# Research Papers — 2026-10 · bundle page 114 of 156

> Full-text markdown of papers #5651–5700 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/114
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/113.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/115.md)

### Later Is Better: Token Reduction for ViTs Under Distribution Shift

Authors: Hyeongheon Cha, Hyungjun Yoon, Sung-Ju Lee
Published: 2026-10-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.07758v1

Training-free token reduction accelerates vision transformers by removing redundant tokens across layers, recovering most of the original accuracy at a fraction of the compute. These methods, however, are designed and evaluated primarily on clean data, and under real-world distribution shift their accuracy gap to the uncompressed model widens with the removal rate. We show that this gap is governed by the reduction schedule, the depth profile of removal, usually left fixed as an implementation detail. Concretely, we introduce a one-parameter late-concentrated power-law schedule that consistently improves out-of-distribution accuracy over flat at no extra inference cost. On ImageNet-C with DeiT-S, the late schedule closes 83% of that gap at a 26% compute reduction (+1.17pp), and 99% of it at a lighter 7% reduction (+0.26pp). The gain cannot be attributed to retaining more tokens or using extra compute: held to flat's compute, the late schedule removes more tokens in total and leaves fewer tokens at the end, yet still wins. Single-layer probes point to a mechanism: earlier reductions perturb features that pass through more remaining layers, front-loading reduction error in depth. The effect is broad, holding across five token-reduction methods (ToMe, EViT, ATS, ATC, PiToMe), nine backbones, all ImageNet-C corruption types, eight further shift suites, and two further modalities, video and vision-language QA. It is also specific to shift, still positive on clean and rising monotonically to ~4x that at the highest severity 5. The schedule keeps its gain under six test-time adaptation methods, and needs no per-input or per-domain tuning.

---

### Trustworthy Method Comparison with AI Judges: Estimation and Design under Order, Batch, and Aggregation Effects

Authors: Tianxi Li, Jie Ding
Published: 2026-10-06
Categories: stat.ML, cs.LG, stat.AP, stat.ME
arXiv: https://arxiv.org/abs/2610.07755v1

Large language models (LLMs) are increasingly used as judges for automated AI evaluation. A common practice is to randomize prompt sequences and average the resulting scores, but its statistical validity remains unclear. We show that LLM evaluation mechanisms can be approximated by a class of Markov generalized linear mixed models (GLMMs), supported by out-of-sample predictions across three major commercial LLMs. Using a first-order Markov GLMM, we study leaderboard ranking and group comparison. For leaderboard ranking, randomize-and-average selection is consistent under a mild separation condition, and a Williams square design can improve efficiency when item qualities are close. For group comparison, naive averaging can yield inconsistent conclusions about differences in group-level quality because of the response model's nonlinearity. Empirical results further support the validity of the proposed model-based inference beyond the first-order theory, including settings with higher-order sequence memory. We illustrate the approach in an application where AI judges compare two graphical model estimation methods.

---

### Adversarially Trained Linear Transformers Are Optimal Robust In-Context Learners for Gaussian Mixtures

Authors: Soichiro Kumano
Published: 2026-10-06
Categories: cs.LG, cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2610.07754v1

Adversarial training is one of the most reliable defenses against adversarial attacks, but its high computational cost must generally be paid anew for each task. Robust foundation models offer a promising alternative: adversarially pretrain a model once and then transfer its robustness to downstream tasks through lightweight adaptation. However, a fundamental question remains open: can robustness acquired during pretraining transfer to unseen tasks without further adversarial training? In this study, we answer this question affirmatively. A single model adversarially pretrained at scale can achieve optimal robustness on new tasks without additional task-specific training. Specifically, we show that, for a family of Gaussian-mixture classification tasks, a sufficiently deep linear transformer adversarially trained across tasks can asymptotically attain the robust Bayes error on previously unseen tasks through in-context learning from clean demonstrations. By contrast, a standardly trained model cannot. We further analyze convergence under gradient flow, an accuracy--robustness trade-off, and demonstration complexity.

---

### From Evidence to Action: How Tool-Using Agents Fail

Authors: Hongzhan Lin, Shidong Cao, Ziyang Luo, Wenhao Chai, Mong-Li Lee, Wynne Hsu
Published: 2026-10-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.07753v1

Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their actions were supported by evidence established beforehand. We study where this evidence-to-action chain breaks as agents move from deciding whether to act to executing single actions and dependent workflows. Across ten model-harness configurations, strong static action assessment can coexist with much weaker interactive execution. Failures often begin before execution: agents stop with incomplete investigation or act before required evidence is established. Once required evidence is obtained, single-action execution is usually reliable, while multi-action workflows additionally expose unresolved prerequisites and incomplete execution. For this analysis, we introduce SafeActBench, comprising 656 cases across six operational domains and five protocols that progress from static action judgment and investigated non-action to single- and multi-action workflows. A provenance-bound Evidence Ledger and deterministic trajectory evaluator track what information was established, when actions occurred, and whether downstream dependencies were satisfied. These results show that failures arise not only from missing information, but also from how agents use established evidence when deciding and executing actions.

---

### How Well Do LLMs Reason with Noisy Evidence? An Active Visual Reasoning Benchmark

Authors: Bach Nguyen, Zhaonan Li, Mau Son Nguyen, Sanika Chavan, Nilay Kumar, Hong Anh Nguyen, Khoa Vo, Ben Zhou
Published: 2026-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.07751v1

Real-world reasoning rarely reduces to static question answering: agents must actively gather information from tools and sensors that are often noisy and unreliable. Yet most existing active reasoning benchmarks assume that environmental feedback is trustworthy, or introduce noise without exposing an explicit, calibrated uncertainty signal, leaving open how LLMs should reason when the evidence itself is uncertain. We introduce VisualNoiseQA, a novel benchmark for active reasoning under noisy visual feedback. A text-only LLM must solve VQA problems by iteratively querying a fixed, off-the-shelf VLM treated as a stochastic visual sensor. For each query, we draw multiple samples and expose an empirical uncertainty signal via self-consistency, enabling the reasoner to probe from different angles and decide what to ask next and when to stop. Our construction is automatic and scalable: starting from diverse VQA sources and two noisy VLMs, we retain only questions where the sensor is inconsistent yet human-solvable. We evaluate multiple LLM reasoners on 1,000 instances spanning perception, chart understanding, and knowledge-intensive reasoning. VisualNoiseQA thus provides a controlled playground to study how different LLMs exploit uncertainty signals for robust reasoning.

---

### Cleave: Scaling Tensor Program Optimization via Decoupled Algebraic Search and Operator Scheduling

Authors: David Pissarra, Jinkun Lin, Haitian Jiang, Aurojit Panda, Jinyang Li
Published: 2026-10-06
Categories: cs.PL, cs.AI
arXiv: https://arxiv.org/abs/2610.07742v1

Optimized kernels such as FlashAttention and FlashDecoding are crucial for accelerating today's large models. Most of them are handwritten by experts because existing ML compilers cannot match their efficiency. Producing such kernels requires fusing computations with multiple reductions, which requires both algebraic transformation of the computation graph and operator scheduling of the transformed graph. Unfortunately, searching the two jointly yields a space too large to navigate. We propose Cleave, an ML compiler built on symbolic decoupling: Cleave discovers transformations by performing superoptimization on a graph with symbolic shapes, and then schedules each resulting graph on concrete shapes. Representing shapes as symbols makes equivalence checking cheap and lets a new Split operator, with a symbolic split count, parallelize along a reduction dimension. Cleave's scheduler fuses graphs with multiple reductions through iterative tiling and horizontal fusion. Evaluation on common LLM subgraphs shows that Cleave generates kernels up to 2.8x faster than the best baseline (1.6x on average) and reduces compilation time by 5.9x on average compared to Mirage. For dynamic workloads captured from production serving traces, Cleave compiles each operator once and achieves geometric mean speedups of 1.4x and 1.7x over FlashInfer's handwritten FA2 and FA3 backends. Cleave's code is available at: https://github.com/nyu-systems/cleave

---

### High-dimensional online calibration from harmonic weights

Authors: Maxwell Fishelson, Mehryar Mohri
Published: 2026-10-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.07740v1

We study the online calibration of multidimensional forecasts over an arbitrary convex set $Y\subseteq\mathbb{R}^d$ relative to an arbitrary error norm $\|\cdot\|_{L}$. For forecasting $d$ binary outcomes simultaneously ($Y=(0,1)^d$), we give the first algorithm that achieves $\varepsilon$-calibration in a number of rounds that is polynomial in $d$ for every fixed accuracy. It requires $d^{O(1/\varepsilon)}$ rounds, exponentially improving the dimension dependence of previous bounds. For multi-class forecasting ($Y=Δ_d$), we obtain the same $d^{O(1/\varepsilon)}$ rate, improving the $d^{\widetilde{O}(1/\varepsilon^2)}$ bounds of Peng and Fishelson et al. Our algorithm is simple: on each round, it outputs a harmonically weighted distribution over harmonically smoothed past outcomes. The same algorithm works for every forecast set and norm. More generally, it achieves $\varepsilon$-calibration after $\exp(O(γ(Y,L)/\varepsilon))$ rounds, where $γ(Y,L)$ is a geometric parameter defined by a matrix discrepancy problem. The harmonic weights are motivated by the fact that the discrete Hilbert transform matrix achieves the optimal discrepancy up to a universal constant, simultaneously for every $L$. This optimality result may be of independent interest.

