# Research Papers — 2026-09 · bundle page 200 of 266

> Full-text markdown of papers #9951–10000 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-09/page/200
[← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/199.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-09/page/201.md)

### One Loop, Two Gains: Can Active Learning win the Lottery for Free?

Authors: Benedikt Tscheschner, Eduardo Veas, Marc Masana
Published: 2026-09-09
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2609.10311v1

The lottery ticket hypothesis posits the existence of winning tickets: sparse subnetworks that, when trained in isolation from their original initialization, match the accuracy of the full dense network. The predominant method for discovering such tickets, iterative magnitude pruning, alternates pruning with full retraining from scratch until convergence over many cycles. Similarly, deep active learning also retrains a model from scratch after each acquisition round as new labels become available. Despite this shared reliance on iterative retraining with a substantial computational overhead, the two paradigms have been studied separately. We observe that the iterative training loop inherent to pool-based active learning already provides the exact computational structure that iterative magnitude pruning exploits, and propose Improve & Prune (I&P), a method that integrates magnitude pruning into each active learning retraining cycle at practically no additional cost. This raises a key empirical question: can iterative magnitude pruning produce winning tickets under the non-stationary data regime of active learning? We investigate this question across multiple acquisition functions, architecture families, and image classification datasets, including an active fine-tuning scenario. Our results demonstrate that I&P yields sparse, deployable models at each active learning iteration. Those match the accuracy of their dense counterparts at sparsities up to 95%, effectively obtaining winning tickets as a byproduct of the active learning pipeline. These per-iteration sparse models can address two computational bottlenecks - per-round model retraining and acquisition scoring over the unlabeled pool - that currently prevent the practical adoption of DAL on large architectures and large unlabeled pools.

---

### View-Structured Conformal Prediction for 3D Gaussian Splatting

Authors: Junzheng Chu, Bin Pan, Zhenwei Shi
Published: 2026-09-09
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2609.10307v1

3D Gaussian Splatting (3DGS) renders novel views in real time, but an uncertainty heatmap does not certify that a rendered view meets a certain prediction coverage. We treat novel-view synthesis as structured regression and ask that, with probability at least $1-α$, RGB prediction boxes cover at least a $1-β$ fraction of pixels in a new view. We propose View-Structured Conformal Prediction (VSCP). It splits the pre-calibration scale into a spatial shape from the renderer and a transferable view-difficulty factor, which predicts the smallest view-wise multiplier that shape needs. A held-out quantile over views (View-CP) then gives finite-sample validity even when transferring to new scenes. The same factorization makes the analysis exact: a conformity score is the ratio of oracle to predicted view difficulty, and excess width separates into a test-side and a calibration-side term. Across 13 real scenes, pixel-pooled calibration reaches 89.9\% marginal pixel coverage but only 61.4\% view-event coverage at a 90\% target, while View-CP reaches 91.7--92.0\%. At matched coverage VSCP cuts width by 22.1\% against a constant scale, and matches a ten-model ensemble's 21.0\% reduction using only one model per scene and four rather than ten rasterization passes per query. VSCP also improves on the closest single-model baseline, the 3DGS-U field, by 4.7 points ($p=0.0225$). The view predictor transfers from bounded source families to all nine unbounded Mip-NeRF~360 scenes. There the full scale beats the constant scale with 20.7\% width saving on all nine scenes. It also keeps an 18.3\% saving under a different densification backbone and runs at 216--280 FPS on an RTX~4090.

---

### RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding

Authors: Fang Li
Published: 2026-09-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2609.10305v1

Language models under one million parameters matter for edge deployment, domain adaptation, and reproducible research, yet a two-layer LSTM or Transformer at embedding width d = 128 still spends roughly one third of its capacity on the output matrix W_out in R^(d x |V|). We propose Riemannian Language Models (RiLM), which remove that layer entirely: context unfolds as a trajectory on a Riemannian manifold, and next-token probabilities arise from squared geodesic distance between the current state and vocabulary embeddings. The same embedding map serves input and output -- decoding is geometry. We instantiate the framework on flat R^d (Flat RiLM) and the Poincare ball H^d (HypRiLM) with a shared MLP composition map phi (~290k parameters, d = 128, |V| = 2000). Across five seeds on WikiText-2, HypRiLM reaches 54.2 +/- 0.2 validation perplexity versus 87.6 +/- 0.6 for Flat RiLM; tied and matched LSTM, Transformer, and SSM controls remain at 113-147 PPL on WT-2 -- HypRiLM leads by roughly 2x over the strongest tied recurrent baseline (SSM, 113.0 +/- 3.8). Penn Treebank and a 10k-vocabulary stress test confirm that geodesic decoding transfers across corpora and larger |V|, while hyperbolic curvature helps selectively. We also characterize boundary collapse in naive hyperbolic recurrence and show how Mobius stabilization restores trainability. Claims are scoped to controlled small-model comparisons, not full-vocabulary state of the art.

---

### SynThermFace: Amplifying Limited Paired Data for Visible-Thermal Face Recognition via Synthetic Data Generation

Authors: Anjith George, Adam Unal, Sebastien Marcel
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.10303v1

Face recognition (FR) is a widely used modality for biometric authentication, but conventional models rely on visible-spectrum imagery and degrade when high-quality RGB images cannot be captured. Cross-spectral face recognition addresses this limitation by matching visible images with other modalities such as thermal imagery, enabling more reliable performance in low-light, nighttime, and unconstrained conditions. However, progress is limited by the scarcity of paired visible-thermal data, which is difficult and costly to collect at scale. We propose SynThermFace, a framework that amplifies limited real visible-thermal supervision into larger paired adaptation datasets for cross-spectral face recognition. A diffusion model is first adapted using a limited set of paired visible--thermal images and then used to generate large-scale paired visible--synthetic thermal data from existing real or synthetic visible face datasets. The generated pairs are used to adapt a pretrained visible-spectrum face recognition model into a CFR model. Unlike synthesis-based approaches that require image translation at test time, the proposed method shifts generation to the training stage and performs inference with a single forward pass through the adapted recognition model. Under the same MCXFace real-pair protocol, PACT improves over the evaluated CFR adaptation baselines, isolating the effect of the proposed adaptation objective. Training PACT on larger generated paired datasets provides additional improvements over both the unadapted model and the real-pair PACT configuration. Cross-database evaluation on the Tufts dataset provides evidence that the learned representation transfers to an unseen database. The source code and trained models will be made publicly available.

---

### A Dominant Diffuse Phase in the Sparse Autoencoder Phase Diagram

Authors: Alexis D. Plascencia
Published: 2026-09-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.10299v1

Sparse autoencoders (SAEs) are increasingly used to recover interpretable features from neural-network activations, yet systematic feature co-occurrence can cause distinct features to be absorbed or merged. The MAIS-O43 open problem proposes a controlled experiment to characterize when recovery of a true synthetic dictionary gives way to feature merging as the nesting fraction $γ$, sparsity penalty $λ$, and dictionary size $M$ vary. We implement the specified protocol and evaluate 200 independently initialized fits across ten of the 165 grid cells. We observe zero full-dictionary recoveries and zero merges. Instead, every run converges to a reproducible diffuse phase: reconstruction is nearly perfect, but learned atoms typically remain far from the true features (median best cosine 0.5-0.7 against a 0.95 recovery criterion) and learned codes are an order of magnitude denser than the ground truth. This behavior persists under robustness checks and across the full 165-cell grid using standard minibatch Adam (3,300 additional fits). Since the global optimum of the exact sparse-coding objective is known to merge nested features in the two-feature case, these results suggest that trained SAEs need not reach the corresponding minima, and that the phase diagram of trained models may differ fundamentally from that of objective minimizers.

---

### Learning Intrusion Response Strategies for OT Systems

Authors: Duc Huy Le, Rolf Stadler
Published: 2026-09-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2609.10298v1

Cyberattacks against Operational Technology (OT) systems, which monitor and control industrial processes, pose an increasing threat to essential societal services. For this reason, developing automated intrusion response strategies is highly important. In this paper, we present a formal model of an OT intrusion response use case using the POMDP framework. It includes a realistic model of partial observability that is based on traffic measurements. This approach allows us to develop tractable, learning-based solution methods for automated intrusion response, which are based on PPO. We evaluate the obtained response strategies on an emulated OT system and find that they are effective against several types of MITRE attacks for the studied use case.

