# Research Papers — 2026-09 · bundle page 197 of 266 > Full-text markdown of papers #9801–9850 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/197 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/196.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/198.md) ### Target-Checked Reliability Score Refinement for Video Question Answering Authors: Guoxiang Ren, Rohitash Chandra Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.13288v1 Video-language models can answer multiple-choice questions with high confidence yet be wrong. We study whether answer-level reliability scores can be improved under target shift without retraining the models or changing their answers. We collect option-probability lists from three fixed video-language models under four deterministic video samplings and represent cross-view changes and cross-model agreement as a response graph. Using a labeled target pilot, we compare the original score, defined as the probability assigned to the chosen answer, with a histogram-based gradient-boosting (HGB) score trained on the development datasets and a regularized logistic-regression score trained on the target pilot. A candidate replaces the original score only when repeated video-level checks indicate a positive, stable improvement. We develop this rule on public VideoQA benchmarks and Video Hallucination Diagnosis (VHD), a controlled diagnostic dataset for shared high-confidence errors. Ranking quality is measured by the area under the risk-coverage curve (AURC), where lower is better. On a held-out 963-question HERBench split, the method reduces mean AURC across the three models by 16.64% (95% confidence interval (CI), 12.12 to 22.61%); the smallest model-level gain is 11.39%. On a separate held-out 911-question Perception Test split, the mean reduction is 18.87% (95% CI, 15.43 to 22.14%). For InternVL3.5, the target check retains the original scores. Using the same outputs, the method outperforms seven training-free baselines in mean AURC on both datasets. It also improves AUROC, reduces calibration error, and lowers the error rate at 50% coverage by 6.50 and 6.58 percentage points. --- ### LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents Authors: Zhangxuan Gu, Haoxing Chen, Qi Qin, Yi Xin, Kai Gan, Lin Liu, Long Cui, Xiaomei Wang, Beitong Zhou, Yunzhu Zhang, Zhengwen Zeng, Changlong Gao et al. Published: 2026-09-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.13287v1 Diffusion large language models (dLLMs) achieve high decoding efficiency through block-parallel, arbitrary-order generation, making them attractive for latency-sensitive applications. GUI agents represent a natural testbed for this paradigm, as they must repeatedly perceive screen states and emit structured, spatially grounded actions in real time. However, whether dLLMs can be extended into capable multimodal GUI agents while preserving their parallel decoding advantage remains an open question. We present LLaDA-UI, a 16.7B-parameter MoE-based, block-wise diffusion vision-language GUI agent. LLaDA-UI follows a two-stage training pipeline: general multimodal pre-training aligns a native-resolution vision encoder with the LLaDA2.0-mini-base diffusion language backbone, followed by GUI-agent supervised fine-tuning on diverse mobile, desktop, web, and grounding data. Across widely adopted grounding benchmarks and navigation benchmarks spanning multiple platforms, LLaDA-UI substantially outperforms Qwen2.5-VL-7B and surpasses Qwen3-VL-8B on four of six reported GUI benchmarks. These results establish block-wise diffusion as a practical generative paradigm for multimodal GUI agents. --- ### Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale Authors: Vaibhav Singh, Pierre-André Noël, Torsten Scholak, Eugene Belilovsky, Oleksiy Ostapenko Published: 2026-09-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.11998v1 Diffusion language models decode tokens in parallel, but their bidirectional denoiser rules out the naive key--value (KV) cache behind fast autoregressive inference. Block diffusion restores caching by decoding block-by-block, and the block caches deployed on it so far are tied to attention: O(L)in memory and, if used as training-free retrofits, only an approximation of the model's computation. Both constraints can be overcome: sequence mixers that summarize finalized blocks into a reusable state support block caching, and the corresponding block-causal training objective makes the cache exact. We study this recipe at scale, pretraining three 3B block-diffusion denoisers (attention, mamba, and hybrid) on 300B tokens under one single-frontier objective and decoding all three through a single cached interface. Only the state-space cache is O(1) in sequence length: its memory and per-step latency stay constant at any context length, while an attention cache remains O(L). At 256k tokens (where attention has grown to 82GB and 29 ms/step), the Mamba cache delivers 4.3x lower latency, 11x less memory, and 2.6x higher single-stream throughput; and because that footprint is constant it scales with batch as well, reaching 14x the aggregate throughput, where attention cannot run beyond a single stream. The same