---

### Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence

Authors: Chen Chen, Dongjie Wang, Mei Liu, Zijun Yao
Published: 2026-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.07739v1

Post-discharge risk prediction from electronic health records (EHRs) is difficult because many dependencies that link discharge-time observations to downstream complications, such as comorbidity cascades and drug-disease interactions, are absent from the record. External medical knowledge graphs (KGs) can supply these missing dependencies, but tracing them demands three properties: KG exploration must remain cost-bounded, retrieved evidence must be differentiated by source quality, and the resulting rationale must be citable for retrospective review. Large language models (LLMs) can plan and verify over structured evidence, making them natural candidates for KG reasoning, but existing LLM-based methods do not satisfy these three properties jointly. In this paper, we propose BAR, a Budget-Aware LLM Reasoning framework over medical KGs with three contributions. First, BAR refines the raw KG into disease-specific evidence graphs whose edges carry support scores and provenance records, turning the KG into a quality-annotated reasoning space rather than a static feature source. Second, an LLM then reasons over this graph through a plan-navigate-verify loop that decomposes the question into steps, retrieves evidence under a patient-specific budget, and revises when verification fails. Third, a reasoning policy is trained with a reward that compares predictions with and without acquired evidence, combined with acquisition cost and citation-integrity terms. Across 8 diseases and 3 prediction horizons on MIMIC-III and MIMIC-IV, BAR improves AUPRC by 3.4 points over the strongest baseline, raises citation precision from 59.8% to 77.9%, and consumes only 62-65% of the budget cap.

---

### Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret

Authors: Avishek Ghosh
Published: 2026-10-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.07737v1

We study fair multi-armed bandits under the Nash Social Welfare (NSW) objective, which measures performance via the geometric mean of accumulated rewards. Existing work defines Nash regret as $\mathrm{NR}_T = μ^\star - (\prod_{t=1}^T \mathbb{E}μ_{I_t})^{1/T}$, where $μ_{I_t}$ is the mean reward of the recommended arm $I_t$ and $T$ is the horizon. Since it applies the geometric mean to per-round marginal expectations, it ignores the joint distribution of rewards across rounds, leaving the NSW fairness motivation unaddressed at the trajectory level. We propose \emph{trajectory-wise Nash regret} $\widetilde{\mathrm{NR}}_T = μ^\star - \mathbb{E}((\prod_{t=1}^T μ_{I_t})^{1/T})$, which computes the geometric mean over complete sample paths before taking expectations, capturing NSW fairness more faithfully. By Jensen's inequality, $\widetilde{\mathrm{NR}}_T \geq \mathrm{NR}_T$, making it a strictly stronger metric. We also introduce \emph{high probability Nash regret} $\widehat{\mathrm{NR}}_T = μ^\star - (\prod_t μ_{I_t})^{1/T}$, giving the first high probability regret bounds in fair bandits. Our two-phase algorithm, Round Robin Nash Confidence Bound (\texttt{RR-NCB}), combines round robin exploration with a Nash confidence bound index policy. We show $\widetilde{\mathrm{NR}}_T \leq \widetilde{\mathcal{O}}(\sqrt{k\log T/T})$ and, with probability $1-δ$, $\widehat{\mathrm{NR}}_T \leq \widetilde{\mathcal{O}}(\sqrt{k\log(kT/δ)/T})$, matching the optimal $\widetilde{\mathcal{O}}(\sqrt{k/T})$ rate despite the stronger metrics. Optimality follows from a lower bound via AM-GM and standard $k$-armed bandit minimax arguments. Simulations validate our theory.

---

### Learning to Retrieve via Reinforcement Learning in Embedding Space

Authors: Qi Liu, Fengming Liang, Yiqun Chen, Erhan Zhang, Jiaxin Mao
Published: 2026-10-06
Categories: cs.IR, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.07731v1

Dense retrieval models are typically trained with contrastive objectives that learn effective representations but do not directly optimize retrieval metrics or downstream task performance. To address this problem, we introduce RELER (REinforcement LEarning for Retrieval), a reinforcement learning framework that enables existing embedding models to learn to retrieve directly in embedding space and align to task-specific rewards. We train RELER by sampling unit-length query and document embedding actions from von Mises-Fisher (vMF) distributions centered on normalized encoder outputs, scoring the resulting retrieval or downstream outcomes as rewards, and updating the encoder with REINFORCE using a leave-one-out baseline (RLOO). As exploration in the high-dimensional embedding space is prone to sampling noise, we further propose conditional-mean projection (CMP), which projects each sampled embedding onto the low-dimensional subspace spanned by its encoder output and the candidate embeddings it is compared against, reducing noise in the policy gradient while preserving its expectation. We evaluate RELER on BRIGHT, a benchmark with reasoning-intensive queries that remain challenging for existing embedding models. RELER consistently outperforms InfoNCE and LambdaLoss in average nDCG@10 when post-training BGE-M3 and Qwen3-Embedding backbones. We further evaluate downstream utility through retrieval-augmented generation (RAG), where we adapt only the query encoder while keeping the document index and generator fixed. Across seven QA datasets, jointly optimizing retrieval and answer rewards improves both average retrieval performance and answer quality in RAG.

---

### SanSi: A Looped Typed Decision Model for System 1.5 Thinking

Authors: Shuyu Gan, Young-Jun Lee, Dongyeop Kang
Published: 2026-10-06
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.07730v2

Typed decision models answer a declared question without generating text: a decision head returns a probability for each of the declared options in a single forward pass. A single pass is fast, intuitive System 1 thinking. We study what lies between one pass and generated reasoning: looping, in which the same layers are recursively applied several times before one typed readout. Each loop lets the model revise its hidden state before it commits to an answer, without generating a token; we call this System 1.5 thinking. We propose SanSi, which turns a pre-trained looped language model into a typed decision model. The option probabilities are read after every loop, and every loop is trained with a proper scoring rule, so that one model serves every budget from one loop to eight in a single run. On 10,027 test decisions from 59 sources, SanSi reaches 72.0% accuracy: 13.5 points above a non-looped model of the same shape trained with the same recipe, 5.3 points above a newer non-looped model of its size, and 1.8 points below one with three times the parameters. On two depth-controlled tasks, loops extend the solvable depth beyond the depths seen in training, where the larger single-pass model fails. Used as the judge for policy optimization with reinforcement learning, without gold answers, SanSi raises the share of the generator's correct answers from 37% to 52%.

---

### Foveated Compression: Selective High-Resolution Preservation for Token-Efficient VLMs

Authors: Donghyun Han, Jangho Park, Yuseok Bae
Published: 2026-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.07729v1

Visual tokens are a major source of inference cost in vision-language models, yet simple image downsampling remains a surprisingly strong compression baseline. This raises a complementary question: under a fixed token budget, where should visual fidelity be preserved? We introduce Foveated Compression, which encodes a full-resolution image once and represents it with a mixture of native- and compressed-resolution visual tokens. A behaviorally self-distilled Foveated Merger compresses local visual tokens while preserving compatibility with their native counterparts, and a lightweight Foveated Selector chooses one of nine spatial cells to retain at native resolution using exhaustive budget-matched intervention supervision. At 11.11% visual tokens, uniform Foveated Compression shows no significant paired difference from iso-token downsampling. At 20.99%, the learned selector significantly outperforms random and fixed allocation, but remains below strong whole-image resizing, showing that localized fidelity is not universally preferable. A budget-matched region-choice oracle reaches 82.73 macro accuracy versus 69.61 for the learned selector, revealing substantial headroom within the same spatial action space. Matched probing further shows that signals predicting when compression breaks the answer are substantially more accessible after language-model computation than to the lightweight prefill-free selector. These results expose complementary bottlenecks in region selection and compressed-region fidelity.