---

### TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents

Authors: Yuhao Wang, Mu Qiao, Xindong Zhang, Yunzhi Zhuge, Lei Zhang, Huchuan Lu
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.10297v1

GUI agents accumulate high-resolution screenshots as the trajectory unfolds, increasing inference latency and memory usage. Training-free visual token pruning can reduce this cost, but cache reuse introduces a fundamental constraint. Once tokens are discarded, the corresponding visual evidence cannot be recovered without re-encoding. Pruning therefore becomes an \textit{irreversible admission decision} that must remain useful for unknown future targets while preserving coverage of operable regions under tight budgets. To address these challenges, we propose \textbf{\method{}}, a training-free framework for \emph{\textbf{T}rajectory-\textbf{r}obust \textbf{A}dmission and \textbf{C}overage-aware \textbf{E}vidence ordering}. Specifically, we combine a query-independent layout-derived interaction prior with instruction relevance and feature novelty to rank visual evidence according to both potential future utility and diversity. Then, we reserve part of the budget for native visual tokens distributed across the screen, repairing missing spatial coverage without breaking the ordering. Together, these mechanisms produce a nested token order, allowing retained visual evidence to shrink monotonically across budgets while remaining reusable throughout the trajectory. Finally, our monotone KV contraction incrementally contracts retired frames into compact session state, avoiding repeated visual encoding or pruning. Extensive experiments across six GUI benchmarks and diverse models verify the effectiveness of our proposed \method{} under tight budgets. The source code will be released.

---

### The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding

Authors: Gilad D. Landau, Dulhan Jayalath, Oiwi Parker Jones
Published: 2026-09-09
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2609.10296v1

Non-invasive speech decoding remains constrained by the low signal-to-noise ratio of neural recordings, which makes fine-grained reconstruction of phonemes or individual words difficult. Motivated by neuroscientific evidence that high-level semantic representations are distributed across cortical regions and evolve over slower temporal scales, we hypothesize that semantic content may provide a more suitable target for non-invasive decoding than low-level acoustic or lexical features. We introduce Brain2Semantics2Text, a method that reconstructs text through an intermediate semantic embedding space. Our model maps sentence-level MEG responses into a semantic manifold and then inverts the predicted embeddings into natural language. This semantic bottleneck enables recovery of high-level meaning without word-level alignment. We describe the core principles of the approach, its implementation, and the strategies used to mitigate the challenges of learning a reliable neural-to-semantic mapping. Finally, we compare against prior non-invasive Brain2Text methods and show improved sentence-level results.

---

### GANDR: Claim Auditing for Verifiable Legal Answer Generation

Authors: Chen Qian, Yimeng Wang, Yu Chen, Lingfei Wu, Andreas Stathopoulos
Published: 2026-09-09
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2609.10293v1

In high-stakes domains such as legal practice, a language-model answer is only useful to the extent that a reader can verify each claim against the source the system cites. Current grounded-generation pipelines score the answer as a whole, so a correct conclusion can rest on fabricated or loosely matched citations and still score well. Closing this gap requires both a system built for per-claim verification and an evaluation that measures it. We introduce GANDR (Grounded ANswer DRafter), a two-agent system in which a Drafter writes an answer in a structured legal-reasoning format and a separate Critic, with the same view as a human verifier, audits each claim against its cited source and emits a per-claim audit trace on every round. We pair it with a strict correctness criterion requiring every citation to resolve to a passage the retriever returned. On a 185-item legal benchmark where all six systems share one backbone, one retrieval surface, and one citation instruction, GANDR ranks first on every primary metric, reaching 70.8% strict accuracy and leading the strongest baseline by 11.3 points (p<0.01). Reverting the protocol-anchored commit rule lowers strict accuracy by 22.7 points, and the strict lead stays positive on three further backbones, at +3.2 to +6.5 points. This lead traces to the Drafter configuration and the protocol-anchored commit, not to rewriting. Against two law-trained annotators the audit flags under-supported claims at F1 0.84 as a binary detector, while its four-way verdict labels agree only weakly and are advisory. Code is available upon request.

---

### Isotropic Embedding Perturbations for Robust Vision Language Encoders

Authors: Hyesong Choi, Daeun Kim, Song Park, Taekyung Kim, Byeongho Heo, Sangdoo Yun, Dongbo Min, Dongyoon Han
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.10292v1

Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandErase, and DropPath, offer strong regularization effects, their combined use has saturated in performance due to overlapping functionalities, and aggressive pixel-level manipulations may disrupt delicate cross-modal alignment. This saturation motivates the search for a new augmentation axis within the embedding space rather than the input space. We introduce Aether, a simple plug-in method that applies diffusion-style random perturbations in the embedding space via controlled alpha-mixing, specifically designed to provide isotropic regularization that remains semantically consistent. Inspired by feature-space perturbations in language models and image degradation in generative pretraining, Aether induces mild yet effective perturbations that smooth the representations without compromising the fine-grained structural information required for strong vision-language encoders. Across diverse architectures and across multiple recognition tasks, Aether delivers consistent gains over the advanced recipe combining CutMix, Mixup, DropPath, and RandAug---a level of improvement rarely observed with modern augmentation alternatives. Notably, Aether demonstrates superior effectiveness in multi-modal alignment, succeeding where traditional pixel-space augmentations fail by providing a stable, isotropic regularization signal that respects the integrity of the high-dimensional feature space.

---

### Training Trajectories Determine Circuit Removability in Annealable Soft-Prior Transformers

Authors: Zonglin Yang, Ziming Zhao, Wei Tang, Xunyu Jiang, Yihong Liu, Tailin Chen, Zifu Yu, Jiayu Liu
Published: 2026-09-09
Categories: cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2609.10287v1

Soft positional priors can help small Transformers learn retrieval circuits, but it is unclear whether the resulting circuits remain functional once the prior is removed. We test this with an annealable soft-prior Transformer whose attention biases can be learned, faded, or zeroed during training and evaluation. On associative recall, unforced models perform well with the prior active ($0.772 \pm 0.020$) but collapse at zero gate ($0.095 \pm 0.009$). Smooth fade-to-zero training preserves high zero-gate accuracy ($0.734 \pm 0.028$), whereas forced-zero training, hard switching, and post hoc continuation fail to recover the same effect. The pattern also appears on Markov induction. Linear regression ICL provides a boundary case because zero-gate training can learn that task directly. Mechanistic traces show that circuit consolidation occurs after the gate reaches zero, even though the responsible heads vary across seeds. These results suggest that circuit removability in small discrete retrieval tasks depends on the training trajectory, not just the final architecture.

---

### FreqFLD: Towards All-in-One Facial Landmark Detection via Frequency Modulation

Authors: Shun Ren, Kaijie Jin, Shengkai Hu, Beihang Song, Hang Sun, Wenwen Min, Youfa Liu, Jun Wan
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.10278v1

Recent progress in deep learning has significantly advanced facial landmark detection. However, most existing methods process features in a spatial-domain manner under a dataset-specific training paradigm, which overlooks the fact that facial landmark detection is inherently geometry-driven and sensitive to frequency variations, thereby limiting cross-dataset generalization under complex scenarios and hindering the development of a facial landmark detection model. To address this issue, we propose \textbf{FreqFLD}, a \textbf{freq}uency-modulated framework towards All-in-One \textbf{f}acial \textbf{l}andmark \textbf{d}etection. Specifically, FreqFLD introduces a Frequency Modulation Module (FreqMoM) to explicitly induce the frequency prior by decoupling and modulating low- and high-frequency components, which is then injected into subsequent feature modeling to enable balanced modeling of global facial structure and local landmark details. Furthermore, FreqFLD employs a Frequency-Modulated Mixture-of-Experts (FreqMoE), with expert selection adaptively conditioned on frequency-modulated priors, enabling flexible modeling of heterogeneous facial landmark patterns under diverse and challenging scenarios. To regularize frequency-consistent modeling under the All-in-One paradigm, we further introduce a Frequency-Consistent Routing (FreqCR) loss, which constrains the routing and assignment of frequency-aware experts to promote balanced expert utilization across diverse facial scenarios, thereby enabling stable expert specialization and achieving robust facial landmark detection. Extensive experiments demonstrate that the proposed FreqFLD achieves comparable performance on popular datasets. The code is available at: https://github.com/jkj1059657014/FreqFLD.

---

### Structural Fusion of Bayesian Networks with Limited Treewidth Using Genetic Algorithms

Authors: Pablo Torrijos, José A. Gámez, José M. Puerta
Published: 2026-09-09
Categories: cs.NE, cs.LG
arXiv: https://arxiv.org/abs/2609.10276v1

This paper introduces an evolutionary computation approach for consensus in structural Bayesian Network (BN) fusion under the constraint of limited treewidth. The consensus BN aims to reconcile multiple input BNs into a single one that retains key structural features present in the original networks. Treewidth, a graph-based parameter associated with computationally tractable inference, is utilized to restrict the complexity of the resulting network. A genetic algorithm is proposed to look for a BN that codifies as much information about the unrestricted fusion as possible while ensuring the treewidth restriction. Experimental evaluation demonstrates the genetic algorithm's ability to obtain consensus BNs with limited treewidth, providing a valuable tool for aggregating information from diverse sources while returning a computationally actionable model.

