# Research Papers — 2026-07 · bundle page 157 of 222 > Full-text markdown of papers #7801–7850 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/157 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/156.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/158.md) ### Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows Authors: Emanuele Quinto, Carlo Andrea Rozzi, Francesco Zanitti Published: 2026-07-09 Categories: cs.AI, cs.PL, cs.SE arXiv: https://arxiv.org/abs/2607.08740v1 Large language model (LLM) applications increasingly use explicit workflows for tool use, retrieval, branching, checkpointing, and human approval. Existing workflow systems already address many execution concerns. This paper proposes a Lisp-inspired but language-independent conceptual model: symbolic forms, object identity, and live-image thinking are used as explanatory lenses, not implementation commitments. In this model, workflow definitions, workflow instances, inference records, context snapshots, and dependency relations are represented as persistent knowledge objects in a shared knowledge substrate. Its central semantic distinction is between derive and infer: derive is deterministic computation over available state; infer is mediated LLM judgment under declared context and executor-controlled capability policy. The result is a preliminary conceptual account of semantic persistence: workflows do not merely produce knowledge and leave traces, but can themselves be represented as inspectable, resumable, and reviewable knowledge objects, while formal transition semantics remain future work. --- ### The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs Authors: Baha Rababah, Shahzeb Qamar, Lorenz Sparrenberg, Rafet Sifa, Murat Kantarcioglu, Cuneyt Gurcan Akcora, Carson K. Leung Published: 2026-07-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.08734v2 Post-Training Quantization has become widely used to compress large language models to make them deployable on resource-constrained devices. However, the evaluation of quantization methods mainly uses accuracy and perplexity, which cannot capture the behavioral changes in the quantized variants. In this work, we propose Correctness Agreement, a decision-level metric that can measure the intersection of correct predictions between the base model and its quantized variant. We use this metric across multiple models and quantization bit levels (8-bit to 2-bit), and we find that the base and quantized variants usually have a shift in behavior even when accuracy and perplexity are preserved. In order to explain this effect, we study the effect of quantization on the structure of the attention weights using statistical and distributional measures. The results reveal a breakpoint at low bit widths and show that query and key projections are more sensitive to quantization than the value and output projections. These results prove the illusion of equivalency between the base and quantized models and inspire behavioral evaluation beyond perplexity and accuracy for quantization methods. --- ### The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs Authors: Baha Rababah, Cuneyt Gurcan Akcora, Carson K. Leung Published: 2026-07-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.08734v1 Post-training quantization is widely used to deploy large language models in resource-constrained settings, yet its evaluation relies almost exclusively on accuracy and perplexity. We show that these metrics fail to capture behavioral changes induced by quantization. We introduce correctness agreement, a decision-level metric that measures overlap in correct predictions between a base model and its quantized variants, independent of absolute accuracy. Across multiple models and quantization schemes from 8-bit to 2-bit, we find that behavioral divergence emerges under moderate quantization even when task performance appears preserved. To explain this effect, we analyze quantization as a structural operator on attention weights and quantify layer-wise distortions using statistical and distributional measures. Our results reveal non-linear breakpoints at low bit-widths and show that query and key projections are consistently more sensitive than value and output projections. These findings expose an illusion of equivalence between base and quantized models and motivate behavioral evaluation beyond conventional performance metrics. --- ### Super Weights in LLMs and the Failure of Selective Training Authors: Shreyas Subramanian, Adewale Akinfaderin, Akarsha Sehwag Published: 2026-07-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.08733v1 Recent work identified Super Weights, individual parameters whose removal degrades model performance by orders of magnitude. We show that this degradation due to pruning Super Weights does not universally apply to all LLMs. Furthermore, if these parameters are so important, Super Weight-aware training should be effective. We show the opposite. Training Super Weights in isolation (100 to 8,192 parameters) drops accuracy to random-guessing levels on both OLMo-1B and OLMo-7B, and expanding to local neighborhoods of up to 36K parameters provides no improvement. The failure is specific to Super Weight coordinates: training an equal number of randomly chosen positions in the same down_proj layers instead improves over the baseline, so the collapse comes from targeting Super Weights, not from sparsity itself. Vanilla LoRA, updating every position in attention weight matrices through low-rank structure, succeeds with only 0.16% of parameters, and applying the same low-rank update to down_proj succeeds as well. A 10-seed ablation confirms that constraining LoRA updates at positions corresponding to Super Weight coordinates yields statistically indistinguishable results. These findings establish that parameter importance does not imply parameter trainability in isolation, and that effective fine-tuning relies on structured decompositions over entire layers rather than targeting individually important weights. --- ### Trusting sovereign language models as scientific instruments: evidence from Portugal's AMALIA Authors: Manuel Pita Published: 2026-07-09 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2607.08731v2 National language models are becoming publicly funded epistemic infrastructure. Public ownership, linguistic specialization, and open weights create a presumption of trustworthiness. Such an instrument, built by and for a language community, looks like the natural choice for measuring what that community says and values. Whether such a model validly measures anything is untested at release. The evaluation of LLMs as measurement instruments is typically task-specific and stops at agreement with human coders. Agreement cannot distinguish an LLM instrument that measures a construct from one that reaches matching codes through surface correlates. We audit the presumption on a favourable case: AMALIA, Portugal's publicly funded 9B model, coding the moral foundation of authority in European Portuguese. The \textit{recovery gap} operationalizes the audit: decompose the codebook into its theory-defined clauses, recombine them through the theory's explicit rule, and measure how much of the original prompt's performance the stated theory reproduces. In a pre-registered, out-of-sample study on a transcreated (English to European Portuguese) corpus, AMALIA agrees with trained coders within six points of open models eight to thirteen times its size. Yet, the recovery gap shows that only about half of coding performance on authority can be attributed to the theory. A larger multilingual LLM closes the recovery gap on the same corpus, suggesting the shortfall lies in the annotator model, not the corpus or its translation. Sovereignty earns operational and performance trust; epistemic trust requires calibration -- and the audit method is inexpensive, and portable across models, languages and tasks. --- ### WaspMOT: A Benchmark for Long-Term Multi-Object Tracking of Trichogramma Wasps Authors: Tomasz Stanczyk, Yuan Gao, Hardik Agarwal, Seongro Yoon, Tiantao Zhang, Vincent Calcagno, Francois Bremond Published: 2026-07-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.08729v2 Multi-object tracking (MOT) has achieved strong performance on benchmarks dominated by short video sequences. However, such datasets do not adequately evaluate long-term identity preservation, where objects must be tracked consistently over extended durations. We introduce WaspMOT, a benchmark designed to address this gap through long-duration tracking of Trichogramma wasps in controlled ecological experiments. The dataset contains 10 sequences of approximately 12,000 frames each (over 8 minutes at 25 FPS), with dense MOTChallenge annotations and oracle detections to isolate association performance. Unlike existing benchmarks, WaspMOT forms a closed-set tracking scenario where all individuals remain present throughout the sequence, requiring consistent identity assignment across thousands of frames despite abrupt jumps, occlusions, and highly similar appearance. We establish a benchmark by evaluating five tracking-by-detection methods, including ByteTrack, BoT-SORT, C-BIoU, OC-SORT, and McByte, under a unified protocol. Results show that all methods suffer from significant trajectory fragmentation, highlighting the difficulty of long-term identity preservation even with perfect detections. A simple spatial tracklet stitching baseline consistently improves performance, indicating that substantial gains remain possible. WaspMOT provides a new benchmark for studying long-term association and reveals limitations of current tracking approaches that are not observable on conventional datasets. The benchmark will be made publicly available at the project repository: https://github.com/tstanczyk95/WaspMOT/ . --- ### Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction Authors: Ayda Eghbalian, Kevin Desai Published: 2026-07-09 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.08725v1 Recent progress in 3D human pose estimation has made markerless recovery of skeletal motion increasingly accurate and scalable. However, most pose estimators remain optimized for geometric keypoint accuracy, while many real-world applications in rehabilitation, sports science, ergonomics, and clinical movement analysis require biomechanical quantities that describe how the body moves, loads, and activates. In this work, we propose BioModule, a lightweight plug-in temporal transformer that attaches downstream of any 3D pose estimator and predicts biomechanical attributes from standard 