# Research Papers — 2026-10 · bundle page 7 of 156

> Full-text markdown of papers #301–350 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-10/page/7
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/6.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/8.md)

### Compiling Multi-Threshold Operators for Quantized Non-Monotonic and Fine-Granular Activations in Custom-Tailored DNN Accelerators

Authors: Christoph Berganski, Felix Jentzsch, Marco Platzner
Published: 2026-10-15
Categories: cs.AR, cs.LG
arXiv: https://arxiv.org/abs/2610.21825v1

Aggressive quantization of neural networks can expose activation functions as bottlenecks for efficient hardware acceleration. Implementing quantized activations as multi-threshold operations has been shown to be a promising optimization, allowing for efficient hardware implementation of few-bit activations. However, current implementations are limited to monotonically increasing functions, quantization schemes with one-dimensional (per-channel) granularity and a small set of predefined activation-quantizer combinations. We formalize the multi-threshold representation to extend it to non-monotonic functions and fine-granular parameters, i.e., multi-dimensional thresholds. For automated conversion of quantized function compositions into threshold representation, we propose a systematic approach via algebraic rules integrated into the ONNX-based compiler infrastructure. We experimentally validate our solution on a selection of monotonic and non-monotonic functions by extending the binary search based multi-threshold operator that is integrated into the FINN framework for end-to-end synthesis of custom-tailored FPGA accelerators. The cost of hardware support for non-monotonicity and fine-granularity is characterized in comparison to an alternative approach utilizing existing operators via graph-level decomposition. We compare our method to prior work as well as the approach taken by the hls4ml framework. As an outlook, we demonstrate the prospects of using the multi-threshold representation during the training of a neural network as a form of quantization aware training.

---

### A Closed Form Depth-Width Law for Neural Collapse in Deep Linear Networks

Authors: Pankhil Gawade, Kirsten Fischer, Guy Wolf, Ewa Szczurek
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.21820v1

How depth and width of neural networks shape learned representations is usually studied only after training. We show that, in a tractable feature-learning setting, this dependence can instead be obtained in closed form. Using neural collapse as a probe of representation geometry, we express NC1--NC3 directly in terms of the learned feature kernel, extending an identity known for NC1 to the angular part of NC2 and to NC3 under a ridge readout. For deep linear networks with exchangeable class structure, the resulting kernel equations yield a geometric law, exact within the theory, for the layerwise evolution of within-class variability. At large width, the accumulated compression becomes a function of the depth-to-width ratio $L/N$, with its rate determined self-consistently by the data, prior and architecture. Numerical experiments support the derived dependence on depth, width and signal-to-noise ratio. The result is a representation-level scaling law derived from feature-learning theory rather than fitted after training.

---

### Measuring the local shape of learning-rate transfer curves

Authors: Satoki Ishikawa, Rio Yokota, Ryo Karakida
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.21814v1

Understanding the learning-rate (LR) dependence of trained model performance is essential for better optimization of neural networks, but the appropriate size of the LR depends on learning dynamics, architecture, and their hidden biases, and thus our understanding of this complex dependence remains limited. The behavior of the loss curve as a function of the LR has recently been observed in extensive experiments on LR transfer across different settings, such as model sizes, and it is becoming more important to explore methodologies for quantitatively characterizing the shape of this LR curve. In this work, we provide two relational equations that give a good empirical explanation of the gradient of the LR transfer curve, i.e., the LR gradient. One is a theoretical formula that holds at the edge of stability, and the other is an approximate expression obtained by naively treating this gradient as a hyper-parameter gradient. Using these two relational equations in a complementary manner, we show a lower bound on the gradient of the curve and a zero gradient under specific conditions for normalization layers in theory. The approximate expression also applies to a wide range of experimental settings and allows us to decompose the LR gradient into layer-wise components and quantify the strong contribution of specific layers to the curve shape. Thus, this serves as a foundation for better understanding the internal mechanisms of LR dependence.

---

### N-Gram Memories at Two Bits: Quantizing Lookup Tables in Large Language Models

Authors: Donghoon Han, Minseop Jung, Dong Woo Kwak, SeungJae Lee, Junhoo Lee
Published: 2026-10-15
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2610.21810v1

Conditional memory expands language-model capacity through selective lookup, but the full embedding table must remain available for every possible input. We introduce Conditional Program (CP), a compressed representation that reconstructs only the rows an input requests. CP represents each row by a short code and a local scale, with a reconstruction program shared across the table. We instantiate this representation with a Gaussian trellis, norm restoration and independently decodable row records. CP's two-bit code lowers output KL by 41--63\% relative to 2-bit round-to-nearest. Analysis across three trained n-gram memory families shows that Gaussian-like coordinate statistics coexist with learned relationships among rows; at matched storage budgets, the shared trellis outperforms the fitted codebooks and low-rank residual variants we test. For DeepSeek, it reduces table storage from 203GB to 51GB, leaving room for larger workloads when the table is kept on GPU.

---

### From Adults to Children: Benchmarking Foundation Models for Chest X-Ray Classification under Domain Shift

Authors: Sara Inácio, Hugo Proença, João C. Neves
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21809v1

Foundation models have shown significant potential across diverse fields and have been applied to medical imaging, but their robustness across patient populations remains unclear. In this work, we investigate foundation models' ability to generalize from adult to pediatric chest X-ray classification. To the best of our knowledge, this is the first benchmark to compare multiple foundation models under a common adult-to-pediatric evaluation setting while also analyzing the effect of adaptation depth. We harmonize VinDr-CXR and PediCXR into a five-label classification task and evaluate six foundation models and two CNN baselines. All models are adapted using adult data only and tested in both the in-domain and pediatric domains using linear probing, partial fine-tuning, and full fine-tuning. The benchmark reveals a clear and consistent trend: all models suffer a substantial performance degradation when transferred from adult to pediatric data, with drops exceeding 10 percentage points. While Macro-AUROC values reach approximately 92% on the adult test set, performance decreases to around 78% on the pediatric domain. Another important finding is that increasing the depth of adaptation does not significantly improve cross-population generalization. Moreover, strong in-domain performance does not translate into better performance on pediatric data.

---

### RoleQ: Role-Aligned Scales for Converting Language Models to Ternary

Authors: Johannes Knittel, Alec Helbling, Hanspeter Pfister
Published: 2026-10-15
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.21808v1

Weight quantization below four bits shrinks memory and bandwidth at a perplexity that looks acceptable, but often at the cost of factual knowledge and task accuracy. Ternary weights have mostly been obtained by training from scratch or long fine-tuning. We introduce RoleQ, a quantization framework that places scales by the functional roles of Transformer units rather than by the layout of the weight matrix, as conventional formats do. Vectors that read from the residual stream take one scale per output unit; those that write to it, one per input unit. The rule is structural, needs no search, calibration or stored state, and holds on integer and ternary grids. In a rotated basis it matches a per-layer axis search at half the solver work, and at ternary it cuts perplexity by up to half against layout-based placement in two families at every size from 0.6B to 14B, where per-row scales leave MMLU at chance. Our lightweight post-training pipeline converts an existing checkpoint to 1.59 bits per weight in a few GPU-hours, a fraction of the cost of learned ternarization, and leads every post-training ternary method at matched or lower memory-resident bits on perplexity, zero-shot accuracy and MMLU, most widely on knowledge. A sparse second ternary plane placed by a per-unit Fisher saliency keeps the matmul multiplication-free and recovers what ternary loses first: at 8B, a fraction of a bit returns about half the MMLU that conversion costs, well ahead of random or Hessian-based placement at equal bits.

---

### Content associations with answer selection and engagement in supply chain community question answering

Authors: Hisatoshi Naganawa
Published: 2026-10-15
Categories: cs.CL, cs.SI
arXiv: https://arxiv.org/abs/2610.21807v1

Community question-answering platforms are important ecosystems for knowledge sharing, yet research on what makes an answer best or a question engaging has often focused on either individual lexical features or broad topics. This exploratory study examines both levels in Yahoo! Chiebukuro, asking which nouns and semantic noun clusters are associated with best-answer selection and question engagement. We analyze a large corpus of questions and answer-tier posts collected under the keyword logistics, using an offline machine-translation pipeline with manually validated noun-level fidelity. Best-answer selection is modeled with conditional logistic regression within question threads, controlling for answer length, order, and question-answer noun overlap. Engagement is modeled in two stages: whether a question receives any response and, conditional on receiving one, how many responses it attracts. Operational logistics nouns such as distribution, warehouse, and center are associated with best-answer selection, whereas broader civic and infrastructure nouns such as car, tax, and shinkansen are associated with higher engagement. At the cluster level, most semantic noun clusters are associated with best-answer selection, while the clusters associated with response likelihood and response volume are largely distinct. These findings reveal differentiated content-outcome profiles across answer and question levels and provide a domain-wide descriptive map of engagement and answer selection in logistics-related cQA discourse.