linear-state bias lets the Mamba and hybrid backbones keep retrieving out to 8-16x their training length, whereas attention's retrieval collapses at 2x, at no measured quality cost. --- ### DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning Authors: Wenrui Xu, Anas Enanaa, Keshab K. Parhi Published: 2026-09-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.11997v1 Learning robust representations for time-series signals under noise and distribution shifts remains challenging, especially in clinical applications such as electroencephalogram (EEG) and electrocardiogram (ECG) analysis. We propose Diffusion-Conditioned Representation Alignment (DCRA), a training framework that repurposes the forward diffusion process as a structured corruption scheduler for representation learning. Different from conventional augmentation and consistency-based methods that rely on independently sampled perturbations, DCRA introduces a structured corruption trajectory via the diffusion forward process, which enables continuous and controlled representation evolution across noise levels. We introduce a feature-level consistency objective that aligns representations across noise levels while preserving class-discriminative structure. This mechanism promotes structure-preserving consistency, which enables smooth and semantically coherent feature trajectories in latent space. The proposed framework is encoder-agnostic and can be integrated with state space models and Transformer architectures. The seizure detection experiments on the CHB-MIT EEG dataset show that DCRA consistently improves performance under multiple noise conditions and achieves higher sensitivity at low false-positive rates. Analysis reveals that DCRA produces more balanced and structured representations compared to baseline and diffusion-only models. These findings highlight the benefit of combining structured corruption with representation alignment for robust time-series learning. --- ### Explainable Prediction from Mobile Sensing Data through LLM-guided Concept Integration Authors: Yuning Wang, Iman Azimi, Amir M. Rahmani, Pasi Liljeberg Published: 2026-09-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.11995v1 Mobile sensing enables longitudinal monitoring of behavioral and physiological patterns in everyday settings. However, accurate prediction remains challenging in small-cohort health-sensing studies, where task-specific outcome supervision is limited relative to heterogeneous sensing data. Interpretability is also important, as model outputs should reflect meaningful behavioral and physiological patterns rather than predictive scores alone. We develop a Concept-Integrated Transformer (CIT) with LLM-guided concept supervision for explainable prediction from mobile sensing data. CIT uses a pretrained large language model to generate baseline-aware concept abnormality targets with confidence weights without manual concept annotation. Across two longitudinal datasets, CIT achieves the highest F1 score on AFFECT (0.756) and ties for the highest on a PHQ-9 dataset (0.765). The learned concept scores also reveal interpretable behavioral and physiological patterns; in AFFECT, sleep quantity and quality show the clearest difference between high and low negative affect groups. These findings support LLM-guided concept integration for accurate and interpretable prediction in small-cohort mobile sensing studies. --- ### FINESSE: An Agent-Based Simulator and Benchmark Dataset for Multimodal Financial Event Sequences Authors: Tyler Farnan, Benjamin Eng, Adam Abate, Xirui Hou, Rizal Fathony, Nam H. Nguyen, Senthil Kumar Published: 2026-09-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.11993v1 Machine learning research in financial services is limited by the scarcity of representative open-source datasets. Existing resources are often narrowly focused on a single modality or task and fail to reflect the structured, multimodal, and dynamic nature inherent to many problems in financial services. In this paper, we introduce FINESSE, a Financial Event Sequence Simulation Environment, an agent-based simulation framework for generating synthetic, structured datasets composed of multiple interdependent event streams. Each stream corresponds to a distinct financial behavior such as transactions, payments, account status changes, and policy interventions, each with unique action spaces, schemas and variable types. These streams are coupled through agents' latent evolving states, enabling the simulation of temporally rich interactions. We also introduce FINESSE-Bench, a benchmark dataset generated by the simulator, supporting four representative tasks: balance forecasting, transaction fraud detection, missed payment prediction, and next event prediction. We report baseline results using methods from time series forecasting, event sequence modeling, temporal graphs, and temporal point processes. We release the FINESSE framework, including the simulator and dataset to accelerate research on structured, multimodal event sequence modeling challenges in financial services. --- ### SearchAtlas: Analyzing Agentic Search Strategies via Evidential Query Graphs Authors: Jiacheng Sang, Mengyuan