---

### Structure-aware Keypoint Localization for Videofluoroscopic Swallowing Study

Authors: Kai Zhou, Chuanshen Chen, Runhao Zeng, Meng Dai, Yifan Yang, Jinwu Hu, Daiyuan Li, Mingkui Tan, Fei Liu
Published: 2026-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.07726v1

Videofluoroscopic Swallowing Study (VFSS) is one of the gold standard for diagnosing swallowing disorders, providing dynamic X-ray imaging of the swallowing process. Automated kinematic analysis in VFSS relies fundamentally on precise anatomical keypoint localization. However, existing studies focus on limited keypoints (e.g., cervical vertebrae or the hyoid) and overlook critical regions such as the soft palate, while annotating only active swallowing segments and ignoring abundant non-swallowing data, resulting in poor data efficiency. Moreover, leveraging this unlabeled data via standard semi-supervised learning is suboptimal, as generic methods are prone to spatial bias. In medical X-rays with fixed layouts, models tend to memorize absolute coordinates rather than understanding anatomical structures. To tackle these challenges, we introduce VFSSKep, a novel dataset that extends annotations to the soft palate and incorporates large-scale unlabeled data. We further propose S$^3$KL, a Structure-aware Semi-Supervised Keypoint Localization framework designed to overcome spatial bias. It integrates a Structure-Aware Learning strategy to extract high-resolution structural cues for structure-aware representation learning, and a Structural Representation Consistency Learning strategy with block shuffling to enforce invariant structural recognition. Experiments show our method achieves state-of-the-art semi-supervised performance, even with unlabeled and 25% labeled data surpassing fully supervised learning with 100% labeled data. Code and data will be made publicly available at: https://github.com/kaai520/S3KL.

---

### PERSIST: Who-What-When Memory Across Sessions for Full-Duplex Spoken Dialogue

Authors: Achira Lin, Siyuan Hou, Wenyi Yu, Xinnian Zhao, Haoyu Niu, Wang Geng, Longshuai Xiao, Shihai Xiao, Mangsuo Zhao, Chao Zhang
Published: 2026-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.07725v1

Modern voice assistants may be shared by multiple users and should be able to answer questions about earlier conversations such as "When did I originally plan to leave?" or adapt their behavior to individual users based on past interactions. This requires more than retrieving a topically similar passage: the assistant must identify the current speaker, recover the relevant past state, and distinguish it from later revisions. We present PERSIST, a persistent memory system for multi-session, multi-speaker spoken dialogue that explicitly models Who, What, and When. PERSIST structures cross-session histories into readable event records and retrieves them with a 3W joint scoring mechanism that combines semantic content, acoustic speaker identity, and temporal state. For real-time full-duplex interaction, PERSIST further reuses intermediate representations from the dialogue backbone, avoiding query-audio re-encoding and reducing retrieval latency from 578.42 ms to 7.03 ms. We also introduce SpokenTrace, a diagnostic benchmark that factorizes evaluation along memory tasks and speaker-query types, exposing failures in recall, speaker attribution, and temporal-state tracking. On SpokenTrace, PERSIST achieves 85.08% end-to-end task accuracy and improves all-support EM@3 from 49.01% with BGE-large to 82.10%.

---

### The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models

Authors: Yibo Zhang, Tianrong Guan, Liang Lin, Puze Wang, Jin Wang, Qingsong Wen
Published: 2026-10-06
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2610.07723v1

Safety alignment in Large Language Models (LLMs) remains vulnerable to backdoor attacks. Existing LLM backdoors are almost all input-centric: activation depends on explicit trigger patterns in the user input, so modern guardrails are built to sanitize the input space. We challenge this assumption with a novel answer-side backdoor for multi-turn dialogue. Instead of inserting the trigger into the input, the adversary uses a benign first-turn prompt to naturally induce the model to generate a specific, seemingly innocuous word. Once merged into the dialogue history, this self-generated word becomes the trigger. When a later harmful query arrives, the model detects its own trigger and bypasses its safety refusal, while the user input stays perfectly clean. Across four LLMs, our attack reaches near-perfect Attack Success Rates, approaching 100\% at only a 5\% poisoning rate, while preserving general utility and clean-input safety, and it evades mainstream input-centric defenses. Representation-level analysis shows that the self-generated trigger consistently suppresses the model's refusal signal, exposing a critical blind spot in current LLM defenses.

---

### Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods

Authors: Haotian Yang, Huikang Jiang, Yucheng Wu, Wen-Jie Jiang, Chenpeng Wang, Yibin Lou, Liangming Pan
Published: 2026-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.07722v1

Activation steering provides a lightweight and flexible way to control large language model (LLM) behavior. However, effective steering requires more than inducing the intended behavior: it should also limit unintended changes and remain robust across inputs and training data. Existing evaluations cover these dimensions only in fragments. As a result, the trade-offs between efficacy and side effects have not been systematically characterized. We introduce SteerScope, a two-axis, multi-dimensional evaluation suite that jointly characterizes steering outcomes and method properties through 15 metrics. We score target efficacy and side effects on language quality, task capabilities, and safety and reliability, and further assess generalization and data dependence through steering-specific metrics for sample efficiency and sample sensitivity. Rather than comparing methods at a single operating point, we characterize the trade-offs between efficacy and side effects. Under matched models, tasks, and evaluation protocols, we benchmark 23 methods spanning 4 families, including prompting, LoRA, and SFT as baseline methods, and release the suite as an extensible codebase. We find that current activation steering methods do not yet surpass the Prompt Steering baseline in their overall balance between steering efficacy and side effects: across both model scales, no evaluated activation steering method achieves higher efficacy without incurring greater composite side effects. We further uncover a consistent coupling between steering efficacy and side effects. Under OOD prompts, target efficacy is often preserved, whereas side effects tend to become more pronounced, particularly through declines in instruction relevance and fluency. Methods also exhibit sharply different sample-efficiency profiles.

---

### Exact Calibration and Sharp Risk Geometry for Volume-Sampled Ridge Regression

Authors: Kihun Rhee
Published: 2026-10-06
Categories: math.ST, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2610.07721v1

We study ridge regression from exactly $s$ distinct rows of a fixed design. Responses are fixed, and only the subset is random. The determinant law and selected ridge fit share one positive definite penalty. Established mean identities and exponential-family duality give the unique penalty that matches a prescribed full-data ridge fit in expectation. It exists exactly when $s$ exceeds the target's effective dimension. Our main result concerns centered covariance risk normalized by full-data penalized loss. For balanced signed coordinate replicas, a strict sector inequality gives the sharp risk and all maximizing responses at every budget from the dimension to one below the row count. This holds for any nonzero positive semidefinite query. With the target and query fixed, the maximizing response space is unchanged across these budgets. For general designs, we characterize attainment of a leave-one-out envelope. For existing real equiangular tight frames, flat row query energy characterizes when every nonzero residual response maximizes at two deletions. At three deletions, we give the sharp risk and complete maximizing space for isotropic queries, using unequal triangle weights. The balanced geometry yields a same-sample unbiased ridge--Horvitz--Thompson mixture with lower sharp risk and an exact mean-share improvement boundary. Under full recalibration after feature changes, we prove quadratic regret from searching the complete old maximizing space and a query-uniform bound on the mixture's risk gain. The strongest sector inequalities have exact computer-assisted proofs.

---

### RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing

Authors: Wanning He, Yuyao Zhang, Yu-Wing Tai
Published: 2026-10-06
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.07720v1

Multi-reference image generation requires preserving the appearance of multiple subjects while composing them into a coherent scene. However, existing diffusion transformers commonly encode references as dense visual token grids and jointly process them with global attention, making conditioning increasingly expensive as the number and resolution of references grow. We present RefRoute, a framework that addresses both reference representation cost and attention overhead through two complementary mechanisms. Compact residual conditioning combines low-resolution latent tokens with lightweight residual features extracted from full-resolution pixels, reducing reference token counts while retaining fine-grained appearance cues. Condition routing and attention routing align reference tokens with their assigned target regions and restrict cross-reference interactions, while allowing selective reference access beyond region boundaries for scene integration. We further introduce RefRoute-Data for training many-reference generation models and ManyRef100, a benchmark spanning human, object, and mixed compositions with 10-17 references. After many-reference fine-tuning, RefRoute achieves an overall Weighted-Ref-VIEScore of 36.06 on ManyRef100, compared with 8.88 for FLUX.2-Klein-9B. Separate inference-cost evaluations show substantially slower latency growth as the reference count increases: at 16 references, our 50-step and 4-step configurations achieve $18.3\times$ and $14.2\times$ speedups over their corresponding FLUX baselines, respectively. These results establish compact reference representations and spatially routed attention as an effective approach to scalable many-reference image generation.

---

### Stability of Measure-to-Measure Transformers on Sub-Gaussian Data

Authors: Frank Cole, Nicholas H. Nelsen, Takashi Furuya
Published: 2026-10-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.07717v1

Transformers have exhibited impressive empirical success across various domains, but their theoretical foundations remain less developed. This work constitutes a mathematical study of the measure-to-measure operators defined by transformers. We show that transformers map sub-Gaussian inputs to sub-Gaussian outputs; this ensures that taking arbitrary-length compositions of the softmax operator is well-defined. We then show that transformers are Hölder continuous with respect to the 1-Wasserstein distance on appropriate spaces of sub-Gaussian inputs. This allows us to establish estimates on the error propagation along a transformer between a sub-Gaussian input and its empirical approximation. We also study a mean-field analog of the cross-attention mechanism, which is an operator from a pair of probability measures to a single probability measure. We show that cross-attention exhibits different Hölder regularity and sample-complexity in its two input arguments. Last, we apply our results to deduce approximation guarantees for measure-to-measure transformers. Together, these results provide a firm stability and finite-sample theory for transformers on sub-Gaussian data.