---

### CIM-Embed: Learning Instruction-Conditioned Multimodal Embeddings for Clustering

Authors: Yinghua Xu, Pengyang Xie, Yanxiang Zhou, Chuanzhi Tong, Xiao Xiao, Chaoqun Feng, Xiaoqing Wang
Published: 2026-10-15
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.21805v1

Multimodal objects can require different partitions under different instructions, as when products in an e-commerce catalog are grouped by color, material, or both. Retrieval-oriented embeddings may not recover these partitions, while generative clustering often relies on intermediate descriptions or iterative decisions. This paper presents CIM-Embed, a framework for learning instruction-conditioned multimodal embeddings for clustering. Supervised contrastive learning uses same-group positives and negatives from other groups, optionally including other tasks; heterogeneous structured batches accommodate tasks with different group counts. At inference, the model maps each object's image, text, and instruction directly to an embedding; HDBSCAN then forms a partition without the ground-truth cluster count. We construct ProductMIC from product metadata in Amazon Reviews 2023, comprising training data and an evaluation benchmark for instruction-conditioned clustering. The benchmark contains 5,373 products and 449 single-attribute and compositional grouping tasks spanning 50 leaf categories excluded from our training. With full-dimensional embeddings and HDBSCAN, direct within-task SupCon training achieves a mean per-task V-measure of 95.01, compared with 53.06 for WeMM 9B, the strongest general-purpose embedding baseline evaluated. Frozen product-trained encoders also improve out-of-domain conditional grouping, while controlled transfer experiments distinguish partition transfer from instruction response. We will release the code and dataset upon acceptance.

---

### Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration

Authors: Wenju Sun, Qingyong Li, Boyang Li, Wen Wang, Siyu Zhang, Yi Wei, Yangliao Geng
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21804v1

Incremental learning (IL) aims to continually acquire new knowledge (plasticity) while retaining previously learned information (stability). However, striking a balance between plasticity and stability remains a significant challenge for intelligent systems. The human brain achieves exceptional balance, owing to various memory units that collaboratively encode and store information. Inspired by human memory mechanisms, this paper introduces an IL framework with knowledge enCoding, Consolidation, and Integration (Co2In). Co2In is designed as a bi-level memory architecture: a working memory for adaptive knowledge acquisition and a long-term memory dedicated to the persistent retention of information. The two memory modules work cooperatively during IL. The working memory first learns from new data to encode knowledge into parameters. Subsequently, Co2In performs a consolidation process to identify underlying patterns in the learned parameters and re-express them into a compact knowledge representation. Next, the knowledge representation and the identified patterns are transformed into separate network layers and integrated into the long-term memory. These designs empower Co2In to accumulate knowledge with high plasticity and stability. We evaluate Co2In on CIFAR-10, CIFAR-100, and Tiny-ImageNet under exemplar-free Class-IL and Task-IL settings. Experimental results show that Co2In achieves state-of-the-art performance with efficient memory consumption.

---

### Teaching DINOv3 About Partial 3D Geometry: A Self-Supervised Geometry-Aware Approach

Authors: Viktoria Ehm, Dongliang Cao, Riccardo Marin, Daniel Scholz, Weikang Wang, Florian Bernard, Daniel Cremers
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21802v1

Partial shape matching is a crucial yet underexplored problem in 3D vision, with significant relevance to real-world scenarios where shapes are often only partially observed. Existing feature descriptors face difficulties in this setting, as traditional representations either struggle with the boundaries of partial shapes or heavily depend on the shape's spatial position. While existing approaches have employed DINO features for partial shape matching, these features are not inherently suited for handling partial observations. In this work, we propose a method to refine DINO features using LoRA-based self-supervised learning, enabling the generation of feature descriptors that are robust to partiality. Our features substantially improve performance on partial shape matching compared to traditional or vision foundation features. Additionally, when integrated into existing partial shape matching pipelines, we achieve state-of-the-art results on partial shape matching and left-right prediction benchmarks.

---

### Behavioral Forgetting Is Not Privacy in Machine Unlearning

Authors: Tyler Lizzo, Larry Heck
Published: 2026-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.21799v1

Machine unlearning aims to remove targeted information from large language models, but existing evaluations often measure forgetting only on a designated benchmark distribution. We argue that such behavioral forgetting is an insufficient standard for privacy-oriented unlearning, and that evaluation should instead test whether forgetting persists across the access paths through which the same information may be recovered. We demonstrate this with a controlled case study of cross-lingual querying: across multiple multilingual model families, forgetting varies substantially when semantically equivalent information is queried in different languages and scripts. A single access path is therefore enough to expose a real gap between behavioral forgetting and information inaccessibility, motivating broader evaluation of access-path generalization and adversarial recoverability alongside in-distribution forgetting.

---

### Cross-Embodiment Causal Transfer from Human Videos to Robot Manipulation

Authors: Xingyu Zhang, Yingchao Li, Peizheng Guo, Jie Hu, Changwen Zheng, Wenwen Qiang
Published: 2026-10-15
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2610.21798v1

Scaling robot manipulation models requires large amounts of interaction data, yet collecting diverse real-robot experience remains costly. Human manipulation videos, in contrast, provide abundant and diverse task experience that could potentially benefit robot learning. However, differences in morphology, action spaces, and control mechanisms make human motions unsuitable as direct supervision for robot actions, raising a scientific question: what knowledge in human videos should be transferred across embodiments to robot manipulation? To address this question, we analyze subtask transfer through the lens of causal beams, focusing on which contextual conditions and interaction dependencies should be retained to support local task effects. Based on this perspective, we propose Causal-Beam-Guided Subtask Transfer (CBST). CBST learns manipulation-related representations from human videos and grounds them in task-level semantic variables using robot demonstrations. Within a predefined manipulation model, causal-beam constraints guide contextual information selection by requiring retained assignments to sustain local mechanism outputs while preserving nontrivial responsiveness to retained inputs. The selected semantic information conditions a world-action model, allowing the robot to generate actions from its own observations without requiring human-robot motion correspondence. Experiments on robot manipulation benchmarks show improvements in task success over the corresponding world-action model baselines.

---

### Single-stage joint diffusion of sky images and clear-sky index for ultra-short-term irradiance forecasting: what the frame-to-irradiance stage discards

Authors: Kanawut Suwandee, Suwichaya Suwanwimolkul
Published: 2026-10-15
Categories: cs.CV, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2610.21795v1

Sky-image irradiance forecasting is dominated by a two-stage design: a video-prediction model forecasts future sky frames, and a separately trained regressor maps those frames to irradiance. We propose a single-stage alternative that co-denoises the future sky-image and clear-sky-index sequences in one diffusion process, with an irradiance head that reads a denoised preview of the future sky rather than the noised diffusion state. The forecaster needs no regression stage and runs from sky images and deterministic covariates alone, with no measured irradiance at its input --- the situation at a site with a camera but no pyranometer. On 2023 SIRTA data the model reaches a pooled RMSE of $104.1$~W\,m$^{-2}$ and a skill score of $+0.34$ on the continuous ranked probability score (CRPS) against smart persistence, higher than any of twelve baseline configurations, and retains that skill when retrained on 2021--2022. On the model's own generated frames, a separately trained regressor reaches $150.6$~W\,m$^{-2}$ against the joint head's $104.1$: roughly $46$~W\,m$^{-2}$ that joint training recovers and a cascade discards. Point accuracy is competitive but not best: a deterministic network that also reads measured irradiance attains $97.6$~W\,m$^{-2}$. The model's CRPS skill leads that network's in every sky-condition tertile, by $0.26$ to $0.30$.