Li, Sanxing Chen, Yukun Huang, Yu Feng, Bhuwan Dhingra Published: 2026-09-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.10901v1 LLM search agents are often evaluated on final-answer accuracy, overlooking the process. Analyzing a search strategy requires understanding how credible evidence is retrieved to address question constraints. This valuable information is buried in raw search trajectories that are long and difficult to parse. We introduce SearchAtlas, a framework that converts search trajectories into structured graphs whose edges represent how evidence is propagated across the reasoning trace, from the query that retrieves it to the final answer. Our automated parsing pipeline achieves a mean edge F1 of 86.0% against human-annotated graphs and remains consistent across repeated runs. We analyze five search agents on three benchmarks, revealing systematic differences in search scale and evidence aggregation. SearchAtlas exposes fragmented answer support, question constraints that do not reach the answer, and unverified parametric knowledge entering the response. These process failures are strongly associated with incorrect answers, even more so than an LLM judge given either the raw trajectory or the ordered query list, suggesting that the constructed graphs provide useful interpretability. Moreover, an audit of cases in which process-diagnostic scores disagree with final-answer correctness shows that they capture information not reducible to answer accuracy. --- ### Symmetry-aware super-resolution of crystal orientation maps via invariant latent-space learning Authors: Umang Garg, Warren Zamudio, McLean P. Echlin, Samantha H. Daly, Tresa M. Pollock, B. S. Manjunath Published: 2026-09-09 Categories: cs.CV, cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2609.10898v1 Crystal-orientation maps are physical fields defined only up to crystal symmetry; electron backscatter diffraction (EBSD) resolves them experimentally, but acquisition-time constraints limit spatial resolution. Unlike conventional images, EBSD data lie on the quotient space $\mathrm{SO}(3)/G$, where $G$ is the crystal-symmetry group. Standard Euclidean interpolation can therefore mix symmetry-equivalent representations and blur grain boundaries. We introduce the Symmetry-Group-Aware Super-Resolution Attention Network (SG-SRAN), which incorporates crystal symmetry and boundary preservation by design. A frozen, locally isometric encoder maps equivalent orientations to a common latent representation in which Euclidean distance approximates misorientation. Super-resolution is performed in this space, with each high-resolution token restricted to a feature-consistent local support to prevent cross-boundary mixing. A dictionary-based decoder then recovers valid orientations. Across FCC and HCP benchmarks, SG-SRAN matches 15-16 million parameter backbones using only 27-49k trainable parameters, while achieving the lowest p68 errors, highest inverse-pole-figure fidelity, and zero-shot transfer to unseen alloys. --- ### LLM-Anchored Paralinguistic Enrichment for Alzheimer's Disease Detection Authors: Xiao Wei, Yuqin Lin, Yaru Cao, Jinyu Li, Bin Wen, Kai Li, Yueying Chen, Longbiao Wang, Jianwu Dang Published: 2026-09-09 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2609.10896v2 Speech-based automatic detection of Alzheimer's disease (AD) provides a non-invasive and scalable approach to early cognitive screening. AD affects both lexical-semantic organization and speech production, including atypical pauses and word elongations. However, existing methods have yet to fully integrate these paralinguistic cues with linguistic content. We propose LLM-Anchored Paralinguistic Enrichment (LAPE), which enriches LLM-derived linguistic representations with paralinguistic cues through three coordinated innovations. The first is prosodic event textualization, which enables the LLM to model pauses and elongations jointly with lexical content by encoding them as explicit markers with bounded duration-aware repetition. The second is lexico-prosodic unitization and chunking, which preserves event identity and magnitude in both modalities by pooling only consecutive word units. The third is text-anchored paralinguistic fusion, which integrates local and utterance-level speech features by using NormGate to normalize and dynamically scale them relative to text. We evaluate LAPE on ADReSS and ADReSSo using participant-level cross-validation and leave-one-subject-out evaluation. LAPE achieves state-of-the-art performance across all four primary settings. Code will be released upon acceptance. --- ### ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs Authors: Yizhan Li, Jianxin You, Mengyang Xiong, Yinhuan Chen, Zicheng Zhao, Dekun Wu, Dongqing Zhang, Bang Liu Published: 2026-09-09 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.10895v1 Reacting to sudden physical hazards (catching a slipping plate, dodging a falling knife) is both a meaningful test of embodied intelligence and a hard requirement for deploying multimodal large language models (MLLMs) as the decision coreof household robots. Existing evaluations, however, probe intuitive physics passively