---

### KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints

Authors: Xi Shi, Mengxin Zheng, Qian Lou
Published: 2026-09-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.10266v2

Reusing key-value (KV) caches speeds up LLM inference by avoiding repeated computation on shared text. Standard prefix caching reuses a KV cache only when the LLM is the same and all preceding text is identical, but real workloads often break both conditions: RAG systems place different documents before the same one, agents with different system prompts read the same file or tool output, multi-agent workflows use specialized LLMs on shared material, and an updated model reads documents cached by its previous version. Because KV caches depend on both the preceding text and the model weights, direct reuse can reduce answer quality. Many methods repair or compress the reused cache, but each paper uses its own tasks, models, and cost measures, and existing benchmarks mainly test long-context processing or reuse of an unchanged prefix. We introduce KVShareArena, a benchmark and open evaluation framework for comparing them under the same conditions. KVShareArena has (1) reuse tests on 2,150 questions from three QA datasets, where the preceding text, the cache-writing LLM, or both change while the answering LLM and input stay fixed; (2) five dense and mixture-of-experts LLMs (4B-30B) and six LLM pairs where one version of an LLM reads caches written by another, for 33 model-dataset settings; (3) 11 repair and compression methods from six method classes; (4) four evaluation perspectives: answer quality, prefill computation, KV-cache memory, and latency; and (5) a common interface for adding new methods and an interactive leaderboard. Experiments yield two findings. First, both the quality loss from reuse and which repairs help depend on the LLM, even between two 8B models. Second, most repairs keep their quality when another LLM version wrote the cache, but a trained repair adapter loses quality in 12 of 18 pair-dataset tests. Code and data: https://github.com/xishi404/KVShare-Arena

---

### KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints

Authors: Xi Shi, Qian Lou
Published: 2026-09-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.10266v1

LLM serving systems already reuse KV caches, but only when the reused text sits at the very start of the prompt. Two growing workloads break this condition: a retrieval-augmented generation server assembles a different set of retrieved chunks for every query, and a multi-agent coordinator reads reports written by other agents. Reused inside a new prompt, a cache carries the wrong positions and never attended to the other sources. The cache may also have been written by a different checkpoint of the same model family, which changes the stored values. Repair methods for such caches have appeared in three separate communities, each measured on its own terms, and existing benchmarks test only exact-prefix reuse, where nothing is lost. KVShareArena benchmarks KV-cache reuse across prompt contexts and model checkpoints on retrieved chunks and agent reports. It scores every method by the fraction of the gap it recovers between no cache and full recomputation, and charges compute, memory, and per-request latency with the cache in hand, reporting the one-time cost of building a cache separately. We find that correcting positions, which needs no recomputation, is enough until a question needs several sources at once. There, only methods that pay, by re-encoding part of the cache or by training, recover half to two thirds of the gap; unrepaired caches can be worse than no cache. Cache-compression methods that are harmless on a single prompt fall significantly behind position correction on freshly written agent reports. These patterns hold across three model boards. When a different checkpoint wrote the cache, training-free methods are barely affected, while an adapter trained on one checkpoint's caches loses quality. Harness, frozen querysets, and cost accounting ship as a pip package with an automated submission workflow and a public leaderboard.

---

### Maverick: Private and Verifiable LLM Inference Made Practical via Matrix-Vector Multiplication Delegation

Authors: Ben Merbaum, Mohammad Amin Raeisi, Wenhao Wang, Charalampos Papamanthou, Katerina Sotiraki, Fan Zhang
Published: 2026-09-09
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2609.10264v1

Open-source large language models (LLMs) are increasingly competitive with closed-source models while offering transparency and the ability to run inference without exposing user inputs to a service provider. However, running large-scale models locally requires substantial computational resources. In practice, users may still resort to a third-party provider, giving rise to privacy and correctness concerns. Existing solutions that address these problems often impose substantial server overhead or introduce additional trust assumptions. In this paper, we present Maverick, a novel approach to private and verifiable LLM inference based on a protocol for delegating matrix-vector multiplication, a dominant operation in LLMs. At its core, Maverick provides, to our knowledge, the first information-theoretically sound verification protocol for matrix-vector multiplication delegation with transparent preprocessing, efficient (batch) verification, and virtually no server overhead. We combine this verification primitive with LPN-based pseudorandom masking to provide input privacy. We implement our matrix-vector delegation primitive and use it to build an end-to-end prototype of Maverick, which we evaluate on Qwen3-4B by measuring throughput in tokens per second. We evaluate client configurations with 1-8 threads. With one client thread and a CPU server using up to 128 threads, Maverick achieves throughput gains over local inference of up to 17x when privacy masks are generated online, 45x when they are precomputed, and 44x when only verification is required. With four client threads, the corresponding gains are 13x, 18x, and 17x. When server computation is no longer the bottleneck, client-side microbenchmarks with simulated network delay show speedups of 12x-20x, 34x-135x, and 38x-157x.

---

### What Should an Agent Forget? Separating What Is Stored from What Is Used

Authors: Yuhang Li, Yuchen Li
Published: 2026-09-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.10263v1

Persistent language agents need stored experience to remain available across time, while each answer requires evidence suited to a particular question. A superseded fact can mislead a current-state answer and still be essential for a historical query. We present RD-Forget, a training-free framework that separates what an agent stores from what it uses. A retained source archive preserves observations, and a query-conditioned memory view controls their influence on the current answer. A frozen language-model curator extracts relevant evidence, groups facts into semantic slots, and preserves the relations needed for multi-hop reasoning. Same-slot replacement links suppress superseded values in current-state contexts, while intent-aware retrieval makes earlier evidence eligible again. A rate-distortion formulation guides construction of the answer-time view within a memory budget. Experiments span conversational memory, knowledge updating, fact consolidation, long-context reasoning, and personalization under a shared answering pipeline. The results associate accurate answers with both query-relevant evidence construction and control over obsolete alternatives. Configurations without forgetting or query conditioning have the largest score deficits, while slot grouping, historical access, and relation preservation contribute complementary functions. Retaining history while selectively controlling its use offers a practical way to accommodate changing facts and future questions.

---

### When Fusion Fails: Corruption-Aware Rebalanced Fusion for Multi-Modal Medical Image Segmentation

Authors: Yuchen Pei, Xiaoyu Hu, Yixiong Zou, Dingwen Hu, Hui Chu, Yutao Ma, Shijun Qiu, Gang Li
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.10261v1

Multi-modal medical image segmentation leverages complementary diagnostic information, yet fusion can underperform single-modality baselines when spatially aligned inputs differ in quality. Here, "corruption" primarily denotes resolution-induced degradation rather than misalignment or complete modality absence, while synthetic noise is evaluated only as an auxiliary setting. We identify a critical optimization-inference inconsistency: degraded modalities can receive weak training updates yet substantially affect predictions, indicating active interference with fusion. We attribute this failure to resampling-induced feature corruption and optimization bias, where noisy features propagate through skip connections and encourage unreliable modality selection. We therefore propose CoReFuse-Med, a Corruption-aware Rebalanced Fusion framework that suppresses corruption during feature transmission and rebalances modality contributions during high-level fusion. Experiments on EPVS, BraTS, and WMH, including multiple Z-axis slice-retention ratios and an auxiliary noise test, demonstrate improved accuracy and robustness under modality-quality discrepancies. Our code is available at https://github.com/lrever/CoReFuse.

---

### DiSCo: A Distribution-First Steering and Cultural Prior Evaluation Framework for Measuring Cultural Preference Bias in LLMs

Authors: Bhuvan Arora, Devesh Saraogi, Sravya Varada, Dhruv Kumar
Published: 2026-09-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2609.10253v1

Large language models (LLMs) are increasingly deployed in globally used assistants, yet their default choices in culturally grounded everyday situations can systematically favour some cultures over others, affecting localisation, user trust, and equitable behaviour. Existing cultural benchmarks evaluate accuracy against a single "correct" answer, making it difficult to characterise an LLM's cultural preference prior when multiple culturally grounded responses are all valid; they also conflate default preferences with context-driven adaptation. We propose DiSCo, a distribution-first forced-choice evaluation framework that isolates default cultural priors and tests steerability via a four-level context gradient (C0--C3). Using DiSCo-Bench (304 items) derived from BLEnD spanning 12 cultures, we evaluate six diverse instruction-tuned LLMs. Default priors are heavily concentrated, with UK and US together absorbing approximately 35\% of all selections despite representing only 2 of 12 cultures. Most critically, prompt-based steering consistently widens the selection gap between high- and low-resource cultures, and injecting explicit cultural facts produces negligible distributional disruption, confirming that cultural preference bias cannot be resolved through prompt-based personalisation alone.