---

### MedPAO-VL: Interpretable and Protocol-Compliant Agent for Structured Radiology Report Generation

Authors: Shrish Shrinath Vaidya, Gowthamaan Palani, Minmini Selvam, Gokulraja Srinivasaraja, Ganapathy Krishnamurthi
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21794v1

Despite the remarkable generalization capabilities of Large Language Models, generating clinically accurate and structured radiology reports from medical images remains a significant challenge. Current end-to-end approaches function as black boxes, prone to factual hallucinations and generating ungrounded findings. This lack of reliability and failure to adhere to domain-specific structuring protocols, fundamentally limits their clinical utility. We present MedPAO-VL, a multimodal agent that shifts the paradigm from monolithic generation to explainable, iterative, protocol-compliant structured report generation. Unlike deterministic models, our plan-act-observe loop functions as a goal-oriented agent: it first perceives the Chest X-Ray through an explainable vision module designed to capture inherent diagnostic uncertainty, then iteratively refines the generated report by observing semantic discrepancies and self-correcting its generation for better alignment with visually detected clinical findings. Evaluation of our framework demonstrates that this agentic reasoning improves clinical correctness and completeness, achieving an expert-rated accuracy score of 3.5/5 and a structural score of 4.3/5. By prioritizing pathology specific explainability and iterative refinement over opaque end-to-end mapping, MedPAO-VL offers a transparent and clinically viable alternative for automated structured radiology report generation.

---

### RSIFlow: Adaptive Self-Improvement Workflows with an Evolving Meta-Agent

Authors: Huan Zhang, Mingju Chen, Dongxu Zhou, Can Lv, Sen Cui, Faguo Wu, Shiji Zhou
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21791v1

Large language model (LLM) agents have demonstrated strong capabilities in complex tasks, including code generation, tool use, and multi-hop question answering. Existing self-improvement methods enhance agent performance through model optimization, harness evolution, and executable artifact refinement, while recursive self-improvement (RSI) further extends optimization to the improvement mechanisms themselves. However, adapting self-improvement workflows to evolving performance bottlenecks while improving workflow orchestration through execution feedback remains a key challenge. We propose \textbf{RSIFlow}, a \textbf{R}ecursive \textbf{S}elf-\textbf{I}mprovement framework that integrates adaptive work\textbf{flow} orchestration with meta-agent capability evolution. RSIFlow diagnoses performance bottlenecks from task-agent trajectories and environmental feedback to dynamically select component-specific improvement workflows. The meta-agent then distills workflow outcomes into component-specific skills and cross-component principles, evolving its own harness to improve subsequent workflow orchestration. Experiments across six benchmarks and two backbone models show that RSIFlow achieves the SOTA average performance on all benchmarks. Ablation studies further demonstrate the contributions of adaptive workflow orchestration and meta-harness evolution. Code is available at https://github.com/1HUAN1/RSI-Flow.

---

### In the Guise of Correction: How Framing and Cultural Adaptation Erode LLM Safety on Real-World Criminal Cases

Authors: Mohsinul Kabir, Md. Tariquzzaman, Karam S. R. Elradie, Polydoros Giannouris, Yuechen Jiang, Shaoxiong Ji, Sophia Ananiadou
Published: 2026-10-15
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2610.21789v1

Existing safety benchmarks rely largely on synthetic prompts with loosely grounded taxonomies and offer little focused analysis of severe crime categories. We introduce GUISE, a benchmark of criminal-assistance scenarios sourced from real-world cases and organised under a taxonomy from the UNODC International Classification of Crime for Statistical Purposes (ICCS). Each scenario is rendered under three linguistic framings and evaluated across five distinct cultures. Using our proposed two-tier evaluation framework, which judges both harmfulness and operational uplift, we find that: (i) framing alone drives unsafe compliance, with the mean unsafe compliance rate rising from 28.9% under direct requests to 66.4% under correction seeking (peaking at 97.3%; p < 0.05), as models correcting deliberately distorted details supply executable criminal steps; (ii) culturally adapted prompts elicit significantly more unsafe compliance than literal translations of the same requests in all four non-English languages (+7 to +18 points), a risk that translation-based benchmarks miss; and (iii) unsafe responses from the least-safe models carry strong Anglocentric registers, and the extent of this leakage increases monotonically with response harmfulness ($ρ$ = 0.46 to 0.63 across languages, all p < 0.001). GUISE offers a grounded resource and fine-grained diagnostics for strengthening refusal alignment across languages and cultures. We publish our code and data to facilitate future research.

---

### NICE Toolbox: Nonverbal Interpersonal Communication Exploration Toolbox

Authors: Aleksandr Evgrashin, Carolin Schmitt, Timo Lübbing, Ashutosh Jha, Buket Naz Zeren, Sophie K. Bauer, Johannes Kopf-Beck, Anton K. G. Marx, Anamaria Semm, Gökce Ergün, Senya Polikovsky
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21786v1

Understanding human communication is a long-standing goal in psychological research. People express themselves through many verbal and nonverbal channels: posture, gesture, gaze, facial expression, and speech. Measurement and annotation of these signals has traditionally required time-consuming manual work by trained human labellers. The Nonverbal Interpersonal Communication Exploration (NICE) Toolbox is a free, open-source Python framework that automatically measures these signals by combining existing state-of-the-art computer vision and speech-processing methods into a single software package. It includes support for multi-camera systems, interchangeable detection algorithms, 2D and 3D visualization of detector outputs, evaluation on the user's custom data, and export to third-party software. With the release of this tool, we aim to make data exploration of interpersonal communication signals scalable, reproducible, and accessible for psychological research.

---

### Learning to Think and Explore in 3D World

Authors: Yijiang Li, Bingyang Wang, Nuno Vasconcelos
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21783v1

We study how vision-language models (VLMs) can learn to think and actively explore in 3D space. Instead of providing multi-view images, videos, or 3D representations to the model, we preserve the native visual encoding of VLMs, i.e., a single image, one at a time, just like humans, and treat the 3D representation only as an environment with which the model can interact through actions (e.g., move left) and observations (rendered images). Each rollout begins from an initial first-person view and a visual question. The model can then iteratively reason, navigate, and reorient its viewpoint before committing to a final answer. Following an initial trajectory-supervised finetuning, we apply reinforcement learning (RL) with rewards driven primarily by final-answer correctness. Crucially, RL provides no direct supervision over which viewpoints the model should visit or which exploration actions it should take. Instead, the model must learn an effective exploration policy solely from the extent to which its interactions improve performance. Across six 3D benchmarks, our model ACT3D achieves an average accuracy of 53.2% that improves its base Qwen model by 22.0% and surpasses proprietary Gemini 3.6 Flash. ACT3D also outperforms existing open-source 3D methods while using 50-70% fewer input frames, and generalizes to unseen domains with an average improvement of 5.9% over its supervised initialization. Further analysis reveals adaptive, question-conditioned exploration. Performance gains over the base model increase from 0.6% on questions answerable from the initial view to 16.3% on those requiring extensive exploration. ACT3D searches for occluded targets, avoids unnecessary exploration, and acquires complementary viewpoints for spatial comparisons. These findings demonstrate that outcome-based RL enables VLMs not only to reason over visual evidence, but also to learn when and how to acquire it.

---

### DINO-FIL: Multi-Layer Transformer Fusion for Generative Inpainting Forgery Localization

Authors: Simon Freitter, David Fischinger, Silvia Poletti, Marcel Hasenbalg, Martin Boyer
Published: 2026-10-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.21780v1

We propose DINO-FIL, a transformer-based framework for pixel-level localization of generative image forgeries. The method leverages multi-layer representations from a pretrained DINOv3 ViT-H+/16 encoder combined with a lightweight fusion decoder to capture both semantic structure and fine-grained texture inconsistencies introduced by image editing. By aggregating intermediate transformer features across depths, the model improves sensitivity to subtle, spatially localized artifacts that are often missed by standard single-layer approaches. We evaluate DINO-FIL in a cross-dataset setting, training on B-Free and testing on Beyond the Brush, CocoGlide, TGIF, and SAGI-D. The model achieves strong generalization, outperforming existing baselines on average and on four of five evaluated datasets, while maintaining a high true negative rate on pristine images.