17-joint 3D skeletons. BioModule is estimator-agnostic and requires no modification of the upstream pose model, enabling existing pose estimators to be extended toward physically interpretable motion analysis. To train and evaluate BioModule, we construct a large-scale aligned dataset pairing Human3.6M video and 3D keypoints with the biomechanical label space of Human3.6Mplus. We establish and verify anatomical correspondence between coordinate systems of the two datasets, enabling frame-accurate cross-modal supervision. Using this aligned supervision, BioModule predicts biomechanical quantities. We further benchmark BioModule across seven state-of-the-art 3D pose estimators, providing the first systematic analysis of how upstream pose estimation quality propagates to downstream biomechanical prediction fidelity. The results position BioModule as a compact, modular bridge between vision-based pose estimation and biomechanically meaningful human motion analysis. --- ### Latent Memory Palace: Reasoning for Control as Autoregressive Variational Inference Authors: Chuning Zhu, Eva Xu, Jose Barreiros, Krishnan Srinivasan, Paarth Shah, Abhishek Gupta Published: 2026-07-09 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2607.08724v1 Human decision-making is highly flexible -- some actions are taken immediately; others require longer deliberation. Language models have exhibited a similar capacity for adaptive "reasoning." However, transferring this capability to continuous control policies has been challenging, as directly reasoning in language space may lack the granularity for spatial understanding and precise motions. In this work, we show that reasoning for control policies can emerge by organizing information in an autoregressive latent space reminiscent of a memory palace, where retrieval is iterative and adaptive. Our method, Latent Memory Palace (LMP), formulates reasoning as variational inference with an autoregressive latent distribution. We derive a latent-space reinforcement learning technique to tractably optimize its variational lower bound. The resulting policy, LMP-$π$, achieves strong empirical performance in simulation and real-world domains while exhibiting interpretable, adaptive allocation of test-time compute. We further show that the same framework yields a variable-length action tokenizer, LMP-$\texttt{tok}$, which significantly improves the performance of downstream autoregressive policies. Together, these results present a new perspective on latent reasoning for control through the lens of variational inference. --- ### Deep Learning for Joint Narrowband Interference Cancellation and Soft Demodulation in OFDM Systems Authors: Emmanouil Kavvousanos, Francky Catthoor, Vassilis Paliouras Published: 2026-07-09 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2607.08717v1 Narrowband interference (NBI) severely degrades orthogonal frequency-division multiplexing (OFDM) systems by corrupting subcarriers and rendering classical soft demodulation ineffective. Conventional compressed-sensing (CS) mitigation exhibits high sequential latency and leaves structured, non-Gaussian residuals that cause log-likelihood ratio (LLR) unreliability, decoder saturation, and severe error floors when employing classical Gaussian demappers. We resolve this pipeline mismatch using a unified deep learning framework for joint NBI cancellation and robust soft demodulation. First, NBI-CNet employs a physics-informed convolutional architecture to estimate NBI parameters and remove multi-tone interference in a single forward pass. Without requiring prior knowledge of the active interferer count, NBI-CNet reduces computational complexity by up to 60% ($N{=}2048, Q{=}64$) compared to the state-of-the-art EOMP-IDS algorithm. Second, LLR-CNet acts as a structural whitener by mapping non-Gaussian post-mitigation residuals onto well-calibrated soft metrics. Simulations demonstrate that this joint framework eliminates the error floors inherent to traditional baselines across dense grids. Under severe interference ($\text{SIR}{=}{-}10$ dB), the pipeline operates within a $0.2$ to $0.5$ dB SNR margin of the optimal iterative baseline at a target block error rate (BLER) of $10^{-4}$. Under mild interference ($\text{SIR}{=}10$ dB) with heavy spectral overlap ($Q{=}12$), where classical greedy algorithms erroneously subtract valid data components and corrupt the payload, NBI-CNet avoids signal-peak confusion to deliver a coding gain exceeding $3$ dB. Finally, the architecture circumvents the $2{\times}10^{-4}$ error floor triggered by interferer-estimation errors, while its scale-invariant design enables robust generalization across arbitrary FFT sizes without retraining. --- ### Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents Authors: Yifan Wu, Lizhu Zhang, Yuhang Zhou, Mingyi Wang, Bo Peng, Serena Li, Xiangjun Fan, Zhuokai Zhao Published: 2026-07-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.08716v1 In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgoals can be buried in the context window or pushed beyond it, failing to influence decisions when needed. We call this failure mode "behavioral state decay". We study memory as an active intervention mechanism rather than passive retrieval. A separate memory agent runs alongside an unmodified action agent, updating a structured memory bank from the recent trajectory and deciding whether to inject a memory-grounded reminder or remain silent. The module is plug-and-play with frontier action agents and existing agent harnesses. Across Terminal-Bench 2.0 and $τ^2$-Bench, it improves pass@1 for both weaker and stronger action agents, with gains of +8.3 pp on Terminal-Bench and +6.8 pp on $τ^2$-Bench. Ablations show that selective intervention outperforms passive bank exposure, always-on injection, advisor-only guidance, and general retrieval. As an early step toward open-weight memory policies, we train Qwen3.5-27B on SETA using SFT and GRPO, improving validation reward and achieving partial transfer to Terminal-Bench. --- ### LTM: Large-scale Terrain Model for Wildfire-prone Landscapes Authors: Xiao Fu, Yue Hu, Meida Chen, Peter Anthony Beerel, Barath Raghavan Published: 2026-07-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.08711v1 Accurate 3D terrain maps are essential for emergency response when assessing wildfire hazards. However, wildfire-prone regions often span vast areas where conventional reconstruction methods underperform. Airborne LiDAR systems provide high-resolution terrain data, but they are expensive and infrequently updated. Image-based methods offer a lower-cost alternative, but struggle due to sparse visual features and limited image overlap. We propose a multi-modal reconstruction framework leveraging outdated Digital Elevation Models (DEMs) as geometric priors for image-based 3D reconstruction. Our key innovation is physics-based pixel-pixel alignment between images and DEM data, dramatically reducing computational complexity by eliminating expensive feature matching procedures. To validate our approach, we developed a large-terrain simulator based on a real wildfire-prone area, generating realistic images enabling a comprehensive evaluation. Given posed images and legacy DEMs, our method produces high-fidelity depth maps while maintaining real-time performance. We find significant improvements in reconstruction accuracy and computational efficiency over existing techniques, offering a scalable solution for wildfire response. --- ### HumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery Rationales Authors: Wenbo Xu, Zhimin Chen, Xiaojie Liang, Hengrui Liu, Ziqi Sheng, Wei Lu Published: 2026-07-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.08705v2 Rapid advancements in video diffusion models and temporal editing tools have enabled the generation of highly realistic human-centric videos, presenting unprecedented challenges to digital content forensics. Existing benchmarks primarily focus on face-swapping or global text-to-video synthesis, overlooking the crucial dimensions of multimodal alignment and complex human-object or human-human interactions. To address these limitations, we introduce HumanForge, a unified, large-scale, and multi-paradigm human-centric video forgery benchmark containing over 18,000 synthesized videos across four distinct scenarios: audio-driven, pose-driven, semantic-driven, and interaction. To construct and annotate this dataset without labor-intensive manual labeling or blind monolithic prompting, we propose Gen2Anno (Generation-to-Annotation), a cooperative multi-agent pipeline. Gen2Anno orchestrates six specialized agents-ranging from driving asset profiling to MoE-based reference analysis and closed-loop verification-to dynamically execute video synthesis and produce structured annotations containing binary authenticity labels, generative model attribution, and natural-language contrastive forgery rationales. By systematically contrasting expected states derived from generation provenance with actual visual observations, the framework generates logically grounded forensic reasoning chains. Extensive benchmarks using state-of-the-art traditional detectors and Vision-Language Models demonstrate the significant challenges of cross-generator generalization, perturbation robustness, and explainable reasoning on HumanForge. The code and dataset will be publicly released. --- ### HumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery Rationales Authors: Wenbo Xu, Zhimin Chen, Xiaojie Liang, Hengrui Liu, Wei Lu Published: 2026-07-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.08705v1 Rapid advancements in video diffusion models and temporal editing tools have enabled the generation of highly realistic human-centric videos, posing unprecedented challenges to digital content forensics. Existing benchmarks primarily focus on either face-swapping or global text-to-video synthesis, overlooking the crucial dimensions of human-object or human-human interactions and multi-modal alignment. To address these limitations, we introduce HumanForge, a unified, large-scale, and multi-paradigm human-centric video forgery dataset. To construct and annotate this dataset without labor-intensive manual labeling or hallucinated monolithic prompts, we propose Gen2Anno, a modular active multi-agent pipeline built on LangGraph. Gen2Anno coordinates six specialized agents-ranging from source profiling to MoE-based reference analysis and closed-loop forensic verification-to generate over 18K high-fidelity video segments and produce structured, contrastive omni-annotations containing