---

### JevCascade: Readout Stability and Inference-Time Compute Allocation for Prefill-Only Decision Models

Authors: Ran Li, Lei Chen
Published: 2026-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.07716v2

We present JevCascade, an inference-time compute allocation framework for prefill-only decision models, built on readout stability and zero-label restricted readout prediction. Prefill-only decision models score every candidate in a menu in a single forward pass and never decode, which makes one call one to two orders of magnitude cheaper than a same-scale generative language model. We show that this read-out structure carries a testable property. When an intervention changes only the menu and leaves the input text fixed, the post-intervention accuracy is already determined by the cached first-pass distribution. The restriction predictor restricts the pass-1 probabilities to the menu, renormalizes and reads off the argmax, with no labels and no second pass. Across six model families, ten core datasets (sixteen in total) and two task types, menu-only interventions are predicted to within 4.2 points, exactly for one family. The property is ordinal, not probabilistic, since a probability-level variant of the same estimator errs by 21.0 points, and class-specific, since same-scale generative models err by 1.6 to 15.8 points and degrade as they grow. It makes inference-time compute decidable before deployment. Uniform extra passes buy calibration but almost no accuracy; at matched cost a confidence cascade beats every scheme that re-asks the same model, and curating the menu beats enlarging the model, a 0.8B model on a curated 5-candidate menu reaching 95.4% on CLINC150 against 80.0% for a 4B model on the full 150-label menu.

---

### When Old Facts Return: Re-Reads, Reverts, and the Limits of Temporal Memory

Authors: Neeraj Yadav
Published: 2026-10-06
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2610.07715v1

A memory system can retire an obsolete value and later restore it merely because the same old statement appears again. A re-read of an old source and a genuine revert can produce the same observed sequence of values while requiring opposite current answers. We study this ambiguity on 130 extractor-selected atomic transitions derived from software fixes. In the ordinary transition condition, identity-based temporal memory reaches 98.5% model-judged accuracy with zero observed errors under a literal stale-value proxy. Appending a verbatim re-read of the old statement reduces accuracy to 10.8% and raises the stale-value rate to 88.5%. A guard that refuses to reactivate a previously retired value restores accuracy to 97.7% and reduces that rate to 0.8% in this constructed re-read condition. The guard cannot also recognize a legitimate revert without additional change provenance. Two supporting studies examine exposing retired history to the answer model and supplying current source for changed behavior. An exploratory extraction study over 707 software fixes provides scope context, not a universal coverage estimate. The design implication is to distinguish an observation of a value from evidence that the value changed. Selected inputs, aggregate-only answer records, related-family judges and a post-failure guard evaluation limit the conclusions to the retained experiments.

---

### Neuromotor Hierarchy Network: Physiological Inductive Biases for Robust Generalization in sEMG Decoding

Authors: He Wang, Hongyuan Qi, Zhaoxian Zhang, Jinbin Luo, Linyi He, Mehul Motani, Changsheng Wu
Published: 2026-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.07713v3

Surface electromyography (sEMG) provides a wearable, noninvasive interface to neuromuscular activity for movement decoding and human-computer interaction. Population-scale decoding remains difficult because the relationship between sEMG and neuromuscular activity varies across users and sessions, while task-relevant dynamics span channels and multiple timescales. Learning waveform-to-output mappings from task labels leaves the distinction between recording variability and coordinated motor activity implicit. We introduce the Neuromotor Hierarchy Network (NHN), which learns a compact latent neuromotor state from task supervision to represent task-relevant neuromuscular coordination. NHN constructs this latent state through a hierarchy inspired by neuromotor organization. It adapts recording statistics while preserving relative intensity. Its spatiotemporal encoder uses parameter-efficient channel interactions and modulates features with multi-timescale history. The resulting features yield candidate activations of learned motor primitives, which are temporally integrated and continuously weighted to form the state. Theoretical analysis characterizes the efficiency, temporal behavior, and optimization of NHN's core mechanisms. We evaluate the architecture for both continuous hand-pose estimation on emg2pose and touch-typing recognition on emg2qwerty. On emg2pose, NHN reduces user-averaged angular error by 0.52% to 2.84% across all three generalization splits in both Regression and Tracking relative to Hadidi et al.'s best task-specific variants, using 48.42% to 48.51% fewer parameters. On emg2qwerty, NHN reduces beam-search character error rate by 19.40% zero-shot and 30.42% after fine-tuning relative to SplashNet-Upscale, using 65.86% fewer parameters. Physiology-guided inference of a latent neuromotor state supports parameter-efficient sEMG decoding.

---

### Mathematical Invariant-Enabled Topological Neural Networks for Molecular and Materials Property Prediction

Authors: Yiming Ren, Xiang Liu, Mustafa Hajij, Pietro Liò, Guo-Wei Wei
Published: 2026-10-06
Categories: q-bio.BM, cs.LG
arXiv: https://arxiv.org/abs/2610.07712v1

Existing molecular and materials learning approaches often rely on a limited set of structural representations, which may capture only selected aspects of complex three-dimensional structure. Here, we introduce mathematical invariant-enabled topological neural networks (MITNNs), a framework that represents complex structures through multiple complementary mathematical views and integrates them with topological neural architectures. MITNNs combine multiscale invariants from topology, spectral theory, commutative algebra, differential geometry, and discrete curvature, capturing complementary structural information from the same system. Systematic invariant-subset, architecture-subset, and ensemble analyses show that predictive performance depends on how mathematical representations and neural architectures are paired, with selected combinations outperforming individual models and the aggregation of all available components. Across protein-ligand binding, metal-organic framework properties, mutation-induced protein solubility, and molecular toxicity prediction, MITNN consistently outperforms existing methods. These results establish MITNN as a mathematically multimodal framework for scientific machine learning.

---

### Comprehensive Evaluation and Fine-Tuning of Foundational Cell Nuclei Segmentation Models in Renal Pathology

Authors: Ruijie Wu, Junlin Guo, Ruining Deng, Yu Wang, Shilin Zhao, Haichun Yang, Yuankai Huo
Published: 2026-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.07711v1

Accurate nuclei instance segmentation is essential for quantitative renal pathology, yet general-purpose models often struggle with low contrast, dense nuclei, complex morphology, and strong background staining. In this work, we extended a human-in-the-loop framework by combining 5,901 foundation-model-generated pseudo-labels from well-segmented cases (Easy), 860 newly expert-annotated unresolved challenging cases (Medium), and 198 expert-annotated consensus failure cases (Hard). These annotations, spanning different levels of segmentation difficulty, enabled the systematic evaluation of seven single-source and mixed-source fine-tuning strategies across nine cell segmentation model configurations. Fine-tuning improved all models, with Medium data included in seven of the nine best-performing strategies. LSP-DETR achieved the highest F1 score of 0.8725 with Hard-only fine-tuning, while StarDist showed the largest improvement, increasing from 0.7380 to 0.8332 with Medium-only fine-tuning. These findings show that annotations spanning multiple difficulty levels support effective model adaptation, although the optimal annotation composition remains model dependent.

---

### Evidence Before Sampling: Interpretable Implicit Negative Candidate Discovery for Recommendation

Authors: Shreya Rajpal, Sonia Sharma, Swapnil Parekh, Lisa Li, Jeyendran Balakrishnan, Nagaraj Janardhana, Andrew Mattarella-Micke
Published: 2026-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.07708v1

Recommender systems learn from observed user-item interactions, but explicit negative feedback is often unavailable. Since deep learning models require negative signals for training, negative sampling methods typically treat selected unobserved interactions as negatives. However, a missing interaction does not explain why a user is uninterested in an item or whether there is sufficient evidence to label it negative. This is especially important in business recommendation, where negative signals should be interpretable and aligned with business objectives. We formulate implicit negative candidate discovery to identify unobserved interactions supported by observed customer behavior. We encode these patterns as symbolic rules, score them based on support, informativeness, and product relevance, and rank the retained rules by evidence. An LLM then interprets the retained rules using business objectives and domain knowledge; the interpretations are combined with the statistical evidence in the final report. We evaluate our method in an industrial B2B setting and across five public recommendation datasets. Candidate-quality evaluations in the industrial setting and three public datasets show higher precision than the evaluated baselines, while symbolic selection improves downstream test PR-AUC by 12.5% over random selection with four negatives per positive example in the industrial task. Our results show that negative candidate validity can be evaluated separately from downstream recommendation performance. This distinction enables evidence-based, business-aligned, and explainable negative selection, improving both interpretability and model training in sparse, skewed, real-world recommendation settings.