---

### FuseAdapt: Parameter-Efficient Multimodal Fusion for Semantic Segmentation with Missing Modalities

Authors: Xin Zhang, Robby T. Tan
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21779v1

Multi-modal semantic segmentation benefits from complementary sensors, but this benefit is fragile when some modalities are degraded or missing at test time. Many existing methods rely on dedicated fusion modules or multi-branch cross-modal encoders, and the fusion often becomes unreliable when modalities are absent, leading to substantial performance drops. We propose \textbf{FuseAdapt}, a parameter-efficient framework that performs fusion within the adaptation space of a frozen vision foundation model (VFM), exploring whether VFM priors can serve as an effective shared backbone for multi-modal segmentation. Instead of attaching a standalone fusion network, FuseAdapt assigns each modality a lightweight adaptation branch and performs \emph{adaptation-space fusion} by keeping Q/V low-rank adaptation private to each modality and routing only FFN low-rank residual activations across modalities inside the frozen backbone. The pretrained VFM remains fixed while modality-specific corrections and explicit cross-modal interaction are learned through the adaptation paths. To handle missing modalities, we further introduce \textbf{Predictive Modality Modeling (PMM)}, a direct representation-level objective for cross-modal redundancy. During training, PMM masks a target modality and predicts its embedding from the visible ones, supervised by a teacher target computed under full-modality input. PMM is used only during training and adds no inference-time overhead. Across three multi-modal segmentation benchmarks (MCubeS, DELIVER, MUSES), FuseAdapt consistently improves both modality-complete and modality-incomplete segmentation with a small trainable budget, yielding up to +3.01 mIoU under full modalities and +12.56 mIoU under missing modalities over prior state-of-the-art. Project page: https://devinxzhang.github.io/FuseAdapt-Page/.

---

### Same Spectrum, Harder First-Order Training: Phase-Locking in Single- versus Multi-Qubit Re-Uploading Circuits

Authors: Michael Poppel, David Bucher, Maximilian Zorn, Markus Baumann, Sebastian Wölckert, Claudia Linnhoff-Popien, Philipp Altmann, Jonas Stein
Published: 2026-10-15
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2610.21778v1

Angle-encoded variational quantum circuits implement truncated Fourier series. For one-dimensional inputs, a single-qubit re-uploading (serial) circuit represents every function that a multi-qubit circuit with the same encoding budget $E$ can; we find that this exchange of width for depth is not free in first-order training. Because its state lives on the Bloch sphere, all parameters of the serial circuit move the state, at each input, along one complex direction, which we call \emph{phase-locking}. We prove that this costs no Fourier direction but leaves no direction to spare: however many parameters it has, the serial circuit has at most $2E+2$ tangent directions, one more than its $2E+1$ Fourier coefficients need, while a two-qubit control with the same encoding budget and model class generically has at least $6E+6$. The cost in training is measured against this control, as the number of runs out of 100 that reach the optimum within a fixed step budget. On an exact loss with flat-spectrum targets the gap grows with $E$; at $E=32$ the serial circuit converges in 3, 53 and 83 runs under gradient descent, Adam and Levenberg--Marquardt, the control in 99, 100 and 100. On three real-world series, at matched parameter counts, the serial circuit reaches the least-squares optimum in at most 9 runs under Adam and in 32 to 93 under Levenberg--Marquardt, the control in at least 98 and in all 100; its held-out error is up to about $1.5$ times that of the control under Adam, but no larger in the typical run under Levenberg--Marquardt.

---

### CF-AVSS: A Coarse-to-Fine Audio-Visual Speech Separation Framework with Target-Speaker Refinement and Post-Fusion for Real-World AVSE Challenge

Authors: Longjie Luo, Zhongshu Hou, Yuepeng Li, Gang Yang, Shidong Shang, Fan Zhou
Published: 2026-10-15
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2610.21773v1

Audio-visual speech enhancement (AVSE) leverages visual cues to recover target speech from mixtures corrupted by reverberation, noise, and overlapping speakers. We propose a coarse-to-fine two-stage AVSE framework. In the first stage, a progressive SPAV-TFGridNet is extended to two synchronized visual streams to produce visually ordered coarse estimates by progressively suppressing interfering speech while preserving target reverberation and shared background noise. In the second stage, a TFGridNet-based target speaker refinement network takes the original mixture and both coarse estimates as input to further recover target speech and improve signal quality. The coarse and refined estimates are finally combined using development-set-calibrated fusion. On the ISCSLP 2026 Real-World AVSE Challenge, our system tied for first place on Track 1 and ranked second on Track 2 in OVRL, while achieving the lowest CER on both tracks at 12.31% and 14.79%, respectively.

---

### From Research Goals to Scientific Closure: Evaluating Agents Through Evidence-Supported Physics Research

Authors: Yijia Mao, Song Dai, Tao Chen, Xiangyu Lu, Linqian Zeng, Chenxi Hu, Sitong Zhou, Dongyang He, Xiaodan Mao, Linxuan Zhang, Tong Zhu, Yafu Li et al.
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21767v1

Can AI agents organize scientific investigations that lead to well-supported conclusions? To evaluate this capability, we introduce PhysClosureBench, a benchmark of 50 expert-verified, goal-specified research tasks spanning strong-field, attosecond, and neighboring physics areas. Each task specifies the research objective and essential scientific constraints, while leaving the agent to organize the investigation and determine how to generate and validate the evidence needed to answer the question. A 20-criterion Atomic Score measures local scientific accomplishment, while Research Closure (RC0--RC4) assesses how fully the investigation resolves the specified research question based on whether its indispensable evidence requirements and applicable scope conditions are satisfied. We evaluate seven frontier LLMs, where Claude-Opus-5 achieves the highest mean Atomic Score (6.29/10) but reaches RC4 in only 32.7% of attempts. Across the benchmark, 36.2% of attempts scoring at least 8/10 still fall short of RC4, while all seven models reach RC4 on substantially fewer tasks in all three runs than in at least one. Case-level analysis further illustrates how misinterpretation of generated results and unresolved physical applicability limits can lead to incomplete closure. Together, these results reveal a persistent gap between AI agents' local scientific accomplishments and their ability to achieve complete research closure.

---

### Q($γ_H$): Entropy-Guided Horizon Mixing in Multi-Discount Q-Learning

Authors: Arwa Albelaihi, Abdulrahman Altahhan
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.21764v1

A fixed discount factor in Q-learning imposes a single planning horizon throughout training, despite the differing demands of early exploration and long-term credit assignment. We propose Q($γ_H$), a multi-horizon Q-learning framework that maintains multiple discount-specific heads and adaptively combines them at control time using an entropy-derived confidence signal. The resulting state-dependent mixing weights shift control from shorter- to longer-horizon heads as policy confidence increases, enabling adaptive horizon mixing without modifying individual Bellman updates. Across classical control and deep reinforcement-learning benchmarks, Q($γ_H$) shows its strongest improvements on delayed-credit tasks relative to strong fixed-discount baselines. By decoupling horizon adaptation from the underlying learning updates, Q($γ_H$) provides a lightweight framework for adaptive planning-horizon control in reinforcement learning, avoiding the need for manual discount-factor selection while remaining compatible with standard value-learning methods.

---

### Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods

Authors: Adnan Al Ali, Jindřich Libovický, Anne Lauscher
Published: 2026-10-15
Categories: cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2610.21763v1

Audio-enabled large language models (AuLLMs) allow users to interact with them simply by talking to them, without the need for an intermediate transcription. This expands the model's accessibility and capabilities by encoding non-verbal cues. However, using non-verbal cues may lead to biased behaviour based on the attributes inferred (or assumed) from them. In this work, we focus on the gender attribute and show that models' perception of it can be unlearned using adversarial methods without a loss in performance on other benchmarked tasks. Such models are useful in situations where gender inference is unwanted. However, in other practical settings, gender perception (without bias) may be desired.As a less radical measure, we distil the gender-agnostic model, creating a model that perceives gender but responds similarly to the gender-agnostic teacher, unless explicitly asked.We apply our newly proposed methods to three AuLLMs and obtain satisfactory results in the gender-unlearning part and partially satisfactory results in the distilling part.