binary decisions, fine-grained artifact categories, and spatio-temporal localization. Extensive benchmarks using state-of-the-art traditional detectors and Large Multimodal Models (LMMs) demonstrate the significant challenges of zero-shot generalization and fine-grained reasoning on HumanForge. Code and dataset will be publicly released. --- ### MPFlow: Learning Budgeted Max-Flow Optimization on the Lightning Network with Deep Graph Reinforcement Learning Authors: Harrison Rush, Vincent Davis, Simone Antonelli, Vikash Singh, Jesse Shrader, Emanuele Rossi Published: 2026-07-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.08703v1 We address liquidity placement in the Bitcoin Lightning Network (LN): given a fixed budget, which channels should a node open to maximize its routing capacity? We cast this as a budget-constrained combinatorial optimization problem on graphs, selecting $k$ edge additions that maximize $s$--$t$ max-flow, a theory-grounded measure of routing capacity, and solve it with graph reinforcement learning. Our lightweight agent combines a message-passing policy network with proximal policy optimization (PPO) and action masking, and is trained under a hub-exclusion curriculum: the network's top hubs are removed from training subgraphs, forcing the policy to learn capacity-aware placement rather than hub attachment. In extensive experiments on real Lightning Network snapshots, our method consistently outperforms strong heuristic baselines on the max-flow objective across multiple seeds and unseen graphs. The agent has been deployed in production for peer recommendations, executing 4640 channel-open decisions that cumulatively allocate 267.3 BTC over $16 million across 30 managed nodes. --- ### Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution Authors: Ethan Leung, Elias Lumer, Corey Feld, Austin Huber, Vamse Kumar Subbiah, Kevin Paul Published: 2026-07-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.08700v1 Reinforcement learning increasingly relies on an LLM judge to score each rubric criterion, and that judge acts as the reward model during training. Before such a signal can be trusted, we need to know how capable the judge must be and how biased it is. We study this calibration question for citation quality in deep-research systems, where a search-grounded LLM must support each claim it writes with a cited source. Citation quality is a structured rubric task in which each attribution-citation pair is judged along two dimensions that require an LLM, source relevance and factual support. On an adversarial long-form benchmark, we score 8 off-the-shelf LLM judges from 3 model families against gold labels over 1,248 rubric decisions, all of which were human-reviewed and 378 of which were hard cases adjudicated from judge disagreements. Cheaper judges remain competitive across both dimensions, with GPT-5-mini attaining the strongest source-relevance pass-class F1 at 0.908 ($κ$=0.636), while on factual support the judges are statistically indistinguishable (overlapping confidence intervals), so no single model dominates. At comparable F1, the judges still differ substantially in pass-rate drift, false positive rate, and false negative rate. Scalar F1 obscures this directional bias, yet it is exactly what a downstream reinforcement learning loop would reinforce. Calibrating the judge is therefore a prerequisite for using citation rubrics as reward signals, and our results show that this calibration does not require the most expensive available model. --- ### ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation Authors: QiHong Chen, Aaron Imani, Iftekhar Ahmed Published: 2026-07-09 Categories: cs.SE, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2607.08691v1 Repository-level code generation requires implementing target functions while accounting for complex cross-file dependencies and project-specific conventions. Existing retrieval methods predominantly rely on lexical, structural, or semantic similarity, often overlooking repository functions that implement similar procedural logic despite differing in identifiers or application domains. We propose ProjAgent, a repository-level code generation system that introduces procedural similarity as an explicit retrieval signal. ProjAgent decomposes the target function into intermediate reasoning steps and employs an agentic workflow to retrieve repository functions that exhibit similar procedural behavior at each step. The retrieved procedural context is integrated with conventional semantic retrieval to construct a richer repository context for code generation. ProjAgent further incorporates a conservative static-analysis feedback loop that iteratively repairs generated code using compiler and static-analysis feedback. Evaluated on REPOCOD, ProjAgent achieves 41.14% Pass@1, outperforming existing retrieval-based baselines. These results demonstrate that procedural similarity is an effective and previously unexplored retrieval dimension for repository-level code generation. --- ### A Practical Investigation of Training-free Relaxed Speculative Decoding Authors: Guoxuan Xia, Luka Ribar, Paul Balanca Published: 2026-07-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.08690v1 Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM. Standard speculative decoding is lossless: its rejection and resampling steps exactly preserve the LLM's sampling distribution. Recent work argues that relaxing this strict guarantee can yield further speed-ups, controlled capability-speed trade-offs, or even capability gains. We practically investigate training-free relaxed speculative decoding techniques, unify existing approaches within a shared framework, benchmark them on contemporary settings, and distil takeaways and empirical findings for practitioners. Important takeaways include: relaxation can require considerable capability evaluation unlike lossless speculative decoding, and many relaxed approaches rely on a drafter that is a good language model, making them unsuited for lightweight dedicated multi-token-prediction drafters. --- ### SAM-MT: Real-Time Interactive Multi-Target Video Segmentation Authors: Ruiqi Shen, Chang Liu, Henghui Ding Published: 2026-07-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.08688v1 Modern Video Object Segmentation (VOS) involves tracking and segmenting user-specified targets. While recent approaches have achieved remarkable performance in single-target scenarios, extending them to multi-target settings typically involves replicating the single-target processing for each individual object, resulting in reduced frame rates (FPS) with unbounded latency as target count increases. Built upon Segment Anything 2 (SAM2), we propose SAM-MT, which addresses this by transforming the model into an interactive framework for real-time Multi-Target video segmentation. SAM-MT uses explicit queries to represent different individual targets, in parallel with a shared representation for global context. It employs decoupled masked attention to keep individual identities distinct from cross-target interference, and sparse memory for stable temporal evolution, along with specialized strategies for occlusion handling and overlap prevention. SAM-MT successfully decouples latency from the number of targets, achieving real-time speed on par with single-target baselines (>36 FPS for 10 targets) while maintaining SAM2's robust video segmentation performance. --- ### SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets Authors: Shilin Ou, Yifan Xu, Luyao Zhang Published: 2026-07-09 Categories: cs.AI, cs.ET, cs.LG, cs.MA, econ.GN arXiv: https://arxiv.org/abs/2607.08681v1 As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustworthiness. In decentralized energy markets, autonomous agents may improve market utility, but may also exploit invalid physical data, create artificial liquidity, and produce unstable governance decisions. Therefore, we propose SolarChain-Eval, a physics-constrained benchmark for evaluating trustworthy economic agents. It formulates market governance as a Gymnasium-compatible Markov Decision Process, where agents make hourly decisions. SolarChain-Eval evaluates each policy across multiple dimensions, including market utility, physical safety, slippage, action smoothness, spatial fairness, and auditability. To support agentic evaluation, SolarChain-Eval incorporates an LLM-based Planner/Auditor layer. The Planner defines episode-level action bounds and audit rules, while the Auditor reviews and revises high-risk actions. All interventions are recorded through structured logs, including trigger signals, proposed actions, revised actions, and audit rationales. Experiments with static, random, myopic, RL, and RL+LLM policies reveal a clear utility-safety trade-off. RL agents improve market utility but can still produce unsafe behavior. When the physics penalty is removed, reward-maximizing agents exploit invalid generation and increase artificial liquidity. The LLM Planner/Auditor improves auditability and mitigates selected risks, but it cannot fully compensate for a misspecified reward function. These results indicate that trustworthy agentic AI evaluation requires both physical constraints and transparent intervention traces. We release data and code as open access on GitHub for replicability. --- ### Multi-Resolution Feature Stem for Diabetic Retinopathy lesion segmentation Authors: Indranil Dutta, Taehee Jeong Published: 2026-07-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.08679v1 Diabetic Retinopathy (DR) is a leading cause of preventable blindness worldwide, requiring automated lesion segmentation using deep learning models for early detection and monitoring. However, DR lesions vary dramatically in size from tiny microaneurysms to large hemorrhages and exudates. This variability creates conflicting demands on the model architecture and input resolution, posing a challenge for effective design. This work investigates the impact of input resolution on different lesion types. Through systematic experimentation with multiple architectures (U-Net, UNet++, Vision Transformers, DeepLabV3+) at $512 \times 512$ and $1024 \times 1024$ resolutions, we identify a critical, counter-intuitive phenomenon where increasing input resolution has opposing effects on different lesion types. We demonstrate that while higher resolution is essential for resolving fine-grained microaneurysms, it can unexpectedly degrade performance on larger hemorrhages. This finding challenges the common assumption that higher resolution is uniformly beneficial. To address this, we propose