---

### AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory

Authors: Chirag Sharma, Benjamin Fowlersmith, Karime Maamari
Published: 2026-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.07707v1

Conversational AI assistants with long-term memory extract facts from user messages into a store consulted in later conversations. A stated plan can enter that store as fact: a user who might move to Seattle may be recorded as already living there. We call this speculation contamination. Final-state memory benchmarks miss this error because they do not probe intermediate state and include few unresolved speculations. We present AgentMemGate, a write-time gate for profile-store memory that classifies extracted statements as speculation, completed event, correction, or other. Speculations remain outside memory, with conditions governing later promotion or deletion. We also contribute a dataset of multi-session conversations in which plans are confirmed, abandoned, or left unresolved. On our 147-conversation held-out set, Mem0 and Graphiti assert unresolved plans as current state for 35.2% and 27.3% of pending plans. On the core benchmark, AgentMemGate eliminates all observed contamination relative to the identical ungated pipeline (87.5% to zero for the most exposed extraction style) and raises task accuracy from 65% to 95%. On the harder held-out set, gated contamination is 3.4% to 5.7% and task accuracy rises by 9 to 13 percentage points. Our analysis identifies field matching as the main remaining bottleneck: realistic speculations often match no profile field and never reach the gate. We release our datasets, prompts, and evaluation code.

---

### WASD: Wasserstein-based Knowledge Distillation for Large Language Models

Authors: Byeonghu Na, Donghyeok Shin, Yeongmin Kim, Mina Kang, Il-Chul Moon
Published: 2026-10-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.07706v1

Autoregressive large language models (LLMs) have rapidly advanced in capability, but their increasing scale comes with substantial computational and memory costs at inference time. Knowledge distillation (KD) offers a practical solution by transferring knowledge from a large teacher model to a smaller student model via alignment of discrete probability distributions. However, existing KD methods for LLMs primarily rely on divergences that evaluate discrepancies through probability values at each vocabulary index, without explicitly leveraging token-level semantic information. We propose Wasserstein-based knowledge distillation (WASD) for LLMs, which incorporates token-level semantic information via the Wasserstein-based distance with a cost matrix derived from token embeddings. To ensure computational tractability, we adopt the Sinkhorn divergence and derive a gradient-equivalent objective that can be efficiently optimized without introducing additional networks. Experiments across multiple LLM families and scales show that WASD consistently improves distillation performance on diverse tasks, including instruction following, mathematical reasoning, and code generation. Our results highlight the importance of semantic information encoded in the token space for effective distribution alignment in LLM distillation. The implementation is publicly available at https://github.com/aailab-kaist/WASD .

---

### What Frame-Level Labels Can and Cannot Do for Small-UAV Point Detection in Thermal Video

Authors: Wonbin Son, Gyumum Choi, Junil Seo, Hyungjoon Kim
Published: 2026-10-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.07705v1

The growing use of unmanned aerial vehicles (UAVs) has increased the importance of image-based UAV detection. Learning-based detectors are trained on imagery and annotations, with annotation type determining the information available during training. We focus on learning localization from frame-level target presence/absence labels when sensor or scene changes make spatial annotations for additional training burdensome. We analyze the detection capability, learning behavior, and potential applications of an existing architecture for point detection of small UAVs, trained with presence/absence labels and requiring no external detector. The architecture freezes spatial features learned through classification and trains a readout with the same frame labels to produce spatial score maps and point detections. On two thermal infrared datasets, CST Anti-UAV and Anti-UAV410, we evaluate localization hit rates and detection rates under false-alarm constraints, analyze the effects of training stages, label allocation, synthesis, and model configuration, and compare with bounding-box detectors. We also explore potential applications on Airborne Object Tracking (AOT) using its visible-light imagery and frame labels. Classification training strengthened target-related spatial responses, while readout training helped extract them consistently. Distributing similar label counts across more videos yielded higher localization hit rates, while synthesis effects varied by dataset and evaluation criterion. Higher localization hit rates did not always improve detection under false-alarm constraints, and failures remained when target signals were weak relative to background variation and under cross-dataset transfer. These findings provide guidance on label allocation, spatial representations and readouts, synthesis, and false-alarm control.

---

### Independent Multi-Agent Reinforcement Learning with Counterfactual Semantic-Social World Models

Authors: Fernando Martinez, Tao Li, Yingdong Lu, Juntao Chen
Published: 2026-10-06
Categories: cs.MA, cs.LG
arXiv: https://arxiv.org/abs/2610.07704v1

Fully decentralized multi-agent reinforcement learning (MARL), also referred to as independent learning, requires each agent to learn and act using only its local information and experience, without a centralized critic or inter-agent communication. Such a stringent information structure renders the conventional reward signal ambiguous. A poor return may result from an ineffective ego action, an incompatible teammate response, or an effective opponent response, yet scalar rewards alone do not reveal which explanation is responsible. We argue that agents can learn more effectively by prospectively comparing the consequences of candidate actions rather than diagnosing failures only from realized returns. We introduce CASTLE (Counterfactual Action-conditioned Semantic Tokens for Local Execution in Decentralized MARL), an offline-training, online-in-context guidance framework with two complementary world models. A Local Dynamics World Model, offline pre-trained over agents' local trajectories, summarizes the agent's local trajectory dynamics and partial observability, while a Semantic-Social World Model predicts compact short-horizon task and social consequences for each candidate ego action. The latter is trained from counterfactual simulator rollouts that expose plausible teammate and opponent responses to alternative actions taken from the same logged rollout state. During online learning and execution, both world models remain frozen and are queried by agents using only locally available information. Their prediction logits provide in-context guidance to an independent PPO policy. Across 30 matched seeds on Tag, Spread, and Adversary in the benchmark multi-particle environments, our proposed CASTLE achieves the highest mean final score among the evaluated methods, exceeding the strongest baseline on each task by 10.67, 6.46, and 0.33 normalized points, respectively.

---

### On the Boundary of Admission Gates: An Injected-Truth Study of Falsification-First Selection in Quantitative Strategy Research

Authors: Tianlun Zheng
Published: 2026-10-06
Categories: cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2610.07701v1

Strategy research conflates two problems: finding a profitable rule, and establishing that the finding is not search luck. The latter calls for admission gates -- statistical criteria that must be satisfied before a conclusion is adopted -- yet whether gates work, and at what cost, remains untested. We introduce an injected-truth protocol with a random-admission control that adopts at the same rate as the gate; only if the gate beats this control does it carry information rather than merely raise a threshold. Across synthetic and real-calibrated panels, gates eliminate false discoveries in the weak-signal regime but cut adoption to 1--7%, and add nothing when signals are strong. Most importantly, criteria computed on absolute rather than excess returns silently reject every candidate, including true signals. Keywords: multiple testing, backtest overfitting, strategy admission, injected-truth validation, excess returns, false discovery rate

---

### Detecting LLM-Assisted Vietnamese Writing via Keystrokes under Behavioral Manipulation

Authors: Thanh Dong, An Ngo, Minh Dau, Rajesh Kumar
Published: 2026-10-06
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2610.07700v1

We study the robustness of keystroke dynamics for detecting large language model (LLM)-assisted writing. We introduce a Vietnamese keystroke dataset capturing realistic writing modes, including bona fide composition, transcription, and paraphrasing. We also define a behaviorally grounded threat model in which users deliberately alter typing patterns. To implement the threat model, we create behaviorally manipulated variants of the data designed to evade keystroke-based detection. We evaluate four keystroke modeling approaches: temporal and rhythmic representations, and sequential representations modeled with a one-dimensional convolutional neural network (1D-CNN) and TypeNet, under user-independent and context-independent settings. The results show that sequential models outperform feature-based approaches in most cases and that keystroke signals encode discriminative information about the writing process. However, detection is not uniformly robust: transcription is reliably identified, while paraphrasing and adversarially manipulated samples are frequently misclassified as bona fide when not explicitly modeled. To address this, we incorporate adversarial training using behaviorally manipulated data, which substantially improves separability and robustness. These results suggest that keystroke-based detection depends critically on exposure to diverse writing behaviors, and that strong performance under limited conditions does not generalize to realistic or adversarial settings without targeted modeling.

---

### Improving Synthetic Data Generation for Argument Mining via Adversarial Reinforcement Learning

Authors: Zhijun Zhang, Qianlong Wang, Keyang Ding, Genan Dai, Bowen Zhang, Bin Liang, Ruifeng Xu, Yongsheng Liang
Published: 2026-10-06
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2610.07699v1

Argument Mining (AM) is fundamentally constrained by the scarcity of high-quality structure-annotated datasets. While LLMs have shown promise in synthetic data generation, producing synthetic AM data that is both structurally accurate and sufficiently diverse remains a challenging problem. To address this problem, we revisit synthetic data generation for AM from a new perspective and propose a novel adversarial reinforcement learning framework for data synthesis. The proposed framework jointly optimizes the generator and the discriminator in an adversarial loop, in which the generator produces structured AM instances, and the discriminator provides learning signals by distinguishing real data from synthetic candidates. This enables the generator to progressively improve both the structural accuracy of generated argument data while maintaining diversity through adversarial feedback. Extensive experiments demonstrate that the proposed framework consistently improves AM performance on three benchmark datasets in both full-data and low-resource settings, validating its effectiveness and scalability.