---

### A-JIT: Agentic Just-In-Time Software Construction

Authors: Mark Marron, Earl T. Barr
Published: 2026-09-09
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2609.10248v1

Traditional software delivery assumes a static paradigm: code is constructed prior to execution and deployed as a fixed artifact. We present Agentic Just-In-Time Software Construction (A-JIT), a paradigm that replaces static binaries with dynamic, software systems that can perpetually evolve to meet changing demands. In A-JIT, an application is an integrated assembly comprising code, a runtime harness, and an embedded AI agent that continuously observes system usage and live execution traces. Much like a traditional JIT compiler specializes machine code to runtime execution paths, A-JIT specializes software logic, workflows, and tool interfaces to meet the specific needs of the end-user. By integrating synthesis directly into the ambient application lifecycle, A-JIT enables applications to dynamically construct missing implementations, generate new capabilities on the fly, and continuously adapt to end-user behavior. We demonstrate how this model supports trace-driven human-AI co-construction and opens a new design space for adaptive, self-evolving software.

---

### Two-Token Features and Small-Large Ensembles for VLM Hallucination Detection

Authors: Eli Schwartz
Published: 2026-09-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.10244v1

We present our system for the SHROOM-Visions 2026 shared task on character-level VLM hallucination detection. A small ($4$B-parameter) VLM is fine-tuned as a per-token classifier reading a two-token feature from its own hidden states, and is ensembled with a $\sim$400B zero-shot VLM judge at prediction time. Both components see off-the-shelf OCR of any visible in-image text. We use synthetic hallucination data generated by the large model as a source of ensemble diversity, and use validation to select feature layer, training data and OCR grounding. Our official entry reaches mean Cor $0.487$ / Cor-lbl $0.387$ on the hidden test set, placing $6$th/$28$ (EN), $6$th/$21$ (FR), $8$th/$21$ (IT) and $7$th/$22$ (ZH) on the task's primary Cor-lbl metric.

---

### LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation

Authors: Daniel Alejandro Coll Tejeda, Pedro García López, Daniel Barcelona-Pons
Published: 2026-09-09
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2609.10239v1

Graph-based retrieval can improve multi-hop question answering, but existing approaches often incur high query-time costs and produce diffuse, oversized contexts that reduce generation efficiency. We present LiteRAG, a graph-based retrieval method that replaces expensive retrieval-time LLM control with query-conditioned algorithmic exploration and reasoning-chain context construction. On DistComp, a benchmark for multi-hop retrieval over distributed-systems papers, LiteRAG attains the highest overall quality among the evaluated methods (0.798) while reducing per-query latency by over 100$\times$ and cost by over 99% relative to GraphRAG Global and DRIFT. On UltraDomain, it matches LinearRAG on overall quality while using about 14$\times$ fewer tokens. An ablation study indicates that LiteRAG's query-adaptive thresholding and community-aware hub penalization are the main drivers of its token-efficiency gains.

---

### The Answer Path and the Grounding Instruction in LLM Question Answering over Knowledge Graphs

Authors: Arquimedes Canedo
Published: 2026-09-09
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2609.10237v1

A graph retrieval-augmented generation pipeline chooses which triples to put in the prompt, a syntax to write them in, an order to write them in, and a sentence telling the model what to do with them. We vary all four over six large language models and two knowledge-graph question answering benchmarks. Two of the four choices move the answer and the other two are flat. The first is whether the answer path, the triples needed to reach the answer, is in the prompt at all. Holding the number of triples fixed and replacing every triple that is not on the chain with material from an unrelated entity changes answer accuracy by +0.003 F1, while removing the chain costs most of what the graph was worth. Retrieval budget belongs on recall, and precision in the range we can test buys nothing. There is no retriever here: subgraphs come from gold SPARQL, so precision describes the context we build, not a system setting. The second is the grounding instruction. With no facts in the prompt, telling a model to answer using only the provided facts drops F1 from 0.299 to 0.035, a factor of 8.63. That figure describes an evaluation with an empty context arm rather than a working pipeline, and an experiment that applies the instruction to its context arm but not to its no-context baseline manufactures a spurious finding that graph context hurts at depth. We found one in our own results and retract it. Syntax, triple order and subgraph size produce no effect we can measure at multi-hop depth. The comparison that would price the grounding instruction against correct context is not measurable with a format-sensitive scorer, because the instruction determines the response format; we report it as an open contrast rather than a number.

---

### $Φ$-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?

Authors: Leilei Ding, Shumin Wang, Yuting Huang, Fanqi Wan, Yinmin Zhang, Qi Han, Yiming Xu, Feiyuan Zhang, Xiaomeng Chu, Guoliang You, Wuyang Zhang, Daxin Jiang et al.
Published: 2026-09-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.10226v1

Large language models (LLMs) have demonstrated remarkable capabilities in reasoning and code generation, raising the prospect that they could assist in developing and optimizing the very infrastructure that powers them. However, existing benchmarks mainly focus on isolated kernels, predefined operators, or pre-specified optimization targets, and therefore fail to evaluate the ability of LLMs to perform open-ended, long-horizon LLM infrastructure engineering. To address this gap, we present $Φ$-Bench, a benchmark for systematically evaluating LLMs on engineering the LLM infrastructure stack. Derived from optimization problems studied in frontier research and grounded in real-world code repositories, $Φ$-Bench provides broad coverage of the LLM infrastructure stack and spans tasks of varying complexity, ranging from localized kernel-level function completion to long-horizon implementation and end-to-end system optimization. Extensive experiments on frontier LLMs reveal their current capabilities and limitations in engineering complex LLM infrastructure, offering insights into the challenges that remain on the path toward autonomous optimization of future AI infrastructure.

---

### Hierarchical and Permutation-Invariant Feature Transformation Learning via Policy-Guided Embedding Search

Authors: Rui Liu, Tao Zhe, Yanyong Huang, Sankha Narayan Guria, Xiao Luo, Wei Fan, Yanjie Fu, Dongjie Wang
Published: 2026-09-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2609.10225v1

Feature transformation improves predictive performance on tabular data by constructing informative abstractions from raw features. Recent generative approaches encode transformation knowledge into continuous embedding spaces for efficient exploration of candidate strategies, but face three key limitations: (1) overlooking hierarchical relationships between low-level features, operations, and high-level abstractions; (2) enforcing order-sensitive embeddings on inherently permutation-invariant transformation sequences, thereby introducing systematic bias; and (3) relying on gradient-based search, which is ill-suited to non-convex transformation spaces. We propose a framework with two complementary components. First, a permutation-invariant hierarchical module captures interactions across features, operations, and abstraction levels, with a self-attention pooling mechanism that maps semantically equivalent structures to consistent embeddings aligned with downstream performance. Second, a policy-guided multi-objective reinforcement learning strategy initializes the search from empirically strong seeds and jointly optimizes predictive accuracy and transformation efficiency. Extensive experiments on diverse tabular benchmarks demonstrate the effectiveness and robustness of our framework against strong baselines. Our code and data are publicly available at: https://github.com/RayLiu1103/PHER.

---

### UOT-Gap: A Variational Principle for the Modality Gap in Vision-Language Models via Unbalanced Optimal Transport

Authors: Zonglin Yang, Huilan Ma, Xudan Zheng, Yuejun Xie
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.10224v1

Vision-language models such as CLIP embed images and text in a shared space, where modality-specific distributions often remain separated. Existing accounts connect this modality gap to initialization, contrastive dynamics, and information imbalance, while its distributional and pairwise contributions to retrieval remain unresolved. We introduce UOT-Gap, a training-free variational diagnostic that models frozen image and text embeddings with unbalanced entropic optimal transport (UOT). The UOT optimum separates transport, coupling complexity, and marginal mass variation; a complementary pair-aware residual compares observed image-caption pairs with the UOT soft matching. On Flickr8K and COCO-1K with frozen CLIP, OpenCLIP, and SigLIP encoders, caption degradation reduces Flickr8K Recall@1 from 0.559 to 0.003. Across six dataset-model conditions, the pair-aware residual tracks retrieval degradation with mean absolute Spearman 0.973, compared with 0.392 for the mean gap. The association remains stable across five random COCO-1K subsets at $0.954\pm0.026$, with a minimum of 0.943. UOT barycentric updates reduce the transport objective while degrading retrieval, distinguishing geometric objective descent from task improvement. These results establish UOT-Gap as a diagnostic for caption quality, modality alignment, and retrieval robustness.