a novel Multi-Resolution Feature Stem, an input-level pyramid integrated with a UNet++ backbone. This architecture processes multiple scales in parallel, capturing fine-grained details without sacrificing contextual information. This work contributes crucial empirical evidence of this complex, resolution-dependent behavior and a practical, parameter-efficient architecture that successfully resolves this trade-off. --- ### Do Transformations Reveal the Truth? Generative Residual Learning for Generalized AI-Generated Image Detection Authors: Kutub Uddin, Nusrat Tasnim, Awais Khan, Mohammad Umar Farooq, Khalid Malik Published: 2026-07-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.08674v1 The rapid advancement of generative AI has enabled the creation of highly realistic deepfake media, posing significant threats, including misinformation, digital identity theft, fraud, and manipulation of public opinion. AI-generated image (AIGI) detection is reliably challenging due to the diversity of generative methods and the subtle artifacts they leave behind. In this work, we propose GenRes, a novel framework for generative residual learning via a neural tensor network, which models fine-grained relational features between original and transformed samples to enhance generalization. To address scenarios involving multiple generative transformations, we introduce GenRes++, which employs a learnable attention mechanism to aggregate relational features across multiple transformed samples and enables the model to focus on the most informative cues. Both models leverage PE-Core as a feature extractor, providing generalized and semantically rich embeddings that improve cross-domain performance and enable the detection of AIGI generated by unseen methods. Comprehensive experiments on multiple benchmark datasets demonstrate that the proposed GenRes++ approach outperforms existing methods. --- ### Resample or Reroute? Recoverable Stopping Debt Without Identified Action Selection Authors: Teng-Ruei Chen Published: 2026-07-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.08665v3 After a weak verifier accepts a large-language-model response, a second call may resample or reroute. Because correctness is hidden, action selection is an identification problem. We order three gates: recoverable stopping debt, two-sided FIT action support, and held-out value from an outcome-blind selector. In a pinned 152-query MBPP+ experiment, a Qwen2.5-14B Base-only false-positive stop leaves +2.592 percentage points of Qwen2.5-7B recovery (query-cluster 95% interval (+1.618, +3.664)). Separately, after 7B Base-test rejection, fixed escalation to 14B exceeds leave-one-out 7B resampling by +2.882 points (+0.931, +5.201); this is fixed-action ranking, not conditional selection. An all-episode audit produces a +2.697-point realized-maximum gap, but for two actions this statistic equals (1/2)E|Delta| - (1/2)|E Delta| and contains no observable-history term. It lies inside an exact-fold exchangeable reference (mean +3.158; 95% interval (+2.434, +3.947)). The audit unconditionally acts on 1,520 episodes: 1,240 observable stops and 280 verifier rejections; 198 stops are evaluator-only false positives. Neither tested outcome-blind controller improves on fixed rerouting. A separate LiveCodeBench ladder has all-zero FIT action advantages despite exclusive TEST rescues. A preregistered BigCodeBench support gate then finds only 23/19 and 22/19 signed episodes/queries against minima of 25/20, so L1-L4, DEV, and TEST stay unopened. Stopping debt exists, but current evidence does not identify when to resample rather than reroute. --- ### Resample or Reroute? Budget-Aware Test-Time Model Selection for Large Language Models Authors: Teng-Ruei Chen Published: 2026-07-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.08665v2 Routing among large language models (LLMs) trades response quality against serving cost, motivated by the reported gap between deployed routers and a per-instance oracle. Recent analysis shows that test-time resampling can recover per-instance selection headroom that no single-commit router captures; however, that guarantee holds only under an idealized oracle equipped with correctness labels and an unconstrained budget, neither of which a deployed system has. To the best of our knowledge, no previous work treats resampling the committed model and rerouting to an alternative model as competing uses of a single per-query cost budget. Therefore, this work formulates budget-aware test-time model selection: given a per-query budget and an imperfect verifier, allocate each unit of budget between resampling and rerouting so that expected correctness is maximized. An online resample-or-reroute (RoR) allocation policy driven by estimated marginal correctness per unit cost is proposed, and its behavior is grounded in the recoverability asymmetry between selection and sampling. Replay experiments on newly regenerated multi-draw correctness tensors from an eleven-model open-weight pool over four benchmarks of differing difficulty show that the proposed RoR policy attains a favorable cost-quality Pareto front relative to single-route, one-commit-router, budget-aware best-of-K, cascade, and random-allocation baselines for the tested pools, with the largest gains on the most heterogeneous benchmark; an ablation further shows the gains are verifier-gated, shrinking as verifier quality degrades, and robustness replays under a provider price vector and a label-free agreement verifier delineate where the conclusions carry over. --- ### WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search Authors: Xiaoshuai Song, Liancheng Zhang, Kangzhi Zhao, Yutao Zhu, Zhongyuan Wang, Guanting Dong, Jinghan Yang, Han Li, Kun Gai, Ji-Rong Wen, Zhicheng Dou Published: 2026-07-09 Categories: cs.CL, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2607.08662v1 Large language model (LLM)-based web search agents are transforming information seeking from simple factoid question answering into complex, deep-and-wide search and research-oriented tasks. A single ReAct-style agent is constrained by one long trajectory and limited context, making it difficult to handle depth and coverage simultaneously. Existing multi-agent systems improve search coverage through parallel execution and aggregation, but still exhibit clear limitations in recursive depth, collaboration adaptability, and evidence-grounded expansion. We propose WebSwarm, a progressive recursive delegation framework that jointly constructs task decomposition, recursive expansion, and agent collaboration during inference. WebSwarm dynamically instantiates agentic search nodes, each coupling a local objective with a search mode that specifies how the node should organize search and collaboration. Each node can either solve its objective itself or further delegate child nodes; after solving, it returns evidence and results upward, enabling parent nodes to further expand, revise, or aggregate the search process. To guide this process, WebSwarm first probes how task-relevant information is organized on the web to ground subsequent node expansion, and reuses process-level experience across homogeneous sibling nodes. Experiments on BrowseComp-Plus, WideSearch, DeepWideSearch, and GISA show that WebSwarm consistently outperforms single-agent and multi-agent baselines on deep, wide, and interleaved deep-and-wide tasks. Further analyses of ablation, task difficulty, web tool efficiency, and model generalization explain WebSwarm's effectiveness and provide insights for multi-agent search systems. --- ### EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy Authors: Wenxiu Ding, Muzhi Liu, Zheng Yan, Mingjun Wang, Yifan Zhao, Qiao Liu Published: 2026-07-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.08659v2 Graph Neural Networks (GNNs) have shown considerable success in learning from graph-structured data, but their use in privacy-sensitive areas remains difficult because graph structure can leak sensitive link information. To satisfy edge-level differential privacy, a common approach is to inject noise into all elements of the graph's adjacency matrix, thereby obfuscating the existence of any single edge. However, stronger privacy requires more noise, and excessive noise reduces utility, making the privacy-utility balance a major barrier to practical privacy-preserving graph learning. To address this issue, we propose EdgeRefine, a local differential privacy framework that improves this trade-off through adaptive edge refinement. EdgeRefine first estimates edge-existence probabilities using Jaccard similarity and ranks edges for noisy edge removal. To ensure the sparsity and reliability of the final graph, it uses the privacy budget $ε$ to determine the ratio of true to false edges, samples them separately based on this probability ranking, and controls the total number of edges with a separate sampling rate $k$. Extensive experiments show that EdgeRefine achieves accuracy comparable to the noise-free baseline and substantially outperforms other privacy-preserving methods across datasets and GNN architectures. Under privacy budget $ε= 2.5$, EdgeRefine improves node classification accuracy over state-of-the-art baselines by 17.8\% on ACM under GAT and 19.7\% on Cora under GCN. In graph classification, it achieves an average accuracy degradation of around 5\% compared to the noise-free baseline. Under graph reconstruction attacks, EdgeRefine maintains relative absolute error levels above 1 across all privacy budgets, averaging 1.962 on Cora and 1.472 on AMAP, indicating strong resilience against privacy leakage. --- ### Formal Mechanisms for Market Stability in Self-Interested Agent Societies: A Marketplace Simulation Study Authors: Eugene Ng Yi Sheng, Bingquan Shen Published: 2026-07-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.08652v1 Self-interested agents, left unconstrained, tend toward defection in repeated social dilemmas, causing cooperative gains from trade to collapse. This paper investigates what formal mechanisms, layered on top of unrestricted communication, are sufficient for a society of such agents to maintain market stability, and how resilient those mechanisms are to adversarial attack. We instantiate the research question as a multi-agent marketplace simulation where 18 LLM agents (DeepSeek-V3) with complementary production specialties must trade within a constrained social network to obtain utility. We conduct two experimental phases: (1) a mechanism comparison across eight conditions under progressive troll injection over 200 rounds, identifying