---

### RBMatch: Dual-Level Class Rebalancing for Semi-Supervised Building Footprint Extraction

Authors: Akil Ahmad Taki, Shaikh Anowarul Fattah
Published: 2026-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.07698v1

Accurate building footprint extraction from high-resolution remote sensing imagery is essential for urban planning, disaster response, and environmental monitoring. However, obtaining dense pixel-level annotations is costly, motivating the use of semi-supervised learning (SSL) to leverage unlabeled imagery. In remote sensing, severe foreground--background imbalance poses a particular challenge for self-training, as it can bias pseudo-label generation and the resulting unsupervised optimization toward the majority background class. We show that addressing this imbalance at only one stage is insufficient: balancing pseudo-label selection alone does not prevent background bias from re-emerging during unsupervised loss optimization, a failure mode we term \emph{imbalance leak}. To address this issue, we propose \textbf{RBMatch}, a dual-level class-rebalancing framework that jointly regulates pseudo-label generation and unsupervised optimization. RBMatch combines a supervised learning pathway with a self-training module comprising three components: adaptive class-specific thresholding (ACT) for balanced pseudo-label selection, confidence-aware class-balanced reweighting (CACBR) for mitigating class bias in the unsupervised loss, and distribution alignment (DAL) for matching the predicted unlabeled-data distribution to the labeled-data prior. Experiments on the WHU, INRIA, and Massachusetts building footprint datasets across labeled ratios of 1%--10% show that RBMatch consistently achieves the best building IoU and F1-score among the evaluated methods. The improvement is most pronounced on the highly imbalanced Massachusetts dataset, where RBMatch improves IoU by 1.37 points over the strongest baseline at a 1% labeling ratio and is the only method to outperform the fully supervised baseline across all twelve dataset--ratio settings.

---

### Anchor-driven Multi-modal Multi-scale Expert Selection for Survival Prediction

Authors: Tao Zhou, Ying Hu, Huazhu Fu, Yi Zhou, Xiao-Jun Wu, Haibin Ling
Published: 2026-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.07694v1

The integrative analysis of histopathological Whole-Slide Images (WSIs) and transcriptomic profiles holds significant promise for cancer survival prediction. However, existing methods typically project multi-modal features directly into a shared latent space without explicit alignment, leading to the entanglement of mismatched morphological cues and molecular signals. Furthermore, current fusion strategies often treat the extreme spatial heterogeneity of WSIs uniformly, lacking mechanisms to adaptively prioritize clinically relevant tissue scales for individual patients. To address these limitations, we propose an Anchor-driven Multi-modal Multi-scale Expert Selection (AM$^2$ES) framework for survival prediction. Specifically, we present an Anchor-driven Multi-modal Fusion (AMF) module, which introduces learnable semantic anchors as cross-modal mediators to bridge the semantic gap by enforcing a structurally regularized alignment between transcriptomic features and multi-scale pathology representations. Built upon this aligned semantic space, we further design a Hierarchical Mixture-of-Experts (H-MoE) selection module to decouple the hierarchical prognostic selection process. Mimicking the pathologist's diagnostic workflow, H-MoE performs (i) Intra-scale Expert Filtering to discriminatively identify salient tumor regions within each magnification, and (ii) Inter-scale Hierarchy Routing to dynamically weight and select the most informative resolution levels. Extensive experiments on multiple TCGA cancer cohorts demonstrate that our AM$^2$ES achieves state-of-the-art performance while offering fine-grained interpretability by visualizing how specific molecular pathways drive the expert routing decisions across tissue scales. The code will be released at https://github.com/taozh2017/AM2ES.

---

### Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling

Authors: Juntong Li, Lingwei Dang, Haomin Wu, Ziyan Qiu, Qingxin Xiao, Qingyao Wu
Published: 2026-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.07689v1

Vision-Language Models (VLMs) such as CLIP excel in global semantic alignment but often lack fine-grained perceptual capabilities. This hinders dense prediction tasks and bottlenecks the visual potential of Multimodal Large Language Models (MLLMs). Existing research has attempted to enhance CLIP's visual representations by incorporating geometric priors from vision-centric models. However, these strategies often struggle to achieve deep alignment for both local spatial structures and global semantics, potentially even distorting the original image-text space. To address these limitations, we propose SALM, an unsupervised embedding alignment framework based on structurally-aware latent mask modeling. SALM effectively synergizes local and global alignment via a dual-path design combining explicit and implicit mechanisms, without requiring any image-text pairs. First, we introduce a dual-matrix alignment strategy that explicitly calibrates intra-sample spatial correlations and activation intensities, thereby effectively injecting local geometric priors. Based on this, we further design a latent mask modeling mechanism to guide CLIP to restore the missing semantic details of the target model, thereby implicitly aggregating fine-grained structures into the global semantic space. Furthermore, driven by the empirical observations that CLIP's shallow features inherently possess strong spatial observational capabilities, we naturally extend SALM to a highly efficient self-distillation paradigm, SALM-Self. This unlocks CLIP's intrinsic fine-grained potential without relying on any external models. Extensive experiments demonstrate that SALM not only significantly improves performance in dense prediction tasks but also boosts CLIP's zero-shot accuracy, effectively enhancing the fine-grained understanding capabilities of MLLMs. Project page at https://qzfm.github.io/salm_project_page/.

---

### BluffJAX: Adversarial Imperfect Information Games in JAX

Authors: Aryaman Reddi, Jan Peters, Carlo D'Eramo
Published: 2026-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.07686v1

We introduce BluffJAX: an open-source suite of adversarial imperfect information games in JAX. We provide canonical implementations of games designed for high simulation throughputs and parallelization on GPU accelerators. Our suite consists of well-studied benchmarks such as Texas Hold'Em Poker and Kuhn Poker, as well as games that have not been previously studied in reinforcement learning research, such as Bluff, Stud Poker, and Kemps. We hope that implementing a variety of game mechanics and difficulties will introduce new challenges and foster novel research directions in game-theoretic methods for RL. We benchmark the throughput performance and memory usage of our environments in single and multi-GPU settings, demonstrating scaling of up to hundreds of millions of samples per second, and motivating the usage of BluffJAX over related GPU and CPU-based libraries. We benchmark reinforcement learning, tree search, and game-solving algorithms in JAX in order to provide users with baseline results and facilitate future comparisons.

---

### Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation

Authors: Haipeng Liu, Yang Wang, Meng Wang
Published: 2026-10-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.07684v1

Personalized image generation aims to synthesize text-driven images conditioned on reference images, while mainly casting the generation as image customization for foreground and style transfer for background. Previous arts of diffusion models suffers from the text misalignment with background for image customization and foreground for style transfer during the denoising process. Such facts, as we observed, rooted from the entanglement among hybrid frequency bands during the denoising process. To address such salient limitation, in this paper, we study personalized generation based on dual references - customization and color and style reference - and propose a paradigm to disentangle these Dual image references within Frequency-aware Diffusion Models, dubbed Dual-FDM, to simultaneously tackle two crucial personalized image generation tasks: customization style transfer and color style transfer, by disentangling different frequency bands via mask strategy within frequency domain. For customization style transfer, we replace the mid-frequency band of the background in the style reference with that from the foreground of the customized reference. For color style transfer, we substitute the low-frequency band of the background in the style reference with that from both the foreground and background of the color reference. Both the substituted frequency bands are used as the key and value to reconstruct the query foreground and background of the denoised personalized image.Extensive experiments validate the superiority of Dual-FDM over the state-of-the-art diffusion models for personalized image generation. Our code can be accessed from https://github.com/htyjers/Dual-FDM.