---

### Beyond Generation: Using Multimodal LLMs as Detectors of LLM-Generated Deepfake Facial Images

Authors: Olivia Salamon, Virginia N. L. Franqueira, Shujun Li
Published: 2026-10-15
Categories: cs.CV, cs.ET
arXiv: https://arxiv.org/abs/2610.21760v1

As image generation models become increasingly capable of producing highly realistic content, traditional forensic techniques are struggling to keep up. This paper investigates whether MLLMs can instead be used as a form of forensic analysis by identifying synthetic media. Specifically, the study aims to determine whether these models detect fake images by recognising physical inconsistencies, or whether they rely on digital artefacts such as embedded watermarks.Six MLLMs: GPT-4o, GPT-5, GPT-5.2, Gemini 2.5, Gemini 3, and Seed 1.6, are benchmarked using a dataset of 400 images. Fifty images are authentic photographs, while the remaining 350 are generated using seven leading image models: Gemini 3, Gemini 2.5, Flux.2 Pro, GPT-Image-1, GPT-Image-1.5, Seedream 4.0, and Seedream 4.5. The evaluation is structured in three stages: single-image classification, pairwise comparison, and a focused "self-detection" experiment on Gemini. Several MLLMs achieved a high detection accuracy, with GPT-5.2 reaching a peak of 97.9% in the pairwise experiment, against specific generators and an overall mean pairwise accuracy of 82.5% by identifying structural or physical inconsistencies within images. However, results from the self-detection experiment indicate that the presence of invisible SynthID watermarks leads to a 10% reduction in Gemini's detection accuracy compared to the clean control group. One possible explanation is that SynthID embedding reduces some of the visible artefacts the models rely on for detection.These results imply that MLLMs can detect structural artefacts without relying on watermarks, but performance varies substantially across model generations. The findings from comparison C5 also suggest that SynthID embedding may suppress some of the structural artefacts used during detection.

---

### Beyond Source Prompts: Towards Visually Grounded AI-Generated Video Quality Assessment

Authors: Kehao Zhou, Yixuan Li, Yuxuan Jiang, Fan Zhang
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21758v1

Recent advances in generative artificial intelligence have accelerated video generation technologies. However, AI-generated videos (AIGVs) remain susceptible to various distortions, highlighting the need for dedicated video quality assessment methods. Content semantics play an important role in AIGV quality assessment, with source prompts typically used as textual references. However, these prompts may not accurately reflect the generated video content, resulting in a discrepancy between the intended textual description and the generated result. To address this limitation, this paper proposes VGCap, an AIGV quality assessment framework guided by visually grounded captions that align better with generated content. Specifically, we introduce two forms of captions: a global caption obtained by minimally revising the source prompt based on multi-frame visual evidence, and prompt-independent segment captions that describe localized temporal content. Together, these captions provide complementary textual evidence for assessing spatial quality, temporal quality, and text-video alignment. Experimental results on the LGVQ and FETV datasets show that VGCap outperforms representative baselines across all three dimensions. Further ablation studies on caption sources and temporal components confirm the effectiveness of visually grounded captions for each quality dimension, while highlighting the benefits of segment-level features for temporal quality prediction. The source of VGCap will be available at https://github.com/lolo123-123/VGCap.

---

### DeciCAD: Harness-Grounded Learning of Action Policies for CAD Agents

Authors: Yufeng Peng, Yixin Zhang, Ziyi Liu, Zhikun Xu, Jiarong Yang, Sijie Wang, Wenjie Feng, Qiyu Kang
Published: 2026-10-15
Categories: cs.AI, cs.CL, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2610.21755v1

Large Language Model agents operate through closed-loop action policies whose decision space is defined by an agent harness. We investigate how this operating space shapes agent behavior and policy learning in computer-aided design (CAD), a professional domain characterized by persistent state, geometric constraints, and long-horizon procedures. We instantiate this perspective in DeciCAD, a domain-native harness that exposes semantic CAD actions, decision-oriented observations, environment feedback, and persistent state transitions. Building on this harness, we develop a learning pipeline that extracts causal decision supervision from interaction trajectories and improves the policy through supervised fine-tuning (SFT) and geometry-grounded online reinforcement learning (RL). Across four CAD benchmarks, DeciCAD achieves the best F1 and intersection over union (IoU) while reducing model-output tokens by 45--88% relative to a general-purpose coding harness. Under matched supervision, its SFT policy improves F1 from 0.6883 to 0.7437 and outperforms the coding policy; subsequent online RL further raises geometry availability from 66.5% to 73.5% and F1 to 0.7880. These results demonstrate that the decision space induced by a harness materially affects both agent execution and policy learning in CAD.

---

### Harmful Partial Interventions and Benign Leakage in Concept-based Models

Authors: Gregory Verghese, Christopher J. Soelistyo, Mateo Espinosa Zarlenga, Alessandro Barp, Christopher R. S. Banerji
Published: 2026-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.21750v1

Artificial intelligence systems deployed in high-risk settings increasingly require models that support meaningful human oversight. Concept-based models (CMs) offer a promising framework by enabling users to inspect and intervene on intermediate, human-understandable concepts. However, concept interventions can counterintuitively worsen downstream predictions, a failure mode we formalise as intervention harm. We distinguish harm after all concepts have been intervened on from harm under partial interventions, the more likely practical use case. Modern CMs often achieve high accuracy by encoding, or leaking, additional task-relevant information in their intermediate concept representations. Recent work argues that such leakage can be benign with respect to intervention harm when concept representations satisfy two conditions: sufficiency and localisation. We prove that these criteria are not sufficient to guarantee that concept interventions improve downstream performance. Across controlled and real-world settings, we find that concept supervision incompleteness is associated with increased intervention harm. Importantly, optimising the model when all concepts are intervened on, a previously proposed leakage mitigation objective, reduces endpoint harm but does not reliably prevent harmful partial corrections. Hence, we introduce a complementary monotonic intervention objective that directly penalises increases in task loss along partial intervention trajectories. Combining endpoint and monotonic intervention training substantially reduces the prevalence and magnitude of partial intervention harm while preserving concept and task predictive performance.

---

### The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks

Authors: Ruichen Ma, Yicai Chen, Pujun Zhou, Yue Zuo, Chongyang Li, Shuang Liu, Shaogang Hu, Guanchao Qiao
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21748v1

Spiking neural networks (SNNs) offer a compelling pathway toward energy-efficient artificial intelligence, fundamentally anchored in presynaptic input-driven sparsity. However, a substantial yet chronically overlooked source of computational overhead persists: the continuous subthreshold dynamics of postsynaptic neurons. Quantitative analysis reveals that up to 44% of neurons in an ImageNet-trained ResNet-18 model reside in a deeply inhibited state, imposing a persistent computational burden despite having a negligible probability of firing. To address this inefficiency, the Dormant Spiking Neuron (DSN) model is introduced. By incorporating a state-driven dynamic gate, the DSN allows a neuron to enter a dormant state when its membrane potential falls below a predefined negative threshold, dynamically pruning redundant computations at the instance level. Crucially, this dormancy mechanism is directly integrated into the neuronal dynamics and trained end-to-end via backpropagation through time using surrogate gradients, enabling the network to actively learn a robust dormancy policy that adaptively preserves critical information flow. Extensive experiments across static and neuromorphic datasets demonstrate that the DSN framework consistently reduces computational energy by 40% to over 70%. Notably, on the large-scale ImageNet dataset, the DSN outperforms state-of-the-art static pruning techniques at comparable reported cost reductions and simultaneously improves the corresponding baseline SNN accuracy by 1.34%. By establishing a trainable, state-driven sparsity paradigm orthogonal to conventional input-driven methods, the DSN unlocks synergistic efficiency gains, presenting an effective approach for advancing neuromorphic computing.