Mediation as the top-performing mechanism; and (2) adversarial red-teaming of Mediation using iteratively prompt-optimised LLM-driven trolls, finding that the best attack (v6) reduces honest-agent utility by 13.3% but cannot collapse the market. Mediation enables recovery even under sustained adversarial pressure. We define adversarial robustness as a mechanism's ability to sustain positive honest-agent utility under optimised attack, and find that Mediation is robust: it can be bent but not broken. --- ### Secure Decentralized Federated Learning via Gossip and Virtual Voting Authors: Amirhossein Taherpour, Xiaodong Wang Published: 2026-07-09 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2607.08651v1 Decentralized federated learning (DFL) removes the central server by letting nodes exchange model updates through peer-to-peer gossip, but existing gossip-based methods often lack provenance finality and resilience to Byzantine or lazy participants. Ledger-assisted federated learning (FL) improves auditability, yet blockchains, shards, or settlement committees can reintroduce global coordination costs that conflict with DFL locality. This paper proposes \emph{gspDAG-FL}, a secure DFL framework that derives consensus from the same gossip history used to disseminate models. Nodes exchange model payloads only with neighbors, while full nodes collect event certificates and receiver-endorsed accepted gossip proofs, reconstruct a compact Topology directed acyclic graph (DAG), and run Hashgraph-style virtual voting followed by compact full-node certificates. Finality is over unique model-origin tuples, not identical local parameter states. To improve resilience, gspDAG-FL combines payload validation, accepted-proof validation, and private semantic audit before aggregation. We formalize the adversarial setting, prove safety and conditional liveness of the control plane, and give a convergence guarantee for certified perturbed gossip under time-varying effective mixing. Experiments on MNIST classification and Penn Treebank language modeling, using fair held-out validation/audit data and networks up to \(N=100\), show that gspDAG-FL achieves learning quality close to validation-based ledger FL while reducing coordination bottlenecks, improving throughput, and maintaining high invalid-origin detection under mixed Byzantine and lazy participation. --- ### Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning Authors: Ali Larian, Qian Lin, Chang Zong Wu, Daniel S. Brown Published: 2026-07-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.08647v1 As autonomous agents are increasingly deployed across diverse operational contexts, aligning their behavior with human intent demands reward functions that remain robust to such changes rather than overfitting to any single environment. Inverse reinforcement learning (IRL) provides a principled way to infer such objectives from human feedback. However, existing analyses of optimal teaching approaches for IRL focus on single-environment, demonstration-only settings, leaving underexplored how heterogeneous feedback modalities and environment dynamics jointly constrain reward functions that generalize across multiple environments. Because demonstrations in one MDP entangle reward information with that environments specific structure, the resulting rewards frequently fail to generalize when the agent is deployed in a new setting. We first analyze how different feedback modalities constrain rewards, showing that, in the unlimited-data regime, comparisons impose strictly stronger global constraints than other modalities. Beyond this theoretical analysis, we introduce a hierarchical machine teaching algorithm for reward learning that operates across multiple MDPs. The algorithm first greedily selects informative environments that expose complementary reward constraints, then strategically queries low-cost feedback within those environments. Empirically, our method achieves substantially lower regret and stronger generalization to held-out environments than uniform teaching baselines under identical feedback budgets, demonstrating the importance of multi-environment, multi-modal teaching for learning dynamics-robust reward functions. --- ### UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing Authors: Xinlong Zhao, Dongsheng Liu, Hengyu Zhao, Zixuan Fu, Zheng Wang, Jie Cai, Jie Zhou, Qiang Ma, Xuanhe Zhou, Xu Han, Yudong Wang, Zhiyuan Liu Published: 2026-07-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.08646v1 As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish. Consequently, improving Large Language Models (LLMs) now depends less on data expansion and more on higher-quality data utilization. However, in the context of large-scale corpora, existing refinement methodologies face significant limitations in quality, efficiency, and reliability: Rule-based approaches are constrained by fixed heuristics and struggle with instance-level variations; LLM-based approaches improve quality but fail to meet the efficiency and reliability requirements of large-scale data processing. To address these challenges, we propose UltraX, a function-calling refinement framework for large-scale pre-training data that completes the editing function space by introducing insertion in addition to deletion and modification, enabling fine-grained instance-level editing. Specifically, UltraX builds a reliable program-supervision generation pipeline. In this pipeline, dataset-adaptive prompt optimization first guides an expert LLM to produce high-quality end-to-end refined texts, and Line Alignment Mapping and Dynamic Context Replacement then convert original-refined text pairs into structured program supervision. Meanwhile, UltraX improves supervision quality and stabilizes the training distribution with low-confidence example filtering and ratio-controlled sampling by operation combination. During inference and execution, it normalizes and validates model outputs through sliding-window prediction, global operation aggregation, and systematic post-processing, improving the stability and reliability of large-scale execution. Experiments show that UltraX achieves the highest average performance across all corpora and also matches or surpasses baselines with fewer training tokens, demonstrating stronger data efficiency and refinement reliability. --- ### BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression Authors: Yuantian Shao, Peisong Wang, Zhilei Liu, Chuangyi Li, Yuanteng Chen, Pengcheng Xie, Yiwu Yao, Zhihui Wei, Jian Cheng Published: 2026-07-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.08643v1 Large language models (LLMs) are increasingly constrained by memory capacity, weight bandwidth, and checkpoint storage during deployment. Existing low-bit compression methods mainly follow two directions. Scalar or group-wise quantization is simple and compatible with efficient low-precision kernels, but its representation capacity becomes limited when the target budget approaches 2 bits per weight. Vector-quantized weight compression provides a richer block-level representation, but usually introduces explicit codebooks, index lookup, and additional storage accounting. This paper presents BiSCo-LLM, a codebook-free binary spherical coding framework for extreme low-bit LLM weight compression. The core pipeline is built on three components. First, local weight chunks are mapped onto a unit hypersphere and binarized into compact spherical codes, so that the main payload is a bit-packed sign stream rather than explicit VQ centroids. Second, a residual BSQ stage encodes the reconstruction error left by the base spherical codec, providing an explicit rate-distortion path without stored codebooks. Third, category-wise recovery distillation is performed after replacing each Transformer module category, reducing the mismatch between local weight reconstruction and assembled model behavior. A small 8-bit protected-channel path is used as an auxiliary stabilization mechanism for sensitive channels and is counted separately from the BSQ payload. The reported storage budget includes binary codes, neural decoders, protected-channel payloads, LoRA adapters, and metadata. --- ### DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding Authors: Saw S. Lin, Jyh-Shing Roger Jang Published: 2026-07-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.08642v3 Speculative decoding accelerates LLM inference by drafting tokens and verifying them in parallel. Block-diffusion drafters such as DFlash model only per-position marginals, and tree methods such as DDTree expand candidate trees from those marginals. The released Domino drafter adds a GRU-based causal correction making each draft token's distribution path-dependent, a structure DDTree's factorized formulation cannot represent. We introduce DominoTree, a training-free best-first draft tree scored by Domino's conditional (non-factorized) correction along each root-to-node path, made practical by restricting the per-node correction to a candidate top-M. We evaluate it on eight benchmarks in a single-stream harness, and in SGLang, where it runs as an out-of-tree plugin against AR, DFlash, EAGLE-3 and Domino under identical flags. DominoTree attains the highest mean accepted length in every serving cell - two model sizes, single-request and concurrent load, context to 32K - and the highest Overall accepted length at every temperature in the research harness (21 of 24 per-dataset cells). A three-arm decomposition holding drafter, budget and verifier fixed separates the gain from applying the correction at all (+10.1% accepted length) from that of recomputing it along each candidate's realized path (+4.7% more), the part this paper adds. Where the round is verify-dominated, throughput follows: up to 7.3x over AR on Qwen3-8B, beating the released Domino decoder at its CUDA-graph best at every temperature, and inside SGLang winning single-request throughput by +12% over Domino on Qwen3-8B. On HELMET long context it beats Domino by +29-36% accepted length and +10-34% throughput at every length and both model sizes. Past a memory-constrained card's admission cap the chain wins goodput, and at our longest context, where prefill dominates, our lead over EAGLE-3 narrows to a tie. --- ### DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding Authors: Saw S. Lin, Jyh-Shing Roger Jang Published: 2026-07-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.08642v2 Speculative decoding accelerates LLM inference by drafting several tokens and verifying them in parallel. Block-diffusion drafters such as DFlash