meteorology, and power systems demonstrate that ICI-Time performs competitively against deep learning baselines and shows promising adaptability under limited-data settings, introducing a new paradigm that bridges temporal and visual domains. ---