---

### Why Sample What You Can Enumerate? Exact Policy Optimization for Genomic Tool Selection

Authors: Haoyue Liu, Xiaoyu Ma, Ye Chen, Zhichao Wang, Xiaoying Tang
Published: 2026-09-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.10221v2

Reinforcement learning over a frozen reasoner has become a common recipe for teaching a policy which external tools to invoke. We show that this recipe becomes structurally mismatched in specialist scientific settings where the complete tool-subset space is enumerable. There, a small set of recurring computational capabilities covers the domain, so the space of tool subsets is combinatorial yet small enough to enumerate, and GRPO still estimates an action expectation from a handful of sampled rollouts. Worse, the approximation degrades as training succeeds: as the policy concentrates on preferred subsets it resamples them, sampled rewards collide, and the group-normalized advantage vanishes. On genomic reasoning the fraction of questions yielding no reward signal rises from 0.2% under a uniform reference policy to 20.8% after GRPO training. As a remedy, we introduce FGPO (Full-Group Policy Optimization), which (1) scores every tool subset and optimizes the exact action expectation, so each update sees the complete action space, and (2) precomputes the reward of each question--subset pair into an exhaustive table, removing frozen-reasoner calls from the training loop entirely. Across five frozen reasoners and three genomic benchmarks, FGPO outperforms GRPO in all 15 settings by 6.75 points on average and up to 14.20, while a standard on-demand GRPO schedule would require 2.4 times as many frozen-reasoner reward evaluations and, on GenomeQA, FGPO cuts invoked tools per question from 2.36 to 1.40.

---

### Why Sample What You Can Enumerate? Exact Policy Optimization for Genomic Tool Selection

Authors: Haoyue Liu, Xiaoyu Ma, Ye Chen, Zhichao Wang, Xiaoying Tang
Published: 2026-09-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.10221v1

Reinforcement learning over a frozen reasoner has become a common recipe for teaching a policy which external tools to invoke. We show that this recipe becomes structurally mismatched in specialist scientific settings where the complete tool-subset space is enumerable. There, a small set of recurring computational capabilities covers the domain, so the space of tool subsets is combinatorial yet small enough to enumerate, and GRPO still estimates an action expectation from a handful of sampled rollouts. Worse, the approximation degrades as training succeeds: as the policy concentrates on preferred subsets it resamples them, sampled rewards collide, and the group-normalized advantage vanishes. On genomic reasoning the fraction of questions yielding no reward signal rises from 0.2% under a uniform reference policy to 20.8% after GRPO training. As a remedy, we introduce FGPO (Full-Group Policy Optimization), which (1) scores every tool subset and optimizes the exact action expectation, so each update sees the complete action space, and (2) precomputes the reward of each question--subset pair into an exhaustive table, removing frozen-reasoner calls from the training loop entirely. Across five frozen reasoners and three genomic benchmarks, FGPO outperforms GRPO in all 15 settings by 6.75 points on average and up to 14.20, while a standard on-demand GRPO schedule would require 2.4 times as many frozen-reasoner reward evaluations and, on GenomeQA, FGPO cuts invoked tools per question from 2.36 to 1.40.

---

### Through the Looking Glass: Directly Reading and Writing Transformers

Authors: Mark Oskin
Published: 2026-09-09
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2609.10210v1

How many of a transformer's components decide a token? Counted by the absolute value of each unit's and channel's contribution to the logit, one prediction rests on thousands to hundreds of thousands of them. But contributions are signed, and across eighteen models the mass pushing away from the predicted token is a median of seven times the mass carrying it. Divide by the net and the count is dozens: on the baseline, 53 components carry ninety percent of a prediction, 13 it cannot survive losing, and 8 suffice to produce it alone. Across twelve models trained elsewhere, 124M to 7B parameters, the sufficient set runs from two components to sixteen, and what a prediction draws on, followed all the way back, is one to three percent of the model, a share that does not grow with size. Three quarters of a layer's update is a fixed linear map of the state it received. Everything is read from the model's own parameters and activations, with nothing trained or fitted, and it names a component on both sides: what it writes, from the predictions it drives, reaching close to half of every model; what it reads, from its weights in the frame of its own layer, at 58.9 percent above chance over its eight strongest inputs. Sorting the remainder by upstream source yields grammatical categories the embedding cannot see. A name can be acted on. An association the model does not hold installs into one spare unit, key and value read from the weights, for a quarter of a percent of held-out loss, a fortieth of what a rank-one update costs. An installed attention head and a unit two layers above it make an edit fire only where a token occurred earlier in the context, and a unit the model trained for itself is driven from two layers upstream, 86 percent of the effect passing through it. An order-preserving activation puts a unit's inputs at the instrument's ceiling, at the price of a two-part install.

---

### Robust Beam Prediction for V2X Networks with Multi-Modal Sensing

Authors: Chen Shang, Dinh Thai Hoang, Diep N. Nguyen, Jiadong Yu
Published: 2026-09-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.10200v1

Integrated sensing and communication (ISAC) provides a promising foundation for beam prediction in future vehicle-to-everything (V2X) networks. However, existing sensing-assisted beamforming methods still rely heavily on radio-frequency sensing, which may become unreliable in complex vehicular environments. Meanwhile, the growing availability of heterogeneous sensors, such as cameras and LiDAR, offers new opportunities to improve beam prediction through richer environmental perception. Motivated by this, this paper proposes a multi-modal beam prediction framework for V2X networks. Specifically, we develop BeamTransFuser, a hierarchical Transformer-based architecture that progressively fuses camera, LiDAR, radar, and GPS observations for robust beam prediction. In addition, to handle possible missing modalities in practical deployment, we introduce a generative module that reconstructs missing modality features from the available observations. Experimental results on a real-world multi-modal V2X dataset show that the proposed framework consistently outperforms representative baselines, while the generative module further improves robustness under incomplete sensing conditions.

---

### Politics of Feelings: Emotional Expression and Legislative Effectiveness in the U.S. Congress

Authors: Segun Aroyehun
Published: 2026-09-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.10198v1

Emotions are a pervasive feature of political communication, yet existing research has focused primarily on describing patterns of emotional expression rather than examining whether they are associated with consequential legislative outcomes. We address this gap by investigating the expression and correlates of discrete emotions in more than 1.7 million speeches delivered in the U.S. Congress between 1973 and 2024. Using a transformer-based emotion classifier, we measure eight discrete emotions: anger, fear, disgust, sadness, joy, enthusiasm, pride, and hope. We examine how these emotions vary over time, across policy topics, legislator characteristics, and their relationship with legislative effectiveness. We find that congressional speeches are becoming emotionally expressive over time. Emotional expression also varies systematically across policy domains and ideological positioning of legislators. Notably, the relationship between emotional expression and legislative effectiveness depends on the specific emotions expressed: enthusiasm and pride are positively associated with effectiveness, whereas anger exhibits a negative association. Emotional valence and emotional diversity are positively associated with legislative effectiveness, while emotional intensity is negatively associated with legislative effectiveness. These findings demonstrate that computationally derived measures of discrete emotions can provide insight into affective dimensions of legislative speeches and facilitate our understanding of how legislators communicate, interact, and perform within democratic institutions.

---

### An Exponential Deterministic--Randomized Gap in ERM-Oracle Complexity for Thresholds on an Unknown Order

Authors: Xuan Li
Published: 2026-09-09
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2609.10196v1

Attias, Hanneke and Ramaswami (NeurIPS 2025) asked whether randomization provably reduces the oracle calls needed for online learning when the class is accessible only through an oracle. We study the instance they singled out: transductive online learning of thresholds on an unknown total order of T instances, with a consistency-type ERM oracle that returns a full concept consistent with a queried labeled set (or reports non-realizability). Our main result is a separation for a fixed natural oracle. When the oracle is the minimal-prefix rule (or the maximal-prefix rule), every deterministic learner makes M mistakes and Q calls with $M+Q\ge T-\varepsilon$ on some instance ($\varepsilon\in\{0,1\}$, according to whether the empty prefix is a concept), and the constant is exact; hence $O(\log T)$ mistakes cost $T-\varepsilon-O(\log T)$ calls, whereas that paper's randomized learner achieves $O(\log T)$ expected calls and mistakes under the same rule. The randomized order is optimal: on an explicit hard distribution under the minimal-prefix rule, every learner has expected mistakes at least $((T+1-\varepsilon)\,128^{-\mathbb{E}(Q)}-1)/2$, so $Ω(\log T)$ expected calls are necessary for polylogarithmic mistakes. The separation is governed by the oracle's selection rule, not by the class alone: for a legal feasible-median ERM rule a deterministic learner achieves $O(\log T)$ calls and mistakes, while a global-median rule again forces linear total cost. The same linear bound holds when the oracle's answers are chosen adversarially and then frozen into a memoryless oracle. We add partial tradeoff results for fixed query budgets (the middle regime is open) and an interface contrast: with only a weak consistency oracle, returning a realizability bit, both deterministic and randomized learners need $Θ(T)$ calls.