produce a draft block in one pass but model only per-position marginals, and best-first tree methods such as DDTree expand candidate trees from those marginals. The released Domino drafter adds a GRU-based causal correction that makes each draft token distribution path-dependent, a structure DDTree's factorized formulation cannot represent. We introduce DominoTree, a training-free best-first draft tree scored by Domino's conditional, non-factorized correction along each root-to-node path, made practical by restricting the per-node correction to a candidate top-M set. On Qwen3-4B across eight benchmarks, DominoTree reaches up to 6.6x speedup over autoregressive decoding and the highest mean accepted length of any evaluated method, up to 10.7 tokens per round, at every tested temperature. DominoTree constructs its tree with a GPU-native CUDA-graph builder that is bit-identical to a reference Python implementation, so acceptance is unchanged, while keeping per-round tree construction cheap. With this builder as default, DominoTree improves throughput over the released Domino decoder, the drafter it builds on, at every tested temperature: 9% to 10% overall on Qwen3-4B and up to 22% on Alpaca. It also outperforms DDTree and CaDDTree at every tested temperature, not only under greedy decoding. On Qwen3-8B, DominoTree keeps the highest accepted length at every temperature and gives a 24% throughput gain over DDTree at T=0; at higher temperature its edge over DDTree and CaDDTree narrows to a tie and a small loss, while its aggregate gains over DFlash and Domino persist. --- ### Steering Neural Network Training through Interpretable Constraints Based on Partial Dependence Authors: Yann Claes, Pierre Geurts, Vân Anh Huynh-Thu Published: 2026-07-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.08641v1 Over the last few years, there has been an increased interest in making machine learning models more interpretable. Although a great deal of effort goes into developing techniques for interpreting the interactions learned by a given model, fewer studies focus on assessing the quality of such explanations. Even fewer focus on how to adjust the model to produce explanations faithful to prior knowledge, a process known as explanation-guided learning. Furthermore, most approaches in this area focus on classification problems and usually assume prior knowledge about which input features or regions are most important. In this work, we introduce a new approach to steering neural networks based on partial dependence, such that their average response to certain features aligns with specific functional domain knowledge about the problem. We empirically demonstrate on a range of regression problems, including dynamical systems forecasting, that models whose training has been controlled using our method perform better than unconstrained models and are more data-efficient. Moreover, we highlight that interpretations obtained from the former actually align with the user-provided knowledge, whereas those obtained from the latter do not. --- ### Native Video-Action Pretraining for Generalizable Robot Control Authors: Qihang Zhang, Lin Li, Luyao Zhang, Shuai Yang, Yiming Luo, Shuaiting Li, Ruilin Wang, Junke Wang, Jiahao Shao, Gangwei Xu, Jiaming Zhou, Yishu Shen et al. Published: 2026-07-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2607.08639v2 The advent of video-action models offers a promising path for robot control. Nevertheless, we argue that repurposing video generative models designed for digital content creation is inherently inadequate for physical environments. To bridge this gap, we present LingBot-VA 2.0, a video-action foundation model built from the ground up for embodiment. Four core design principles showcase its evolution from LingBot-VA. (1) Departing from traditional reconstruction-focused VAEs, we introduce a semantic visual-action tokenizer, which aligns visual representations with both semantics and actions, improving instruction following and action precision in subsequent policy learning. (2) Given the strictly causal nature of temporal dynamics, we adopt a causal pretraining paradigm, training from scratch to circumvent the catastrophic forgetting that frequently occurs when adapting bidirectional architectures. (3) To meet the demands of high-frequency inference, our model employs a sparse MoE backbone, expanding model capacity without compromising efficiency. (4) Real-time closed-loop control is realized through an enhanced asynchronous inference scheme, which predicts future latents in parallel with action execution while re-grounding each rollout on the latest observation via learned forward dynamics. Real-world deployment validates LingBot-VA 2.0 as a robust foundation model, as evidenced by its few-shot generalization across complex manipulation tasks. --- ### The complexities of patient-centred conversational artificial intelligence Authors: João Matos, Olivia Buege, Donny Cheung, Gary S. Collins, Paula Dhiman, Nan Li, Bingyu Mao, Benjamin W. Nelson, Michail Ouroutzoglou, Paul Varghese, Jonathan Amar Published: 2026-07-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.08625v1 Consumer-facing health chatbots powered by large language models (LLMs) are increasingly used for symptom assessment. However, chatbot development and evaluation often rely on cooperative, articulate, simulated patients. We analysed 2,053 real patient-chatbot conversations and found that communication patterns and expression of emotions vary widely across users. We developed a patient simulator that separately models clinical content, emotional state, conversational strategy, and communication style. In a Turing-inspired evaluation of realism with 15 human graders, simulated conversations were nearly indistinguishable from real ones, with human graders achieving an accuracy of 55%. We used five distinct patient personae, across 1,164 clinician-graded cases, to evaluate the performance of four LLMs in urgency assessment. We found that communication style can significantly alter triage outcomes. Patient-centred conversational artificial intelligence must accommodate communication diversity: systems designed for idealised, rather than realistic, interactions risk underperforming and amplifying health disparities when deployed in the real world. --- ### When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities Authors: Weiduo Liao, Yunqiao Yang, Ying Wei Published: 2026-07-09 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.08605v1 Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept. However, in vision-language models (VLMs), vanilla SAEs struggle to learn modality-consistent concepts, with concepts often exhibiting fragmented coverage (i.e., disjoint regions) in the visual modality. To address this challenge, we propose a Structured Sparse AutoEncoder ($S^2AE$) that enforces concept consistency from both semantic and spatial perspectives in the visual modality. Specifically, we group image patches based on Transformer attention similarity and spatial proximity, and introduce a structured sparsity regularization when training the vanilla SAE. The regularization consists of exclusive sparsity for inter-group concept disentanglement and group sparsity for intra-group concept consistency, which drives the latent neurons by SAEs to specialize in distinct, semantically grounded concepts. Evaluated on the \texttt{Qwen2.5-VL-7B-Instruct} model, the method achieves 6.06% average improvement in semantic alignment (mIoU) and 60.81 in representational efficiency (lower l0 norm) while maintaining near-perfect reconstruction fidelity with an Explained Variance above 99%. Cross-modal analysis further demonstrates that $S^2AE$ enhances neuronal monosemanticity by this visual structural prior, achieving a 3.08% average gain in semantic consistency and a 2.37% average gain in monosemanticity scores for both modalities of multimodal features, thereby fostering more coherent and disentangled representations. --- ### Towards Precision Therapy in Hepatocellular Carcinoma: A Clinical-Reasoning LLM for Risk Stratification and Treatment Guidance Authors: Peng Cui, Jitao Wang, Siyan Xue, Yao Huang, Haoming Xia, Dong Li, Dengxiang Liu, Weilin Wang, Liping Liu, Leida Zhang, Yunfu Cui, Tao Peng et al. Published: 2026-07-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.08602v1 Hepatocellular carcinoma (HCC) is a common malignancy and a leading cause of cancer-related mortality. Current guidelines and staging systems provide coarse categories, but often miss within-stage heterogeneity and the clinical context in electronic medical records (EMRs). We present HCC-STAR (Hepatocellular Carcinoma Staging, Treatment And pRognosis), a clinically aligned large language model that reads routine EMR narratives and jointly outputs risk score-based staging, ranked guideline-consistent treatments with evidence-based rationales, and individualized survival estimates. We curated about 30,000 HCC cases from SEER and expanded them into EMR-style narrative training data using a clinician-validated, prompt-based augmentation workflow. On this corpus, we developed a knowledge-aligned reasoning framework optimized with a step-verifiable composite reward, moving beyond text-level memorization of clinical guidelines. In a multi-center cohort of 6,668 patients from 12 hospitals in China, HCC-STAR achieved state-of-the-art performance in treatment recommendation and risk stratification compared with clinical guidelines and competitive models, including GPT-5 and Gemini-2.5 Pro. Hypothetical overall-survival analysis showed a median survival of 51 months under adherence to HCC-STAR recommendations, compared with 29 and 32 months under BCLC and CNLC. In clinician-centric evaluations, blinded hepatobiliary specialists rated HCC-STAR's reasoning and evidence-based justifications as trustworthy. The model surpassed resident and attending physicians in treatment accuracy and helped physicians make more accurate decisions faster when used as an assistant. These findings support HCC-STAR as a reliable and verifiable decision-support system for risk stratification and precision therapy in HCC. --- ### It Takes a MAESTRO To Prune Bad Experts Authors: Palaash Goel, Ayush Maheshwari, Tanmoy Chakraborty Published: 2026-07-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.08601v2 Sparsely-activated Mixture-of-Experts (MoE) language models achieve remarkable inference efficiency by activating only a small fraction of parameters per token, yet their full expert banks reside in memory at all times, creating a prohibitive deployment