---

### The Delegation Dilemma: Economies of Scale, Accountability, and Polycentric Governance

Authors: Arin Mukhopadhyay, Aris Filos-Ratsikas, Panayiotis Danassis
Published: 2026-10-15
Categories: cs.MA, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.21746v1

Many collective-action systems are neither fully decentralized nor fully centralized: agents voluntarily organize into institutions that share organizational costs and delegate decisions to representatives. Delegation can reduce individual costs, but it also transfers control to representatives whose private objectives need not align with those of their constituents. We study this tension in a repeated game with endogenous delegation to self-interested centers. A simple reduced-form model yields a scale--accountability tradeoff: larger constituencies offer greater cost-sharing benefits to members, yet the marginal value to a center of retaining any one constituent decreases as group size grows. Consequently, the prospect of individual exit can sustain non-exploitative delegation only up to an endogenous accountable constituency size. Additionally, we identify parameter regions in which fully delegated, accountable governance, when feasible, must be polycentric. We investigate these predictions through simulations with large language model (LLM) agents. Across five matched pairs of 30-agent simulations, polycentric structures repeatedly emerge but remain fluid, exhibiting cycles of concentration, exploitation, exit, and re-formation. We further find that models of different capacity exhibit similar willingness to assume leadership but differ substantially in their exercise of authority, with Sol initiating exploitation more frequently than Luna in matched decision states.

---

### Pairwise AUC Optimization Needs Corrective Power: A Unified View

Authors: Jia Chen, Zhiyong Yang, Shilong Bao, Qianqian Xu, Qingming Huang
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.21743v1

Direct pairwise AUC-surrogate training is attractive because it trains toward the ranking metric used at test time, especially under class imbalance. This creates a direct alignment between the training objective and the evaluation metric, but such metric alignment alone does not guarantee that stochastic training remains corrective. We study this gap through Corrective Power: whether pairwise mini-batch updates produce stronger and more reliable improvements for more severe positive-negative ranking errors. Our main observation is that direct pairwise training can enter regions where severe errors remain common but no longer produce useful corrective motion. In such regions, even the mini-batch noise that would normally help SGD move along the steepest severe-error correction direction can become much weaker. In this paper, we seek a theoretical explanation for this by exploring the degenerate property of the U-statistics formed from the pairwise gradients therein. Our results provide a mechanistic explanation for several empirical patterns: (a) squared-hinge loss is often an effective AUC surrogate; (b) cross-entropy warm-up can help models that enter the AUC phase from a poor starting region; and (c) parameter-efficient fine-tuning from a pretrained model can reduce that need by starting closer to a favorable ranking geometry. Experiments on 8 CV tasks and 8 NLP tasks, using ResNet50, DenseNet121, DistilBERT-base, and Qwen2.5-1.5B-Instruct, support these predictions.

---

### Sparse Federated Echo State Networks for Time-Series Classification via Smooth-L1 Regularization

Authors: Gengcheng Lyu, Manuel Röder, Frank-Michael Schleif
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.21742v1

Echo State Networks (ESNs), as lightweight implementations of reservoir computing, provide efficient solutions for temporal data processing in resource-constrained environments. While standard ESNs offer computational efficiency, their dense readout layers inflate the stored model and the per-sample inference cost. This paper introduces a Smooth-L1 regularized ESN (SL1ESN) that promotes sparsity in the readout layer while preserving differentiability for gradient-based optimization. The method employs a twice-differentiable Smooth-L1 approximation compatible with Newton's method, which we exploit both for centralized training and for a second-order (Newton-step) federated aggregation scheme. Under a single fixed shrinkage threshold shared by every dataset and both settings, experiments on seven time-series classification benchmarks show that SL1ESN learns readouts that are $77$--$95\%$ sparse in the centralized setting and $75$--$95\%$ sparse in the federated one, while staying within $0.7$ accuracy points of the strongest dense baseline on five of the seven benchmarks in the centralized setting and within $1.6$ points on the same five in the federated one, and the second-order federated update converges in only a few rounds. The resulting sparsity compresses the stored model, the per-sample inference cost, and the server-to-client broadcast by a comparable factor. These results demonstrate the practical value of sparse readouts for edge computing and IoT deployments.

---

### Reliable Knowledge Acquisition for Continual Learning Agents

Authors: Yixu Huang, Jiaqi W. Ma
Published: 2026-10-15
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.21739v1

As agents powered by foundation models move into open-ended environments, continual learning from experience becomes essential. For agents built on models with fixed parameters, this learning requires reusing prior task experience in context to improve performance and efficiency on future tasks. Existing memory and experience-learning systems typically focus on either retained facts or procedures, and lack a mechanism for establishing the reliability of claims extracted from the ongoing task stream. Indeed, we find that approximately 12--33\% of entries produced by representative systems harm future task performance when reused. To address these limitations, we propose \textbf{RIKA} (Reliable Knowledge Acquisition), which combines hierarchical extraction of factual, conceptual, procedural, and metacognitive knowledge with Evidence-based Knowledge Admission, which uses source evidence and subsequent experience to govern which claims enter the task agent's context, without additional validation tasks. Across six task streams from Continual Learning Bench and four model backbones, RIKA achieves the highest aggregate score on every backbone.

---

### SceneWeave: Audience-Guided Scene Exploration for Dramatic Adaptation

Authors: Aolin Li, Xiao Xu, Haihua Xie
Published: 2026-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.21737v1

Adapting prose into a script requires transforming narration and inner experience into scenes that convey relationships and psychological contradictions. Planning specifies intended effects but leaves their realization in dialogue and action unresolved. Drawing on screenwriters' accounts of revising scenes and their connections to the surrounding work, we present SceneWeave, which uses alternative scene drafts to revise the adaptation as a whole. It writes contrasting treatments of a focal scene, compares the interactions they create, and revises characterization, preceding preparation, subsequent development, and scene order before generating the complete script. The central contribution is to use actual scene writing to inform adaptation decisions and propagate their consequences across the work. We also develop a task-specific writing model and a human-preference model for comparing script drafts. The writing model learns from adaptation examples and human preferences; the preference model combines human and synthetic supervision. Blind reader comparisons favor SceneWeave over a baseline workflow and description-based controls, while content assessment indicates reduced narrative redundancy and strong psychological treatment.

---

### In-Context Preference-Conditioned Pareto Set Learning from Limited Offline Data

Authors: Yiming Yao, Liang Zhao, Qingfu Zhang
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21736v1

Multi-objective optimization involves diverse preferences over conflicting objectives. Rather than returning a finite set of trade-off solutions, preference-conditioned Pareto set learning seeks to map a specified preference directly to a corresponding Pareto optimal solution. Yet in many real-world scenarios, optimization must proceed offline without further objective evaluations, leaving only a limited static dataset that sparsely covers the decision and objective spaces. Existing methods either optimize separately for each preference or train a problem-specific Pareto solution model, requiring repeated search across preferences or repeated training across problems. We introduce in-context preference-conditioned Pareto set learning (ICPSL), a framework that amortizes both preference-wise solution search and problem-specific model construction. ICPSL pretrains a foundation-style hypernetwork on a large and diverse set of synthetic prior data. Given the offline observations of an unseen problem, the pretrained hypernetwork learns to generate a problem-specific, preference-conditioned Pareto solution model in a single forward pass. The generated model can then be reused to predict solutions for arbitrary preferences without problem-specific training or preference-wise search. Experiments on synthetic and real-world problems show that ICPSL produces high-quality Pareto solutions while providing substantial speedups in problem-specific solution-model construction.

---

### Retrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available Evidence

Authors: Owen Walters, Lihu Chen, Francesca Toni
Published: 2026-10-15
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2610.21731v1

Web search allows LLMs to access up-to-date information, but it remains unclear why they sometimes produce outdated answers even when relevant evidence is available. To study this problem, we construct temporal facts whose values changed after the models' training cutoffs. We evaluate one proprietary model under deployed web search and six open-weight model configurations under controlled retrieval. We find that models often answer from search snippets without opening the source pages, which is associated with higher rates of outdated answers and unfaithful citations. Our controlled experiments and layer-wise analysis reveal a gap between the availability of evidence and its effective use. Even when retrieved evidence influences internal predictions, models may still favour outdated information in their final answers. We hope these findings will help advance research on the reliable use of retrieved evidence in search-augmented LLMs.