---

### EigenDEXplore: Structured Exploration for Dexterous Manipulation with Human Priors

Authors: Harsh Gupta, Tyler Ga Wei Lum, Changhao Wang, Chuer Pan, C. Karen Liu, Jeannette Bohg, Shuran Song
Published: 2026-10-06
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2610.07681v2

Dexterous manipulation poses a challenging high-dimensional optimization problem, as useful behaviors require coordinated motion across many hand joints. In reinforcement learning (RL) and sampling-based trajectory optimization, exploration commonly relies on independent robot joint perturbations, making coordinated behaviors difficult to discover. Prior work reduces this search space for grasp learning using low-dimensional spaces of coordinated joint motions learned from human hand data, but this restricts the expressivity required for general manipulation. Some combine learned and joint-space actions to restore expressivity, but this increases dimensionality and introduces redundancy. We study these effects across diverse manipulation settings, varying action dimensionality, exploration strategy, and the source of human data. Our experiments suggest that human-motion priors are most effective when used to structure exploration rather than change the action representation. Motivated by this finding, we propose EigenDEXplore, which induces correlated exploration by adding perturbations along human-derived eigenvectors to independent joint-space noise, leaving the action space unchanged. Across multiple dexterous hands, EigenDEXplore consistently outperforms joint-space and learned action-space baselines in grasping, in-hand reorientation, and contact-rich manipulation. These gains span unstructured and reference-guided RL, trajectory optimization, and sim-to-real deployment, and are largest in settings with less reward shaping and curriculum design.

---

### Adaptive Model Inversion Attacks Generalize a Privacy-Robustness Tradeoff

Authors: Shailen Smith, Rasmus Torp, Adam Breuer
Published: 2026-10-06
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2610.07677v1

In this paper, we show that standard evaluations of high-resolution Model Inversion Attacks (MIAs) significantly underestimate training-data privacy leakage. State-of-the-art privacy defenses, standard training techniques such as MixUp and Adversarial Training, and undefended models all leak training images at rates 1.16 to 6.59 times higher on FaceScrub under simple adaptive changes to the attack, with the largest increases among defenses reporting the strongest privacy. We further show that measured leakage depends on the feature basis of the external classifier used to evaluate reconstructions: for the same reconstructed images, an adversarially trained Inception evaluator identifies the targeted identity at different rates than the standard Inception evaluator. Our results suggest that standard MIA evaluation can mistake optimization and measurement failures for privacy. These underestimated leakage rates also concealed a broader relationship between privacy and adversarial robustness. Once we adapt the attack and vary the evaluator, reconstruction leakage closely tracks adversarial robustness across recent defenses and standard training regimes, suggesting that robustness provides an attack-agnostic proxy for reconstruction vulnerability that applies far more broadly than previously theorized. This raises an open question: can a practical defense reduce training-data reconstruction without paying a corresponding cost in adversarial robustness?

---

### Exact-Solution Volume and Length Generalization in Transformers

Authors: Yijia Jessica Zhu, David Chiang
Published: 2026-10-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.07676v1

Research on transformer expressivity shows whether a transformer is capable of solving a given task, but gives little indication of whether the solution, if learned, is generalizable to longer input lengths. We study this question through normalized exact-solution volume (NESV): the fraction of a bounded parameter region that achieves an exact solution on every input of length $n$. For fixed-width, single-layer transformers with $\log n$-scaled attention, we establish asymptotic bounds on NESV for four tasks: FIRST ($Θ(1)$), MAJORITY ($Θ(1/(n\log n))$), INDEX ($Θ(1/n^3)$), and PARITY ($0$). These results are consistent with previous empirical results: the faster the exact-solution volume decays with input length, the harder it is to length-generalize on that task. Looking deeper into INDEX, our volume analysis reveals two error sources that grow with $n$. Consequently, we study a transformer model that would structurally eliminate one of the terms, theoretically improving the NESV bound to $Θ(n^{-1})$, and empirically achieving 85% accuracy when tested at $10\times$ the training length, compared with the 60% accuracy of the original model. We conclude that volume analysis may be a useful approach to identify concrete sources of length sensitivity and thus provide insights into task-specific model refinements.

---

### EIO-Agents: The Missing Semantic Layer for AI Agent Evaluation

Authors: Fouad Bousetouane
Published: 2026-10-06
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2610.07675v1

AI agents are entering production in increasingly consequential environments without a shared semantic standard for what their evaluations actually mean. Scores, traces, judge outputs, and multi juror findings are increasingly used to justify readiness and release decisions, yet they often do not specify what evidence supports a claim, what that evidence can establish, or how the claim leads to a decision. We introduce EIO-Agents, an open specification for interoperable AI agent evaluation built on two layers. The Evaluation Intelligence Ontology (EIO) provides the semantic layer through typed evidence, versioned behavioral predicates, evidence contracts, claims, witness rules, proof status, recurrence, and computable derivations for metrics, findings, controls, and PASS, REVIEW, or BLOCK decisions. The Portable Evaluation Record (PER) provides the system of record: a canonical, content addressed representation of one evaluation that preserves the evidence to decision chain and can be re derived, explained, and verified. Scores summarize, juries interpret, and traces record, but none of them define what the evidence means or what it can prove. EIO provides that missing semantic contract, while PER preserves the resulting evaluation as a portable and verifiable system of record. As AI agents assume greater operational responsibility, evaluation must become more than a collection of scores and verdicts; it must become an accountable artifact whose meaning, evidence, limitations, and decisions can be independently checked.

---

### Evaluating human-AI workflows for field research in viticulture

Authors: Niko Carvajal Janke, Daoyuan Jin, Shivranjani Baruah, Nicholas Gunner, Jacob Maus, Yu Jiang, Kaitlin M. Gold
Published: 2026-10-06
Categories: cs.HC, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2610.07669v1

We assessed the value of two live human-AI interactions in a precision disease control project in California vineyards. The project tested whether 2021-2024 commercial scouting records and remote-sensing measurements across 140 hectares could support 2025 red-leaf symptom forecasting for prioritized scouting and virus testing. In Workflow 1, Aleks v1, a multi-agent research system, developed forecasting models with iterative human refinement. We applied Aleks's 2024 vine-scale model to updated 2025 predictors and evaluated red-leaf forecasts against independent 2025 scouting. In retrospective simulations surveying 45% of all vine positions, adding model-informed row prioritization to adaptive scouting increased the encountered proportion of newly recorded red-leaf observations from 85.8% to 94.1%. Within-block scouting comparisons suggested the model mainly improved scouting allocation among blocks. Despite unreliable internal 2024 performance estimates from synthetic oversampling before train/test splitting, Aleks developed an informative vine-scale model in 145 minutes, increasing throughput and answering our research questions. In Workflow 2, we assessed whether higher model-score vines had more frequent virus detection, and whether Aleks could infer this sampling goal from a general prompt with data and literature. Aleks's plan prioritized balanced vineyard and model score coverage, while our plan prioritized field efficiency and high-model-score oversampling. Aleks's and our plans yielded 41/50 (82%) and 97/100 (97%) sampled vines. Aleks's plan omitted instructions for replacing missing vines, limiting implementation and operational value. Five of 137 sampled vines tested positive for grapevine red blotch virus (model score ROC AUC 0.735). These findings support assessing AI interactions by how well they advance field research objectives under live, project-specific constraints.

---

### CACHEFORGE: LLM-Guided End-to-End Generative Cache Replacement Policy for Performance and Hardware Efficiency

Authors: Kaushal Mhapsekar, Bita Aslrousta, Brijesh Kumar Bhayana, Paula Contreras, Azam Ghanbari, Ethan Goodman, Anna Andriiko, Samira Mirbagher Ajorpaz
Published: 2026-10-06
Categories: cs.AR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.07668v1

Modern cache replacement designs saturate because they operate within fixed representational structures, hand-crafted and heuristic based feature-engineered predictors, or offline imitation models that cannot generate new decision logic on their own. At the same time, replacement is shaped by the causal interaction of prefetching, thrashing, spatial locality, and access-type behavior, producing an enormous design space that is difficult to traverse manually. Prior approaches typically rely on heuristics, parameter tuning, or imitation of an offline optimal policy, capturing correlations rather than synthesizing new mechanisms. As a result, their performance gains often plateau and they overfit under dynamic workload conditions. CACHEFORGE is the first framework to evolve cache-replacement policies end-to-end by embedding a large language model inside a governed hardware-aware loop. In each iteration, the LLM proposes new C++ replacement logic, the policy is evaluated under a trace-based CRC-2 ChampSim simulator, and the framework enforces feasibility through reward shaping, structural checks, dynamic mutation, temperature scheduling, and cross-policy crossover. This closed-loop generation-evolution loop specifically designed for cache replacement policy enables the discovery of compact policies that satisfy hardware constraints while exploring algorithmic transformations beyond fixed predictor structures. Across SPEC CPU2006, CACHEFORGE outperforms all CRC-2 baselines. It improves the total hit rate by 27.36%, 19.69%, 13.72%, 13.15%, 11.83%, and 5.73% over MPPPB, ReD, Hawk-eye, SHiP++, LIME, and LRU, respectively. On memory-intensive workloads, it increases IPC by 10.15%, 7.89%, 6.34%, 3.64%, 3.12%, and 2.71% over LRU, MPPPB, LIME, ReD, SHiP++, and Hawkeye.