bottleneck. Existing structured pruning methods, largely designed for dense transformers, assess expert importance using locally derived heuristics that are blind to the interdependent nature of MoE routing. We introduce MAESTRO (Markov-chain Approximated Expert Sparsification via Transition-based ROuting), a structured pruning framework designed for MoE architectures that models autoregressive expert activation trajectories as Ergodic Markov chains whose stationary distributions encode cross-layer dependencies, yielding a globally aware importance heuristic. Evaluated across five diverse domains including Safety, Bias, and Ethics, MAESTRO outperforms state-of-the-art baselines by up to 10.61% in average performance retention under a strict 50% compression regime, while exhibiting substantially lower cross-task variance, indicating that global, routing-congruent pruning produces models that generalize more consistently across heterogeneous tasks. --- ### Federated Deep Learning for Privacy-Preserving Cardiovascular Disease Risk Prediction Authors: Hyunho Mo, Djura Smits, Mahlet A. Birhanu, Maarten J. G. Leening, Daniel Bos, Pim van der Harst, Esther E. Bron Published: 2026-07-09 Categories: cs.LG, cs.HC arXiv: https://arxiv.org/abs/2607.08595v1 Cardiovascular disease risk prediction models often rely on data from a single institution or centrally pooled datasets. Extending these models across institutions could be limited by privacy regulations and constraints on sharing patient-level data. Federated learning enables collaborative model development without transferring sensitive patient data, but its application in healthcare remains challenging because datasets often differ in size, population characteristics, and outcome definitions. In this study, we present a federated deep learning approach for privacy-preserving cardiovascular disease risk prediction that integrates two population-based cohorts with different characteristics: Lifelines, including 148,230 participants meeting the study inclusion criteria with self-reported outcomes, and the Rotterdam Study, including a smaller cohort of 10,155 participants with digitally linked clinical outcomes. Model performance was primarily evaluated on the Rotterdam Study because of its complete follow-up. Deep survival models trained using federated learning achieved higher predictive performance than models trained locally without federation. For the Rotterdam Study, the C-statistic increased from 0.728 (95% CI: 0.717-0.739) to 0.739 (95% CI: 0.728-0.749). For Lifelines, the C-statistic increased from 0.783 (95% CI: 0.775-0.791) to 0.787 (95% CI: 0.780-0.792). These findings suggest that federated deep learning across heterogeneous cohorts can improve cardiovascular disease risk prediction while preserving the privacy of individual-level patient data. --- ### Robust Bayesian Decision Making under Adversarial Uncertainty Authors: Haripriya Harikumar, Sammie Katt, Yasir Zubayr Barlas, Samuel Kaski Published: 2026-07-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.08590v2 Scientific experiments are often designed to maximize information gain, yet in many applications the primary objective is to support reliable downstream decision-making. Existing decision-aware experimental design and active learning methods typically assume well-specified outcome models and implicitly rely on the stability of the optimal decision under real-world perturbations. In practice, however, experimental outcomes are frequently influenced by hidden or weakly modeled effects, which can substantially alter decision optimality and lead to misleading conclusions. We study sequential adversarially robust decision-aware experimental design, where data acquisition has to take into account information gain against plausible worst-case unexpected effects, modeled here as variation in adversarial variables. Building on Bayesian decision theory, we formalize an adversarially robust optimal decision under this setting and derive a principled Bayesian experimental design criterion. The criterion explicitly targets decision stability rather than nominal optimality. Experiments on synthetic and real-world scientific datasets show that conventional decision-aware design can converge rapidly to high confidence yet fragile decisions, while our robustness-aware approach yields decisions that are significantly more stable and reliable under adversarial variation. --- ### Spectral Stability of Pseudoinverse-Based Extreme Learning Machine Authors: Bich Van Nguyen, Ngoc Anh Khong Published: 2026-07-09 Categories: cs.LG, math.SP arXiv: https://arxiv.org/abs/2607.08581v1 Extreme Learning Machine (ELM) computes output weights analytically using the Moore-Penrose pseudoinverse. Although this leads to fast training, its numerical stability depends strongly on the conditioning of the hidden layer matrix. This paper studies pseudoinverse-based ELM from a spectral perspective. We show that the smallest singular value governs perturbation amplification in the output weights, while the condition number provides a quantitative measure of hidden-layer instability. We compare SVD-based pseudoinverse computation with iterative hyperpower methods and discuss width-dependent conditioning through a random feature interpretation. Experiments on synthetic matrices and ELM benchmarks show that SVD-based methods remain the most reliable under ill conditioning, while iterative methods are more sensitive to spectral properties. The results suggest that ELM stability is fundamentally governed by the singular value structure of the hidden layer matrix. --- ### ImputeViz: A Visual Analytics Dashboard for Diagnosing Missing Data and Comparing Imputation Methods Authors: Aitik Dandapat, Lalith Punepalle Raveendrareddy, Mithilesh Kumar Singh, Klaus Mueller Published: 2026-07-09 Categories: cs.HC, cs.LG arXiv: https://arxiv.org/abs/2607.08579v1 Missing data is a persistent obstacle in scientific, social science, and public health research, often biasing analyses and placing accountability on analysts for how they handle missing values. We introduce ImputeViz, an integrated visual analytics dashboard that supports diagnosing missingness, configuring imputation models, and evaluating results. The system brings together widely used methods, including MICE, Random Forest, XGBoost, and kNN, within an interactive environment that makes missingness patterns explicit. To support geospatial reasoning, we introduce gKNN, a geographically informed kNN variant that blends socioeconomic and spatial distances and exposes donor contributions, enabling provenance-based visual accountability by showing which regions drive each estimate. Our primary contribution is a method-agnostic visual analytics environment that makes cross-method comparison a first-class visual task and integrates gKNN alongside standard methods. Coordinated views reveal missingness structure through heatmaps, co-missingness summaries, and distributional diagnostics that help analysts reason about missingness patterns (MCAR/MAR) and cases where missingness may be non-random (MNAR). Users can compare and tune models and interrogate results via distributional overlays, a Method Comparison Summary reporting MAE, RMSE, Delta RMSE, and runtime for each algorithm on the current target and mask, along with variable-level discrepancy views. Cached per-method results and locked axis scales reduce cognitive overhead from shifting ranges during method switching. These comparisons highlight where methods disagree, which variables are sensitive, and how imputation choices affect downstream summaries. Case studies demonstrate how ImputeViz helps analysts select effective strategies, surface sensitive variables, and assess model robustness. --- ### SHAP-Weighted Cross-Modal Expert Fusion for Emotion and Sentiment Recognition: Evidence and Limits Authors: Adis Alihodzic, Selma Skopljakovic Hubljar Published: 2026-07-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.08573v1 Multimodal emotion and sentiment recognition is commonly addressed by early fusion, which concatenates modalities before classification, or late fusion, which combines independently trained unimodal predictors. Early fusion can be accurate but monolithic, while late fusion is modular but may lose cross-modal interactions. This paper revisits XAI-guided adaptive fusion (\xgaf), a tree-based mixture of unimodal and cross-modal experts whose sample-level weights are derived from TreeSHAP attribution magnitudes. We focus on the effect of SHAP attribution reduction when experts have unequal feature dimensionalities. In this setting, mean-abs and median-abs reductions can suppress high-dimensional cross-modal experts, whereas sum-abs reduction preserves total attribution mass. On MELD 7-class emotion recognition, sum-abs \xgaf{} nearly matches early fusion across three face-sequence aggregators; the Transformer variant reaches 0.5983 \wf{}, compared with 0.6018 for early fusion and 0.4598 for probability-average late fusion. McNemar testing shows no significant difference between sum-abs \xgaf{} and early fusion on MELD ($p=1.000$), while \xgaf{} remains significantly better than late fusion ($p<0.0001$). On CMU-MOSEI 3-class sentiment recognition, sum-abs \xgaf{} reaches 0.6519 \wf{}, slightly exceeding early fusion (0.6485) and late fusion (0.5696). Ablation studies show that the main gain comes from adding cross-modal experts, especially the trimodal expert, rather than from complex per-sample routing. Diagnostics further show that mean-abs and median-abs weights are nearly uniform, while sum-abs weights concentrate on the trimodal expert. Thus, the main contribution is a transparent empirical analysis of how SHAP reduction, expert dimensionality, and cross-modal expert design affect modular multimodal fusion. --- ### Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning Authors: Yiyang Fang, Pei Fu, Jinjie Li, Jian Liang, Wenke Huang, Ruijie Luo, Shaojie Zhang, Jian Luan, Yi R. Fung, Mang Ye Published: 2026-07-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.08572v1 Multimodal Large Language Models (MLLMs) often follow a fixed Think-then-Answer paradigm, which is inefficient in heterogeneous multitask settings because simple inputs may not require explicit reasoning while difficult ones can benefit substantially from it. Learning when to think is also unstable during post-training, where imbalanced rollouts can drive the model toward always-thinking or always-direct behavior. We propose Switch-Reasoner, a GRPO-based framework that learns to adaptively select reasoning modes for MLLMs. It