---

### FIRM: Fisher-Informed Retention Merging for Federated LLM Unlearning

Authors: Reeyansh Shah, Maram Hasan, Subhasis Chaudhuri, Biplab Banerjee
Published: 2026-10-15
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.21720v1

Federated LLM unlearning addresses targeted knowledge removal when forget and retain data remain distributed across private clients and are inaccessible to the server. The resulting locally trained adapters encode conflicting objectives, making their aggregation fundamentally different from conventional federated optimization. A key failure mode is magnitude explosion, whereby unnormalized cross-client aggregation increases the merged update magnitude and degrades retained utility under stronger unlearning. We propose FIRM (Fisher-Informed Retention Merging), a single-round framework for stable and retention-aware server-side aggregation. FIRM uses client-local Fisher statistics as a unified sensitivity signal to construct a Fisher-normalized base merge and impose explicit control over retain-sensitive parameters. Its second-order retention projection admits a unique minimum-distance solution, while the corresponding dual scales with the number of retain clients rather than the model dimension. Experiments across WMDP, TOFU, and MUSE-HP using Zephyr-7B and Llama-3-8B show utility gains at comparable forgetting on WMDP and MUSE-HP, with metric-dependent trade-offs on TOFU. Controlled comparisons support benefits of the combined base merge and additional retention correction at selected operating points.

---

### International Multi-Centre Validation of Unsupervised Domain Adaptation for Precise Discrimination between Normal and Abnormal Retinal Development

Authors: Zhanhan Tu, Nikhil Reddy, Helen J. Kuht, Ha-Jun Yoon, Gail D. E. Maconachie, Ravi Purohit, Prateek Pani, Line Kessel, Jinu Han, Jing Jin, Shui-Hua Wang, Karthik Bharadwaj et al.
Published: 2026-10-15
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.21719v1

Arrested retinal development can cause childhood visual impairment, but grading optical coherence tomography scans is difficult to standardise across devices and centres. We developed and evaluated an unsupervised domain adaptation model to classify normal and abnormal retinal development across different OCT systems. This retrospective multicentre study used OCT scans from five centres in four countries and the UK Biobank. Data covered four OCT devices, including table mounted and handheld systems. A ResNet50 based Domain Adversarial Neural Network was trained using labelled images from a source device and unlabelled images from a target device. We evaluated six source to target pairings and compared model performance with seven clinician graders. A separate Heidelberg Spectralis dataset was reserved for external evaluation. Across validation sets, accuracy ranged from 87.75% to 96.06%, sensitivity from 88.68% to 98.38%, and specificity from 78.00% to 98.02%. The best performing model, adapted from TM OCT1 to HH OCT1, achieved 96.06% accuracy and an area under the receiver operating characteristic curve of 0.994, with a 95% confidence interval from 0.981 to 0.999. Several models also maintained discrimination on the unseen Heidelberg device. Unsupervised domain adaptation enabled OCT classification across devices without labelled target device data. The approach may support more consistent assessment of retinal development and large scale analysis of existing imaging datasets.

---

### Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems

Authors: Linda Beková, Rodrigo Alves
Published: 2026-10-15
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2610.21713v1

Language embeddings are increasingly used in recommenders to represent item content, but their privacy risks remain poorly understood. We study whether item embeddings can reveal item identities when an adversary has access to auxiliary item text from external sources. We show that a simple cosine-similarity attack can recover item identities with high mean reciprocal rank across language models and candidate-set settings on two real-world datasets. Leakage is strongest when the adversary's partial information overlaps with the victim representation, but it also persists through semantic alignment between independently sourced descriptions. We further show that item leakage can propagate to user re-identification from sparse ratings. Finally, we evaluate obfuscated descriptions as a mitigation and find a clear leakage-utility tradeoff.

---

### Robust Covariance Estimation for Entry-wise Contaminated and Partially Observed Data via Expectation Maximization Algorithm

Authors: Matys Savidan, Mohammed Nabil El Korso
Published: 2026-10-15
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.21709v1

Robust covariance estimation under entry-wise contamination and missing data is challenging in various signal processing applications. Under the Student-$t$ model, observation-level reweighting induces a uniform attenuation across samples, which can lead to cumulative information loss even when most coordinates remain informative. The alternative Student-$t^*$ model enables coordinate-wise robustness, but its E-step is not available in closed form. We extend inference for the Student-$t^*$ model to incomplete observations through a stochastic approximation EM (SAEM) algorithm operating on a reduced latent space: stochastic updates of the coordinate-wise scales are combined with Rao-Blackwellized Gaussian conditional moments, which avoids explicit sampling of latent Gaussian variables while preserving a likelihood-based framework. Experiments on synthetic and real sensor data show a lower Fisher-Rao error than Gaussian, Student-$t$, imputation-based and detect-then-estimate estimators at moderate to high outlier rates under diffuse contamination.

---

### Human Interventions as Labels: Localizing, Steering, and (Sometimes) Editing the Computations Behind LLM Agent Failures

Authors: Cesare Zavattari, Alessandro Tommasi, Giuseppe Prencipe
Published: 2026-10-15
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.21708v1

When an LLM agent misbehaves, a human steps in, and that intervention is usually discarded or replayed as training data. We treat it instead as a measurement: a label pointing at the internal computation that failed. We study it in a controlled agent environment, on one failure (asking a clarifying question when the request was already unambiguous), with labels from a rule-based overseer validated against blind human judgment. Claims cover eligible models, which both over-ask and sometimes act on matched unambiguous requests: five of thirteen qualified (Qwen2.5-3B, gemma-2-2b, OLMo-3-7B, Mistral-Nemo-12B, Phi-4). Four findings. First, the ask-vs-act decision is causally localizable in every eligible family: a direction learned from intervention labels flips 72-100% of held-out over-asks at a definite residual-stream depth, with site and dose chosen on training data, and random directions under the same procedure flip at most one episode. Second, over-asking has two mechanistic signatures: in four families the model demonstrably knows the request is unambiguous (the belief is decodable, causally inert and orthogonal to the decision) and asks anyway; in the fifth, the rare over-asks track different world-representations. Third, steering gated on a probe readout removes most of the simulated oversight burden while legitimate questions survive (bootstrap 95% intervals exclude zero); a prompt instruction makes it worse. Fourth, consolidating the fix into the weights yields a map, not a rule: on one model a LoRA confined to the causal band passes every criterion fixed in advance while behavior cloning on identical data breaks retention; on three families the reverse holds; on the fifth the outcome crosses the boundary across seeds. A geometric rule written down in advance to predict the regime failed on two out-of-family tests; we report the failure and stop rather than fit a replacement.

---

### Mixture of Multi-Sequence Feature Difference for Contrast-Enhanced MRI Synthesis

Authors: Jonghun Kim, Junmo Kwon, Hyunjin Park
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21703v1

Contrast-enhanced magnetic resonance imaging (CE-MRI) is crucial for accurately diagnosing and segmenting brain tumors. However, the acquisition of CE-MRI requires injecting contrast agents, which poses potential health risks and increases scan costs. Here, we propose a CE-MRI synthesis method from non-contrast sequences, reducing both risk and cost. Unlike existing methods that rely on channel-wise concatenation to fuse multi-sequence information for synthesis, we introduce a Mixture of Feature Difference (MoFD) module. The proposed module uses a dynamic weighting strategy to adaptively select and aggregate informative features from both individual source sequences and explicit differences among them. Quantitative and qualitative evaluations demonstrate that our proposed method outperforms baselines in terms of image fidelity and perceptual quality on the UCSF-PDGM and UPenn-GBM datasets. Our method successfully reconstructs tumor regions and achieves segmentation performance comparable to that obtained with real CE-MRI. Our ablation studies show that although adversarial learning improves perceptual quality, a regression-based variant of our method achieves higher structural fidelity.

---

### Bridging the Markerless Tracking Validation Gap: Intraoperative X-ray Workflow Integration

Authors: Connor Daly, Salvatore Russo, Jinendra Ekanayake, Daniel S. Elson, Ferdinando Rodriguez y Baena
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21696v1

Markerless intraoperative tracking of spinal anatomy via RGB-D sensors is a promising alternative to invasive bone-anchored fiducials, yet no existing clinical dataset provides independent subsurface ground truth for validating these methods. We address this gap with a clinically viable pipeline that derives per-vertebra 6-DoF pose from routine intraoperative C-arm fluoroscopy, co-registered to the RGB-D camera frame through a multimodal fiducial array detectable in both imaging modalities. Critically, the pipeline requires no additional radiation, instrumentation, or deviation from standard surgical workflows, relying solely on the fluoroscopic images already acquired during routine level checks. A calibrated transform chain links the vertebral pose recovered via multi-view 2D-3D CT-to-fluoroscopy registration to the RGB-D coordinate frame, enabling direct comparison of any markerless registration estimate against a subsurface reference. Ex vivo validation against optically tracked ovine vertebrae confirms end-to-end accuracy of 2.06 +- 0.29 mm and 3.35 +- 0.93 degrees, sufficient to serve as independent ground truth for methods with substantially larger errors. We demonstrate the pipeline's utility by evaluating two markerless registration strategies on clinical data spanning 11 vertebrae across 1,500 frames from three surgical sequences: the first such evaluation against an independent subsurface reference in a clinical setting. The proposed framework provides reusable infrastructure for benchmarking emerging markerless tracking methods on real surgical data.