---

### Are You Learning Biological Signal or Shortcuts? Auditing and Mitigating Bias in Protein-Protein Interaction Datasets

Authors: Judith Bernett, Anton Spannagl, Joel Ås, Markus List, David B. Blumenthal
Published: 2026-09-09
Categories: q-bio.MN, cs.LG
arXiv: https://arxiv.org/abs/2609.10193v1

Protein-protein interaction (PPI) databases do not faithfully reflect biological realities. Instead, they are influenced by study and technical biases that distort certain protein and interaction attributes. Machine learning models can exploit these as learning shortcuts if the negative dataset is not constructed with care. So far, the shortcuts introduced during PPI dataset construction have only been examined in isolation. Here, we systematically characterize both reported and, to our knowledge, previously unreported biases in PPI datasets that lead machine learning models to learn shortcuts instead of biological signal. We analyze HIPPIE, IntAct, and STRING, dedicated PPI databases, as well as two datasets derived from 3D-structural information in the Protein Data Bank (PDB). We show that random data splitting introduces strong topological shortcuts. When train-test protein overlap is removed, the resulting datasets still retain usable shortcuts stemming from self-interactions, taxonomic identity, and functional relatedness, whose prevalence interestingly depends on the data source. We further show that sampling negatives from a set of high-confidence non-interactors, an intuitively appealing choice, can amplify the shortcut stemming from functional relatedness. To detect and mitigate these biases, we provide an open Nextflow pipeline that combines similarity-aware, data-loss-minimizing dataset splitting with bias-minimizing negative sampling, both formulated as integer linear programs. Its key concept of quantifying biases to minimize them through optimization-based negative sampling can, in principle, be extended to any machine learning problem where the pool of negative candidates is much larger than the positives and is thus of interest also beyond PPI prediction.

---

### Who Argues What? Joint Argument-Entity Detection and Classification in Political Debates

Authors: Lucio La Cava, Stefano Francesco Monea, Sergio Greco
Published: 2026-09-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.10192v1

Political debates are often analyzed through Argument Mining (AM) to investigate the key arguments that drive them. However, political arguments are rarely interpretable from argumentative spans alone, as claims and premises generally depend on the entities (e.g., people, events, locations, parties) they mention. Existing AM resources and methods typically annotate argumentative spans and roles, but do not provide a paired debate-entity layer for asking which Debate Named Entities (DNE), e.g., actors and events, are invoked within debates. In this work, we address these data and methodological gaps by (i) introducing DNE-ElecDeb, an entity-enriched version of the USElecDeb dataset that adds DNEs in both argumentative and non-argumentative spans and defines Debate Named Entity Recognition (DNER) as the task of detecting DNEs, and (ii) proposing Joint Argument and Entity Tagging (JAET), a generative framework that fine-tunes decoder-only LLMs to insert inline argument and entity tags into debate turns while preserving the original transcript. Under BIO-tagging evaluation, JAET improves relative F1 on the joint AM+DNER task by +27.3%, resp. +41.9%, under the untyped, resp. typed setting over the strongest sequential AM-DNER pipelines, demonstrating that such gains cannot be recovered by composing two independent modules. Notably, similar margins replicate on Persuasive Essays (+26.6%, resp. +52.7%), showing effective generalization to domains orthogonal to political debates. By unifying argumentative and entity-level representations within a single view, our contributions pave the way for richer political debates understanding.

---

### 3rd Place Solution to Human Motion Challenges in Real-World and Clinical Settings (MoCha) @ECCV2026: Language-Aligned Motion Representations for Domain-Generalizable UPDRS-Gait Severity Estimation

Authors: Soojie Kim, Muhammad Munsif, Minkyung Kim, Seungryul Baek
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.10187v2

In this work, we introduce language-aligned motion representations for domain-generalizable UPDRS-Gait severity estimation, aiming to learn semantically structured motion features that generalize across heterogeneous clinical domains. We first learn motion representations using a Bi-GRU backbone that captures the temporal dynamics of SMPL sequences. Prior to model training, motion captions are generated offline using Qwen2.5-7B-Instruct. The backbone is then trained with both classification and text-alignment objectives to learn discriminative and semantically structured motion representations while accounting for the class imbalance present in the training data. We subsequently adapt the learned backbone independently to each source domain so that the model can capture domain-specific motion characteristics. The resulting source-specific models are then merged at the parameter level to consolidate complementary knowledge across source domains into a single domain-generalized model. To further mitigate class imbalance, we perform GPT-5.5-based pseudo labeling, and our final merged models for each site do not use any class-prior correction during inference. The resulting model is evaluated under the unseen-site setting of the MoCha Challenge, using Macro F1 as the primary evaluation metric. Our method achieves a macro-F1 of 0.57 on the hidden test set with only 637K active parameters at inference, ranking 3rd among 58 leaderboard entries in the MoCha 2026 Challenge. The challenge attracted 1,669 submissions from 112 participants and offered monetary prizes sponsored by Machine Medicine Technologies.

---

### 3rd Place Solution to Human Motion Challenges in Real-World and Clinical Settings (MoCha) @ECCV2026: Language-Aligned Motion Representations for Domain-Generalizable UPDRS-Gait Severity Estimation

Authors: Soojie Kim, Muhammad Munsif, Minkyung Kim, Seungryul Baek
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.10187v1

In this work, we introduce language-aligned motion representations for domain-generalizable UPDRS-Gait severity estimation, aiming to learn semantically structured motion features that generalize across heterogeneous clinical domains. We first learn motion representations using a Bi-GRU backbone that captures the temporal dynamics of SMPL sequences. Prior to model training, motion captions are generated offline using Qwen2.5-7B-Instruct. The backbone is then trained with both classification and text-alignment objectives to learn discriminative and semantically structured motion representations while accounting for the class imbalance present in the training data. We subsequently adapt the learned backbone independently to each source domain so that the model can capture domain-specific motion characteristics. The resulting source-specific models are then merged at the parameter level to consolidate complementary knowledge across source domains into a single domain-generalized model. To further mitigate class imbalance, we perform GPT-5.5-based pseudo labeling, and our final merged models for each site do not use any class-prior correction during inference. The resulting model is evaluated under the unseen-site setting of the MoCha Challenge, using Macro F1 as the primary evaluation metric. Our method achieves a macro-F1 of 0.57 on the hidden test set with only 637K active parameters at inference, ranking 3rd among 58 leaderboard entries in the MoCha 2026 Challenge. The challenge attracted 1,669 submissions from 112 participants and offered monetary prizes sponsored by Machine Medicine Technologies.

---

### A Bio-Plausible Visual Neural Network for Locust-Inspired Collision Perception

Authors: Qinbing Fu, Jiani Li, Jiajun Huang, Jigen Peng
Published: 2026-09-09
Categories: cs.NE, q-bio.NC
arXiv: https://arxiv.org/abs/2609.10183v1

Locust visual systems have long served as an important biological paradigm for studying looming perception and collision avoidance. Numerous computational models have successfully reproduced the selective responses of Lobula Giant Movement Detector (LGMD) neurons to approaching objects, thereby emulating the fundamental functionality of the biological system. However, existing models remain limited in biological plausibility and robustness when operating in complex and dynamic visual environments. To address these limitations, we propose a biologically plausible neural network for locust-inspired looming detection. The proposed framework incorporates a spatially isotropic sampling strategy that mimics the ommatidial organization of the locust compound eye, a population-voting mechanism inspired by population coding in biological neural systems, and leaky integrate-and-fire neuronal dynamics to replace conventional sigmoid-based membrane activation. Systematic experiments on synthetic stimuli, laboratory sequences, and real-world driving scenarios demonstrate that the proposed model improves robustness under challenging visual conditions while preserving computational efficiency and enhancing biological fidelity. These results highlight the potential of biologically grounded neural computation for robust and efficient collision perception.