---

### SENSE: State-aware Emotion Navigation Storytelling Engine

Authors: Yi Xia, Pablo Carrasco Velo, Mudit Paliwal, Ibrahim Khan, Yifan Geng, Mustafa Can Gursesli, Juho Hamari, Ruck Thawonmas
Published: 2026-10-06
Categories: cs.HC, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2610.07666v1

This paper presents SENSE, a state-aware framework for generating playable branching visual novels with multi-track emotional navigation. Integrating a state-based narrative architecture called MIND, a structure analyzer, and a path-aware context management module, SENSE produces narratives that are both structurally coherent and emotionally rich. From minimal high-level inputs, it generates multiple intersecting routes while preserving character consistency and narrative causality. Evaluations using LLM judges, affective metrics, and visual assessments indicate SENSE outperforms baselines in narrative diversity and robust asset integration, while preliminary human trials show directional improvements in emotional fidelity alongside comparable enjoyment.

---

### Joint Workflow and Prompt Optimization for User Behavior Simulation

Authors: Nipun B Nair, Tongtong Wu, Hongzhi Yin, Hui Li, Weiqing Wang
Published: 2026-10-06
Categories: cs.MA, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.07663v1

User behavior simulation is the computational modeling of user interactions within information systems through the use of simulated agents in place of live users. It supports system testing and evaluation, decision-making and forecasting, and user experience design. Existing simulators rely on hand-crafted rules or domain expertise that transfers poorly across tasks. SWORD (Simulation-driven Workflow and Prompt Optimization with Role-based Design) is introduced as a framework that jointly optimizes multi-agent workflow topology and natural-language prompts. It is guided solely by a scalar task metric, without domain initialization or task-specific engineering. The experimental results demonstrate that SWORD achieves statistically significant gains over prompt-only, workflow-only, and staged-optimization baselines under a controlled, identical-backbone comparison. Against the strongest published domain-specific baseline, SWORD further improves accuracy while using a smaller backbone model, substantially less training data, and a very reasonable API cost (\$4--\$6 for each dataset). Beyond predictive performance, SWORD autonomously discovers domain-relevant signals, review-sentiment mapping rules and epidemiological decay priors, purely from scalar error feedback, establishing textual gradients as a mechanism for unsupervised feature-importance discovery in user behavior modeling.

---

### MS-ECG-FM: Towards a More Universal Electrocardiogram Foundation Model for Health Monitoring using Multi-source Contrastive Learning

Authors: Robert A. Lewis, I-Min Chiu, Kyle Verrier, Karthik Jayaraman Raghuram, Francoise Marvel, Salar Abbaspourazad, Anshuman Mishra, Guillermo Sapiro, Andrew C. Miller, Joseph Futoma
Published: 2026-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.07662v1

Electrocardiography (ECG) records the electrical activity of the heart, aiding diagnosis by detecting abnormalities in cardiac function. ECG foundation models have demonstrated promising results, but are limited by a reliance on ECG interpretation reports as their sole supervision. Because interpretation reports only capture the subset of waveform information routinely recognized by clinicians, this constrains representation learning to overlook the broader diagnostic signals present in ECG. We introduce a new ECG foundation model --- MS-ECG-FM --- that is trained through contrastive alignment to multiple distinct clinical note types, including ECG, echocardiography, radiology, and discharge reports. We evaluate MS-ECG-FM on an extended set of ECG detection benchmarks, showing that it comprehensively outperforms existing methods on the full span of conditions that ECG can detect, including in reduced-lead configurations. Different reports improve representations for different diagnostic domains, while multi-source alignment captures their complementary information and produces consistently strong representations across clinically diverse tasks.

---

### Massive Activation Gating Channel in Large Language Models

Authors: Minjia Mao, Shi Chen, Bowen Yin, Xiao Fang
Published: 2026-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.07661v1

Massive activations, a phenomenon in which a small number of hidden channels exhibit exceptionally large magnitudes, are pervasive in large language models (LLMs). However, the mechanism by which a token develops massive activations as it propagates through a pretrained LLM remains poorly understood. In this paper, we find that the emergence of massive activations is controlled by a single channel in the input embedding to a spike feed-forward network (FFN). The position of this channel is fixed for a particular LLM. We name this channel the massive activation gating channel (MAGC). When the value of the MAGC is sufficiently large (or small, depending on the LLM), the output of the spike FFN exhibits massive activations. Examining six LLMs across four model families and different model sizes, we verify the existence and effect of MAGC. We further provide a theoretical explanation of the mechanism by which MAGC induces massive activations. When the value of MAGC is sufficiently large (or small), the output of a spike FFN asymptotically reduces to a quadratic form that mixes a few columns of the down-projection matrix of the FFN. Since these columns exhibit the shape of massive activations, the output therefore exhibits massive activations.

---

### DLoop: Looped Speculative Decoding

Authors: Geonmo Gu, Byeongho Heo, HeeJae Jun, Yoohoon Kang, Sangmin Lee, Sangdoo Yun, Dongyoon Han
Published: 2026-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.07659v1

Speculative decoding accelerates autoregressive generation in large language models. In each drafting stage, a lightweight draft model proposes tokens that the target model subsequently verifies. With increasingly capable draft models, we find that the target model frequently accepts all tokens produced in a drafting stage. A verification nevertheless follows each drafting stage, resulting in unnecessary target-model forward passes even when drafting could have continued. Adaptive draft length methods decide during decoding how many draft tokens precede a verification, but they raise the speedup only for autoregressive draft models. For a parallel draft model, drafting further requires target-model hidden states for draft tokens that have not been verified. We propose DLoop, a looped form of speculative decoding that adaptively performs multiple drafting stages before verification. DLoop continues drafting while the draft model remains confident and verifies all accumulated draft tokens together. Loop-aware training keeps the draft model reliable in the additional drafting stages by exposing it to its own hidden states for unverified draft tokens. By spending additional draft-model forward passes, DLoop reduces the number of target-model forward passes required for verification. Across diverse speculative decoding methods including EAGLE-3, DFlash, Domino, DSpark, and multi-token prediction modules, DLoop improves the wall-clock speedup by 5 to 41 percent while preserving lossless decoding. Code will be available at https://github.com/naver-ai/DLoop.

---

### Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security

Authors: Shaswata Mitra, Raj Patel, Subash Neupane, Sudip Mittal, Md Rayhanur Rahman, Shahram Rahimi
Published: 2026-10-06
Categories: cs.AI, cs.CL, cs.CR, cs.MA
arXiv: https://arxiv.org/abs/2610.07657v2

LLM-based multi-agent systems (MAS) engage tools, share memory, and delegate tasks, often encountering adversarial content. Current defenses for MAS are typically evaluated in isolation, focusing on one attack type at a time, which can lead to costly and hard-to-audit outcomes. This study organizes defenses into five principles, implementing them as DEFER1 (DEterministic-First Enforcement with Residual judgment), which includes a cascade of 28 checks that blocks what it can and refers the rest to a panel of four judges. In independent testing across four domains, attack success rates drop from about 30.0% to approximately 3.0%, with 78% of blocked attacks handled by deterministic checks. Only a quarter of proposals reach the judges in the security-operations domain, illustrating that the rules provide security for attacks violating clear policies, while judges manage those that only misrepresent intent. Both systems have weaknesses, such as a risk-score approval gate that inaccurately approves most attack proposals but few legitimate ones, highlighting the challenges in assessing threats accurately.

---

### Uniform Discrete Diffusion Models are Minimax Optimal for Estimating Distributions with Small Effective Support Size

Authors: Dongsun Yoon, Saptarshi Chakraborty
Published: 2026-10-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.07655v1

Discrete diffusion models have emerged as a practically successful framework for generative modeling on discrete product spaces, yet their statistical generalization properties remain poorly understood. Discrete real-world data such as text or biological sequences often concentrate on a small fraction of the astronomically large ambient space because of semantic or physical constraints, but existing bounds fail to capture this distributional structure and instead scale with the size of the ambient space, giving rise to almost vacuous error bounds. We address this gap for uniform discrete diffusion, one of the two dominant discrete diffusion paradigms alongside masking diffusion, by deriving statistical guarantees governed by the effective support size $s_n(P_0)$, a sample-size-dependent measure of distributional complexity. Given $n$ independent and identically distributed (i.i.d.) samples from an unknown data distribution $P_0$ on $(K)^d$, we show that, with appropriate choices of network size and hyperparameters, the expected total variation (TV) loss scales as $O(\sqrt{s_n(P_0)/n})$, while the expected Kullback--Leibler (KL) divergence is bounded by $O(\frac{1}{n}s_n(P_0)\log(eK^d/s_n(P_0))\log n)$. Furthermore, we show that the TV rate is minimax optimal and that the KL rate is minimax optimal up to a factor of $\log n$. Together, these upper and lower bounds show that uniform discrete diffusion successfully avoids the curse of dimensionality for distributions with small effective support size: the TV error rate depends on the ambient state-space size only through $s_n(P_0)$, while the corresponding KL rate incurs only an additional logarithmic dependence on the ambient state-space size.

---