---

### ShiftQAT: Quantization-Aware Training for the Numerical Contract of a Fixed-Function Edge CNN Accelerator

Authors: Oguzhan Buyuksolak, Osman Erman Okman, Mehmet Gorkem Ulkar
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.21695v1

Fixed-function CNN accelerators make edge inference fast and energy-efficient, but they execute only networks that obey a precise numerical contract. On the MAX7800x family, this contract requires power-of-two, per-tensor, symmetric scales, 8-bit activations and biases, integer-only arithmetic, and one statically configured shift per layer. We present ShiftQAT, the quantization-aware training (QAT) flow we developed for this family, which produces networks satisfying the contract by construction. It is the default training path of ai8x-training, the family's open-source training toolchain. ShiftQAT resolves residual, concatenation, and weight-sharing dependencies so that activation scales propagate statically and each layer's requantization reduces to one offline-configured shift. It also trains weights and biases on a joint power-of-two grid that fits the 8-bit bias budget. Among the compared methods, only ShiftQAT satisfies all of the contract's scaling constraints, including signed 8-bit activation storage. Even so, on ImageNet it matches the W8A8 accuracy drop of less constrained QAT methods and stays within 2.9 percentage points of FP32 at W4A8. On MAX78002 silicon, ShiftQAT-trained MobileNetV2 and ResNet-18 classify ImageNet images in 14.6 and 8.4 ms at 5.1 and 2.8 mJ per inference.

---

### Abstracts or full text? Evaluating input scope and computational efficiency in biomedical lay summarization

Authors: Egecan Çelik Evgin, İlknur Karadeniz, Olcay Taner Yıldız
Published: 2026-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.21690v1

Biomedical research articles are mainly written for experts and often contain terms that are difficult for the general public to understand. Automated lay summarization has become a solution to make biomedical knowledge easier for patients and the public to understand. However, generating lay summaries from full-text articles requires more computing power because the articles are long and costly to process. Fine-tuning large language models for this task also requires substantial resources. This study asks two questions: (1) whether abstracts contain enough information to produce lay summaries as good as those based on full-text articles, and (2) whether few-shot learning performs as well as task-specific fine-tuning. The study used two public biomedical lay summarization datasets and two recent models, evaluated for readability, factual consistency, semantic similarity, and runtime efficiency. Results show that abstract-based summarization performs better overall. Across both datasets and models, abstract fine-tuning is 4.70 times faster, while abstract zero- and few-shot prompting is 5.31 times faster than full-text methods. These results show that abstract-based prompting reduces runtime cost while maintaining lay summary quality.

---

### MARS: A Momentum-Aware Adaptive Rating System for Personalized Assessment

Authors: Vikrant Sahu, Khethavath Sunil Naik, Gagan Raj Gupta
Published: 2026-10-15
Categories: cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2610.21685v1

Adaptive assessment systems personalize learning by estimating learner proficiency and recommending suitable questions. However, many existing approaches rely on fixed difficulty labels, static rating updates, or black-box prediction models that provide limited control over rating stability, interpretability, and time-constrained routing. This paper proposes MARS, a Momentum-Aware Adaptive Rating System for interpretable adaptive assessment. MARS represents the question bank as a directed weighted knowledge graph and updates learner proficiency using dynamic rating sensitivity, response quality, and momentum-aware learner velocity. We also formulate a time-budgeted mark-maximization objective in which the policy selects questions within a fixed test duration under negative marking. Experiments on ASSISTments 2009 and MARS-SimExam evaluate MARS for prediction, rating stability, and adaptive routing. Results show that MARS provides smoother rating updates than Fixed Elo and achieves the highest score under time-budgeted negative-marking routing, improving the total score by 8.09 over the strongest baseline and reducing overtime violations from 50% to 5.6%. These results suggest that MARS is suitable for real-time, interpretable, and deployment-friendly adaptive assessment.

---

### Router Drift Control: Mitigating Off-Policy Degradation in Mixture-of-Experts Reinforcement Learning

Authors: Liangyao Jin, Zhixin Wang, Liming Liu, Mingjun Zhang, Zhengzhou Zhu, Fangcheng Fu, Jinlong Hou, Yuan Cheng, Xiaohe Hu, Ping Zhang, Siyuan Feng
Published: 2026-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.21682v1

Reinforcement learning (RL) can become off-policy due to training-inference mismatch, mini-batch updates, and asynchronous training.The resulting mismatch is especially harmful in Mixture-of-Experts (MoE) models, where rollout--training discrepancies can change routing decisions and lead to router drift. Rollout Routing Replay (R3) mitigates this mismatch by reusing expert selections from the rollout stage during training. Our analysis shows that routing replay introduces gradient bias by losing contributions from experts selected by the training router but not the rollout router. To address this, we propose Router Drift Control (RDC), which uses routing disagreement between rollout and training as a signal of off-policy staleness and selectively rejects high-drift responses. The sequence-level filtering avoids gradient bias introduced by replay while preserving native expert selection and the associated learning signals for retained responses. Experiments show that RDC achieves larger gains as policy staleness increases and remains effective in asynchronous RL. In asynchronous training, RDC combined with Truncated Importance Sampling (TIS) improves the average peak validation accuracy across AIME 2024 and AIME 2025 by 5.5 points over TIS and 4.5 points over R3.

---

### Data Strategies for Large Language Models: A Unified Perspective on the Training Lifecycle

Authors: Yuanjian Xu, Jianing Hao, Tianze Sun, Yongyao Duan, Sam Chen, Jinyi Han, Wanbo Zhang, Yuxuan Sun, Guang Zhang, Zhong Li
Published: 2026-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.21681v1

Data strategy plays a central role in training large language models (LLMs). It governs the selection, weighting, and scheduling of training data, thereby determining the capabilities a model can acquire from a fixed data budget. We treat high-quality data as having high training-dependent utility, which depends on the target objective, the model, and its training state rather than on the text alone. Research in this area now spans pretraining and post-training, but related ideas use inconsistent terminology and evaluation protocols. This work reviews data strategies across the training lifecycle and formulates them as policies that allocate a training budget over candidate examples. We organise methods by their decision granularity, model dependence, and temporal adaptivity, then compare their computational requirements and empirical support. Fine-grained or state-dependent policies offer more control but incur additional scoring, search, or rollout costs. Evidence for transfer across model scales and comparable end-to-end cost remains limited. A continuously updated list of papers, along with their public implementations, is available at https://github.com/xuyj233/data_strategy_survey.

---

### No Single Tokenizer Feature Reliably Predicts Downstream Language Model Performance

Authors: Antonio Lopardo, Luis Frentzen Salim, Shikhar Srivastava, Kevin Jiang, Mridul Sharma, Catherine Arnett
Published: 2026-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.21679v1

Tokenization is a critical component of the language modeling pipeline, but it is poorly understood. Tokenizers can impact downstream performance, but there is currently mixed evidence about which tokenizer features predict a better language model without requiring a full training run. In this paper, we analyze approximately 200 language models trained on nine different languages. We evaluate both models and their tokenizers and test whether there is a relationship between any proposed intrinsic tokenizer evaluations and model performance, as measured by a wide variety of benchmarks. Despite the quantity and variety of proposed intrinsic tokenizer metrics, we find that none consistently predicts downstream performance across model families, tasks, and languages. This motivates the need for novel tokenizer evaluation metrics and approaches. We propose novel linguistically grounded metric introduced in this work shows that new metrics can capture aspects of tokenizer quality that existing metrics miss, though their predictive power is likely to vary across model families, languages, and tasks.

---