---

### Can AI Agents Deliver Verifiable Network-Wide Outcomes Across Authority Boundaries?

Authors: Tianzhu Zhang, Chih-Kai Huang, Meikang Qiu
Published: 2026-09-09
Categories: cs.NI, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2609.10181v2

AI agents are increasingly involved in network automation, where they can initiate configuration changes through mediated operational interfaces and assess the resulting state. Nonetheless, operational networks usually span many devices and administrative domains. Realizing an operator's intent requires coordinating agents with distinct authority scopes that define the resources they can access, the operations they can invoke, and the network state they can observe. This division limits the blast radius of an erroneous action but fragments the evidence needed to assess the network-wide outcome. Successful execution of a configuration action proposed by one agent does not establish that remote devices responded as intended or that routing changes reached the required devices. A valid observation may also become stale after a subsequent change. Before the coordinated operation can be declared complete, a trusted assurance layer must collect current observations from the required scopes and determine whether they collectively support the operator's intended network-wide outcome. To address the completion admission problem, we present EvidenceNet, a runtime assurance layer for deciding whether coordinated agent operations have achieved an operator's network intent. Its broker collects the post-change observations required by a completion contract, and its admission gate checks that the evidence comes from the required scopes, remains current, and satisfies the task rules. A verifier agent provides an additional assessment of the observation content. Experiments on live routing networks show that post-change state checks recognize successful outcomes that configuration-action records alone cannot establish. Controlled interventions further show that EvidenceNet rejects completion when otherwise satisfactory observations have the wrong source, have been substituted, or are stale.

---

### Can AI Agents Deliver Verifiable Network-Wide Outcomes Across Authority Boundaries?

Authors: Tianzhu Zhang, Chih-Kai Huang, Meikang Qiu
Published: 2026-09-09
Categories: cs.NI, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2609.10181v1

AI agents are increasingly involved in network automation, where they can initiate configuration changes through mediated operational interfaces and assess the resulting state. Nonetheless, operational networks usually span many devices and administrative domains. Realizing an operator's intent requires coordinating agents with distinct authority scopes that define the resources they can access, the operations they can invoke, and the network state they can observe. This division limits the blast radius of an erroneous action but fragments the evidence needed to assess the network-wide outcome. Successful execution of a configuration action proposed by one agent does not establish that remote devices responded as intended or that routing changes reached the required devices. A valid observation may also become stale after a subsequent change. Before the coordinated operation can be declared complete, a trusted assurance layer must collect current observations from the required scopes and determine whether they collectively support the operator's intended network-wide outcome. To address the completion admission problem, we present EvidenceNet, a runtime assurance layer for deciding whether coordinated agent operations have achieved an operator's network intent. Its broker collects the post-change observations required by a completion contract, and its admission gate checks that the evidence comes from the required scopes, remains current, and satisfies the task rules. A verifier agent provides an additional assessment of the observation content. Experiments on live routing networks show that post-change state checks recognize successful outcomes that configuration-action records alone cannot establish. Controlled interventions further show that EvidenceNet rejects completion when otherwise satisfactory observations have the wrong source, have been substituted, or are stale.

---

### Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning

Authors: Mingbo Yang, Wenqiang Wang, Zhaolu Kang, Peng Chen, Yannan Chen, Sunshang Wang, Yan Xiao
Published: 2026-09-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.10177v1

In-context learning (ICL) is widely used in multimodal large language models (MLLMs) and achieves strong performance across a wide range of multimodal tasks. However, existing multimodal ICL methods often rely on surface level imitation of in-context demonstrations, making it difficult for MLLMs to align their responses with the reasoning path required by the given multimodal input. This limitation becomes more pronounced in complex multimodal tasks, thereby restricting further improvements in MLLM performance. To address this issue, we propose a new multimodal ICL framework that combines contrastive demonstration modeling with the self-refinement capability of MLLMs. Specifically, our framework reformulates each demonstration by explicitly contrasting a suboptimal response with a better response under the same input, together with a reasoning path that reveals how the response should be refined. This contrastive formulation makes the reasoning path toward the desired response more explicit and guides the MLLM beyond superficial imitation. Furthermore, because effective refinement depends on the current response, we introduce a response-conditioned retrieval mechanism to select demonstrations whose reasoning paths are more relevant to the current response. In addition, we use a lightweight alignment controller to predict response quality and determine whether further refinement is needed. Experiments on three types of multimodal tasks show that the proposed framework consistently improves MLLM performance, with particularly notable gains on visual question answering (VQA).

---

### CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalization

Authors: Luyao Tang, Jiewei Zheng, Kunze Huang, Chaoqi Chen, Yue Huang, Cheng Chen
Published: 2026-09-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.10158v1

Generalized Category Discovery (GCD) assigns unlabeled instances, mixed with labeled data, to known or novel categories, requiring human-like compositional reasoning: reusing primitives learned from known classes and deciding when new combinations imply new categories. Existing GCD methods operate on unstructured token features and struggle to extrapolate to novel compositions. We propose CoGe-GCD, which rethinks GCD through compositional generalization with two coupled stages. (i) Compositional Perception structures patch tokens by mapping them to a small vocabulary of primitives and refining token embeddings via competitive token-primitive assignment and information passing, yielding coherent groups for discovery. (ii) Generalizing Induction exploits the induced geometric structure and applies a structure-preserving calibration over spatial relations, maintaining probabilistic semantics while improving extrapolation to unseen primitive combinations. CoGe-GCD is implemented as an inductive-bias module between backbone and projection head, without modifying heads or losses, and can be plugged into diverse GCD frameworks. On standard benchmarks, it consistently improves all-class accuracy, unknown-class number estimation, and geometric quality, with marginal computational overhead. Code is available at https://github.com/lytang63/CoGe-GCD.

---

### ScopeMamba-YOLO: Widening the Perceptual Scope Inward and Outward for Small Object Detection in Remote Sensing Imagery

Authors: Junjie Fan, Yijun Mai, Linduo Wei, Jiayu Rao, Junmin Bao, Qiushi Jin, Guijia Li, Yong Qi
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.10156v1

Small object detection in unmanned aerial vehicle (UAV) and remote sensing imagery requires preserving high-resolution detail while modeling long-range context. Adding a stride-4 detection level and removing the stride-32 stage benefits tiny targets but weakens peripheral spatial support, whereas directly inserting selective scanning into the main feature path can interfere with weak local cues. We propose ScopeMamba-YOLO, built around an off-path, zero-gated selective-scanning principle that decouples contextual modeling from the convolutional stream. The principle is instantiated by a Cascaded Global-Context Module (CGCM) in the backbone and a Selective-Scan PAN (SS-PAN) in the neck. An Adaptive Multi-scale Strip (AMS) Block reduces the cost of high-resolution feature extraction, while a Scale-Adaptive DFL (SA-DFL) head reallocates distributional support and regression capacity across scales with only 0.008M additional parameters. Controlled experiments show that matched main-path selective scanning reduces mAP50 by 0.98 pp, whereas off-path CGCM improves the final configuration by 0.67 pp over the three-seed no-CGCM mean; operator controls indicate that this gain is not explained by auxiliary branch capacity alone. ERF analysis further shows that the complete context pathway increases the peripheral energy ratio from 0.008 to 0.090 at stride 8. On VisDrone-2019, ScopeMamba-S achieves 50.8% mAP50 with 3.57M parameters, exceeding YOLOv8s by 10.8 pp while using 32% of its parameters; ScopeMamba-M reaches 52.6% mAP50 with 6.48M parameters. Consistent improvements are also observed on AI-TOD, especially for very-tiny and tiny objects.

---

### From Retrieval to Weights: Parametric Individualization of Small Language Models with Individual Text Corpora

Authors: Christoph Wigbels, Ali Abusaleh, Markus T. Jansen, Alexander Mehler, Markus J. Hofmann
Published: 2026-09-09
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2609.10155v1

We approach a cognitive simulation perspective on episodic and semantic memory in multiple-choice question answering by incorporating text from individual text corpora (ITC) into retrieval-augmented generation and DoRA fine-tuning. We web-crawl the search histories of 515 participants who answered 36 multiple-choice knowledge items and analyze a stratified subsample of 150 participants. For each participant, one DoRA adapter consolidates their ITC into a small language model (SLM) whose baseline correctness falls below the participants' lowest quartile. The adapter measurably writes the ITC into the weights: it fits its own participant's held-out text better than other participants' texts (dz =1.27), an individuality effect that increases with ITC size in rank order. On the generalized knowledge test, however, the adapter adds knowledge rather than alignment with the individual: log-loss match improves, whereas match accuracy under a bias-corrected PMI readout does not, and retrieval adds nothing on top. Our results demonstrate that ITCs can be consolidated into the weights of SLMs, an encouraging basis for individualized tutoring agents, and we discuss how to move from there toward a realistic simulation of episodic and semantic memory at the individual level.