treats thinking as a virtual tool invocation and allows the model to either answer directly or invoke explicit reasoning before answering. To stabilize this decision, we introduce a dual-level regulation mechanism that balances the overall use of Thinking Mode and Direct Mode while providing sample-level supervision based on the relative benefit of the two choices. Experiments on 11 multimodal tasks show that Switch-Reasoner reduces unnecessary reasoning while maintaining strong performance, achieving a better accuracy-efficiency trade-off. --- ### SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling Authors: Jiahao Wang, Kaizhan Lin, Kaixi Zhang, Jinbo Han, Xingda Wei, Sijie Shen, Chenguang Fang, Wenyuan Yu, Rong Chen, Haibo Chen Published: 2026-07-09 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2607.08565v2 LLM scheduling is critical to serving, yet how well existing designs fit agentic serving--where agents, not humans, issue the requests--remains unclear. Agents shift the workload in two ways: they consume many more tokens than humans, so the cluster must provide high throughput (TPS) at low latency; and their requests reuse far more KV\$ than chat. Existing schedulers still trade off load balance against KV\$ reuse: cache-aware schedulers may crowd requests onto the few instances caching the KV\$, leaving the rest idle, while balanced schedulers may lose the opportunity for reuse, which is costly at a high reuse ratio. We thus present two key insights: (1) with a global-tier KV\$ store, pursuing load balance need not compromise KV\$ reuse, though the slower global tier must be used with care; and (2) given the agent's intra-session locality, routing requests by their sessions can balance the load with high KV\$ reuse. A key challenge in realizing session-centric scheduling is that the scheduler must identify a request's session statelessly, which is difficult for model providers serving arbitrary agents. SMetric addresses this with differential scheduling based on two indicators derived from the request itself, the session turn and the local KV\$ hit: it schedules first-turn requests for load balance, and sticks follow-ups to the instance with the highest local hit for high KV\$ reuse. As sessions differ widely in size, SMetric sticks a follow-up only if the instance can serve it within its SLO, and otherwise migrates the session to the least-loaded instance to prevent many long sessions from eventually imbalancing the load. Evaluated on real-world traces, SMetric improves the peak TPS by 9-15% under prefill-decode colocation with a provisioned global tier and the peak prefill TPS by 9% under disaggregation over state-of-the-art schedulers, also with lower latency. --- ### SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling Authors: Jiahao Wang, Kaizhan Lin, Kaixi Zhang, Jinbo Han, Xingda Wei, Sijie Shen, Chenguang Fang, Wenyuan Yu, Rong Chen, Haibo Chen Published: 2026-07-09 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2607.08565v1 LLM scheduling is critical to serving, yet it remains unclear how well existing designs fit agentic serving--with LLM requests issued by agents instead of humans. This shifts the workload in two ways: (1) agents act only on complete responses, making the cluster's tokens per second (TPS) the primary goal and relaxing--not eliminating--per-token latency requirements; and (2) requests share much of their KV\$-reuse exceeds 80% of request tokens in a production trace from BAILIAN, versus 54-62% in chat. This paper first contributes a systematic study of request scheduling for agents on two real-world traces. We find that to increase KV\$ reuse, existing schedulers overly prioritize routing requests to instances caching their KV\$, overloading a few while leaving the rest idle, capping TPS. We thus present two key insights: (1) load balance need not sacrifice all KV\$ reuse, thanks to the global-tier KV\$ store and (2) by utilizing the workload's intra-session locality, balancing a small fraction of requests--the first request in each agent session--suffices to balance the cluster without sacrificing most KV\$ reuse on local instances. SMETRIC realizes these insights with balanced session-centric scheduling: it routes each session's first request purely for load balance and its follow-up requests in a cache-aware manner, preserving load balance and local reuse while keeping demand on the global tier low. Using the session turn information as the scheduling metric is deliberate: it is derived efficiently and accurately from the user inputs alone, so the scheduler stays clean and stateless. SMETRIC improves cluster TPS by 10-16% under prefill-decode colocation with a global store and prefill TPS by 2-34% under disaggregation over state-of-the-art schedulers, also with a better per-token latency. --- ### Contravariance Theory: Strong Alignment for Minimal Solutions to Hard Tasks Authors: Dan Yamins, Aran Nayebi Published: 2026-07-09 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2607.08561v2 A series of results from the NeuroAI over the past fifteen years have raised core questions both about how to compare Deep Neural Network (DNN) models to the brain, and about how much convergent evolution to expect between artificial networks and real brain networks. Here, we show that for any two minimal DNN solutions to a sufficiently hard task: (i) "weak" alignment of network representations based on affine mappings guarantees "strong" alignment of privileged axes, and (ii) alignment "zippers" up the network hierarchy, causing the emergence of privileged axes from end-to-end task optimization. These results formalize the notion of contravariance from Cao and Yamins (2024), and illustrate important consequences for the theory of NeuroAI: with sufficiently strong tasks, choice of metric for inter-network comparison is not all that sensitive, and that convergent evolution is probably inevitable. --- ### CAAD: Causality-Aware Multivariate Time Series Anomaly Detection via Multi-Scale Alignment and Structural Causal Consistency Authors: Xin Wang, Yunshi Wen, Yanan He, Haotian Xu, Youlan Zhao, Michel Ferreira Cardia Haddad, Tengfei Ma Published: 2026-07-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.08555v1 The operational integrity of complex industrial systems relies on precise anomaly detection and diagnosis. The vast majority of existing methods narrowly focus on capturing temporal similarities of representations, often overlooking the disruption of internal causal relationships, which characterizes system failures and latent anomalies. In this paper, we propose a novel framework (CAAD) that reframes anomaly detection as the continuous verification of Granger causality consistency through exogenous variables. Specifically, the CAAD framework models exogenous time-series variables as residuals, identifying anomalies as significant deviations caused by external interventions. The proposed framework leverages multi-scale alignment to internalize system dynamics and utilizes a gradient-based matrix to monitor internal causal relationship breakdowns. By quantifying causal deviations of both dynamic evolution and relational topology, the CAAD is able to capture subtle causal shifts to achieve precise anomaly detection. Extensive experiments on real-world industrial datasets demonstrate that the CAAD achieves high-precision anomaly detection, outperforming most state-of-the-art baselines. --- ### CommuniWave:A Machine Learning Model for Quantifying the Degree of Temporary Informal Behavior in Urban Communities Authors: Hongye Yang, Shien Liu, Zhihao Xie Published: 2026-07-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.08554v1 For urban managers and designers, improving the functional attributes of urban communities to enhance territorial resilience in the face of complexity and uncertainty is crucial. Currently, community planning often follows a top-down approach and lacks effective metrics to quantify informal behaviors of residents, leading to frequent conflicts with original plans. This study introduces CommuniWave, a machine learning model designed to efficiently detect and quantify the Degree of Informal Behavior (DIB) in urban communities. The model integrates a Behavior Capture Net (BCN) based on mmaction2, a self-developed YOLOv10 model (YLX), and a Behavior Eval Model (BEM) using random forest. Ultimately, by generating DIB fluctuation charts from street videos, the model facilitates dynamic monitoring, supporting urban managers in making refined decisions to enhance the overall resilience of communities. --- ### Structural Bottlenecks on Frequency Representation in End-to-End Audio Models Authors: Nicole Cosme-Clifford Published: 2026-07-09 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2607.08545v1 End-to-end neural audio models achieve high-fidelity compression and generation. We might read that performance as evidence they directly represent interpretable features such as pitch and timbre, but a model can produce plausible outputs without doing so. A model may encode these features in any reachable basis, but regardless of which, the features are well described as compositions of time-frequency-localized primitives. Whether state-of-the-art encoders preserve access to these primitives, and thus to compositions of them, remains unclear. Through theoretical analysis and controlled experiments, we show that several state-of-the-art strided convolutional encoders impose two structural bottlenecks, both predictable from architecture and signal structure, on access to these primitives: (1) they collapse primitives into alias equivalence classes, establishing a bound on representational capacity, and (2) they limit the frequency resolution available to learned filters, restricting separability. For well structured data, we find collapse rates of 31-35% and filter bandwidths 10-35x above the theoretical resolution bound, confirming that both bottlenecks arise under realistic signal conditions. We then introduce Gabor Latent Refactorization (GLRF), a lightweight post-hoc intervention that re-expresses encoder latents in a frequency-localized basis, reducing filter bandwidths from 10-35x to 1.5-3x of the theoretical resolution bound while preserving reconstruction fidelity and improving control over attributes like pitch. These results show that the encoders in question predictably degrade access to frequency-localized primitives, entangling the features that depend on them, and that a lightweight, retraining-free intervention can recover much of that access, improving steerability and interpretability. ---