---

### CompassOPD: Cross-Family On-Policy Distillation via Within-Family Likelihood Shifts

Authors: Naibin Gu, Qingyi Si, Chenxu Yang, Chuanyu Qin, Junhao Zhou, Peng Fu, Zheng Lin, Weiping Wang
Published: 2026-09-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.10154v1

On-policy distillation (OPD) provides dense token-level supervision on student-generated trajectories. Although OPD performs strongly when teacher and student belong to the same model family, we find that its effectiveness degrades in cross-family settings even after tokenizer alignment, with substantially stronger external teachers offering little additional improvement. To understand this disconnect, we decompose the cross-family OPD signal into two components: an offset between a low-capability teacher-family reference and the student, and the within-family log-likelihood shift from that reference to the strong teacher. Standard OPD transfers both components together, allowing the offset to dominate the update direction and obscure the changes associated with teacher capability improvements. We propose CompassOPD, which removes this offset and transfers the within-family shift, while a frozen student reference anchors updates to the student's initial policy. Thus, both teacher-side and student-side changes are measured within their respective model families. Experiments across three student families and multiple teacher families show that CompassOPD consistently outperforms standard cross-family OPD, improving average reasoning accuracy by up to 5.50 points. For an MoE teacher, we further construct the reference directly from the teacher checkpoint by reducing expert activation, eliminating the need for a separate reference checkpoint while retaining a 3.43-point gain over OPD.

---

### YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models

Authors: Mahmoud Reda, Salam Khalifa, Reham Marzouk, Nizar Habash
Published: 2026-09-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.10153v1

Arabic morphology remains challenging for large language models, since fluent generation does not guarantee accurate morphosyntactic control. Existing Arabic evaluations mainly target downstream tasks and do not directly test controlled morphological generation from explicit lexical and feature-based input. We introduce YallaMorph, a large-scale benchmark for Arabic morphological generation covering verbs, nouns, adjectives, their cliticized forms, and invalid configurations. We evaluate multilingual and Arabic-oriented LLMs under diacritized and undiacritized settings over 600K benchmark entries. Results show that Arabic morphological generation remains difficult, especially for cliticized, unseen, and morphologically rare forms.

---

### Kernel-Managed Shared Memory for System-Wide Personalization

Authors: Ryan Lum, Yongfeng Zhang
Published: 2026-09-09
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2609.10144v1

AI systems become more useful when they can adapt to the people using them, but in multi-agent systems, useful context learned by one agent often remains unavailable to others. We present kernel-managed shared memory, a system-level abstraction in which specialized agents write structured, tagged memories while the agent-system kernel, not individual agents, governs retrieval, privacy enforcement, and prompt injection. We implement and evaluate this design on AIOS and compare it against three alternatives across three assistant models (GPT-4o, Llama-3.1:8B, Qwen-2.5:7B) and 1,800 total trials. Against an unmanaged external memory backend (Mem0) using identical underlying storage, kernel-managed retrieval and injection improve personalization scores by 2.4-4.0 points on a 5-point scale (e.g., 1.05 to 4.69 profile usage on GPT-4o), with every comparison significant at p < 10^-18. Against standard retrieval-augmented injection, gains are similarly large and consistent across all three models. Against full, unfiltered context concatenation, a soft ceiling on available context rather than on response quality, kernel-managed injection statistically matches performance on two of three models and shows a small, model-specific deficit on the third, while using substantially shorter prompts: end-to-end latency is 15-61% lower across all three models, with corresponding reductions in per-call token usage and inference cost. These results indicate that centralizing memory management in the agent-system kernel, rather than leaving retrieval and privacy enforcement to individual agents, delivers most of the personalization benefit of unconstrained context at a fraction of its cost.

---

### Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning

Authors: Jing Guan, Yachao Yang, Zhaoliang Liu, Yuyao Zhang, Fanyu Meng, Junlan Feng
Published: 2026-09-09
Categories: cs.CL, cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2609.10142v1

Large language models remain fragile against malicious fine-tuning, motivating training-time defenses against harmful persona drift. Preventative Steering injects undesirable-trait persona vectors during fine-tuning and removes them at evaluation time, yet the mechanism behind its lasting protection remains unclear. Analyzing its temporal optimization dynamics, we find that the defense emerges from an early compensatory adaptation phase followed by a steady-state phase where the corrective signal decays; in parameter space, attention output projections emerge as the dominant residual-write route for defensive updates. Through Intervention Delta Preservation (IDP) and IDP Continuation experiments, we further show that preserving or reinjecting the weight offset fails to maintain protection, indicating that preventative steering relies on active adaptation rather than a static defense. Motivated by this finding, we propose Progressive Intensity Scheduling (PIS), which starts with a moderate injection strength and increases it after static-strength alignment begins to decay. Across the evaluated Qwen2.5 and Gemma-3 models, PIS improves safety robustness over static-strength steering while reducing harmful trait expression.

---

### The Sample Complexity of Quantum Entanglement Allocation

Authors: Nathan Roll
Published: 2026-09-09
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2609.10141v1

How many past requests are needed to decide which qubits should share entanglement? We show that the answer depends on the allocation choices created by the queries: a larger memory can require no more data. The memory stores a classical bit and answers requests through a fixed detector that preserves coherence within each measured sector. For independent commuting $X$- and $Z$-type Pauli queries, we characterize the full attainable prediction-contrast region and construct encodings that preserve the bit at every nonzero vertex. With sharp reports, a $d$-qubit path and groups of at most $k$ qubits have minimax excess error after $m$ requests proportional to $k^{-1}\min\{1,\sqrt{d\log(k+1)/m}\}$, uniformly for $2\leq k<d$. Connected biclique regions can grow without increasing sample demand when depth, region count and connections per region stay bounded. Preparation noise introduces a separate calibration requirement. We derive an exact tradeoff with extra fresh detector calls and transfer the learning law to structured transaction co-location. Population-risk experiments test the statistical predictions. We also compare encodings on a native 15-qubit device and learned partitions on public purchase baskets. The full chain wins on the device; frequency grouping outperforms basket search in the largest-capacity retail setting.

---

### TransGaze-Object: Transformer Based Driver Gaze Object Prediction Framework in Real Driving

Authors: Pavan Kumar Sharma, Ayush Pande, Pranamesh Chakraborty
Published: 2026-09-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.10139v1

Driver gaze provides information regarding driver visual attention and situational awareness to the surrounding traffic. Existing driver gaze estimation studies represent gaze in terms of gaze zone or gaze vector/point-of-gaze (PoG). However, object-level gaze information provides a more semantically meaningful representation of visual attention by identifying attended objects, such as vehicles, pedestrians, or traffic signals. In this study, we propose an end-to-end driver gaze object prediction framework, TransGaze-Object, Transformer-based Gaze Object prediction model. The proposed framework first extracts facial features, including face and iris-weighted eye features, along with trafficobject spatial features. A transformer based cross-attention mechanism is then used to compute similarity scores and attention weights for predicting the drivers gaze object. To train this model, we propose a benchmark driver gaze dataset, Urban Driving-Face Scene Gaze (UD-FSG), comprising synchronized driver-face and traffic-scene images, scene objects bounding boxes, and gaze labels in terms of 2D gaze coordinate and gaze object. The TransGaze-Object model achieves an overall accuracy of 60% for gaze-object prediction, compared to 51% accuracy obtained from associating the estimated Point-of-Gaze to traffic objects. The error analysis reveals that TransGaze-Object reduces confusion between traffic objects (predicted) and the background (ground-truth), achieving an error rate of 11.68%, a 49.7% relative reduction compared with 23.21% error obtained from PoG-based gaze-object association. Overall, the results demonstrate the effectiveness of directly predicting gaze objects from driver-face and traffic-scene information, rather than estimating an intermediate Point-of-Gaze and subsequently associating it with traffic objects.

---

### Agent-Based ML-LLM Fusion with Self-Optimizing Prompts for Plateau Weather Alerts

Authors: Shuai Yan, Yang Xu, Shan He
Published: 2026-09-09
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2609.10135v1

To address insufficient contextualization, weak generalization, and poor scenario adaptation in tourism meteorological services, we propose SmartWeatherAgent--a unified three-stage architecture integrating intent recognition, hazard prediction, and reasoning-enhanced generation. The system fuses rule-based methods with large language models to parse queries at multiple granularities and employs a LightGBM model enriched with highland-specific features (e.g., wind speed abruptness rate), achieving an F1-Macro score of 0.605 with 1.60 ms latency on high-wind, precipitation, and low-temperature events. A 12-round micro-step prompt self-optimization loop boosts the composite warning quality score S_final from 4.2 (B01) to 8.9 (B12, +112%). Key improvements include a sharp rise in B08 from data source citation (6.5 -> 8.5), sustained high performance in B10 via physical mechanism explanation, and a peak scientific rigor score of 9.2 in B12 through explicit uncertainty statements. The system autonomously generates structured warnings that integrate causal mechanisms, spatiotemporal evolution, quantitative evidence, regulatory references, and confidence statements--enhancing professional depth, logical rigor, and scientific soundness, and advancing meteorological services toward proactive perception, explainable decision-making, and intelligent agency.

---