through question answering over videos, or target deliberate, long-horizon tasks such as navigation and rearrangement; none measure whether a model can turn physical understanding into immediate, safety-critical action. We introduce ReactHuman, the first physics-grounded benchmark for human-like reactive decision-making, in which the evaluated MLLM acts as the brain of a simulated humanoid facing sudden household hazards; it spans 17 event families and over 1,000 bit-for-bit reproducible scenes with exact, annotation-free ground truth derived from 240 Hz rigid-body simulation, including adversarial objects whose appearance contradicts their physics (a foam anvil, a steel apple). We further design a five-metric suite that scores each reaction along three axes: reasonable, safe, and physically grounded. We physically execute every committed plan so that decisions have observable consequences. With this harness we evaluate seven representative MLLMs. Results show that reactive safety is far from solved: models mishandle roughly one hazard in three, act from fixed dispositions rather than the observed scene, trust appearance over motion, and miss interception points at meter scale even when the chosen action is correct; none of these failures shrink with model scale. ReactHuman thus offers both a fine-grained diagnosis and a scalable training signal toward physically grounded, safety-aware embodied agents. The benchmark can be found here: https://huggingface.co/datasets/Alan123/reacthuman-benchmark-scaled --- ### Does Linguistic Structure Enrichment Enhance Coherence Assessment? Not With Current Architectures Authors: Victor Mazzotti, Luiz Pereira, Marina Bitencourt dos Santos, Helena Maia, Carlos Caetano, Nádia Felix, Sandra Avila Published: 2026-09-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.10893v1 Recent advances in large language models have transformed human-computer interaction. Despite their fluency, these models often produce texts that are grammatically correct but semantically incoherent, containing contradictions or disruptions in logical flow. This work investigates whether enriching text with syntactic and rhetorical information can improve incoherence prediction. Our experiments and analysis show that plain texts achieved higher accuracy because the added information was structurally and syntactically incompatible with the language model's architecture. Additionally, to demonstrate the practical importance of coherence assessment, we performed zero-shot experiments on a Brazilian disinformation dataset, suggesting that textual coherence can serve as a proxy for detecting misleading content. Code and models are available at https://github.com/ittozzamV/cohereclassifier. --- ### DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents Authors: Asif Pinjari, Mithun Paul Saint-Germain Published: 2026-09-09 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.10892v1 When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls, a poisoned observation, and a suffix of actions that serve the attacker. An operator needs three facts: where the attack entered, which steps it corrupted, and whether apparent poison was resisted. Existing systems return either a whole-trace verdict or a single unsafe index. We present DriftNet, a dual-head trajectory Transformer that reads a logged tool-call trajectory and answers all three questions in one forward pass: one head classifies the trajectory as compromised or not, and a second assigns every step one of four labels (benign, injection point, hijacked, failed injection). To our knowledge it is the first supervised detector to produce this joint output. A frozen sentence encoder and four identity-free world features embed each step; the trained trunk, under two million parameters and optimized with a class-weighted joint objective over both heads, needs no access to the agent's model. On the task-disjoint split of the AgentDrift benchmark (12,536 trajectories, 71,024 labeled steps), with a 20-configuration sweep bounding hyperparameter sensitivity to 0.011 F1 and the test part evaluated exactly once, DriftNet reaches trajectory-level F1 of 0.983, exact injection-point recovery on 98.7% of attacked trajectories, hijacked-span IoU of 0.979, zero flags on 218 resisted attacks, and 2.9% flags on hard negatives. A surface baseline retrained on the identical split recovers 11.1% of partial hijacks and 17.1% of delayed executions; DriftNet reaches 98.6% and 93.2% while lowering every false-alarm rate. Reading all 26 residual errors shows that most misses trace to trajectories whose labeled injection observation carries no legible instruction, and we report the benchmark's measured world-identity regularity alongside the results. --- ### Relatively Smart II: Tractable or Semi-Supervised Instance-Optimal Learning Authors: Shaddin Dughmi, Alireza F. Pour Published: 2026-09-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.10886v1 We continue the study of relatively smart learning, introduced by Dughmi and Pour (2026), which asks a supervised learner to compete, marginal by marginal, with every distribution-fixed error guarantee soundly certifiable from unlabeled data. They showed that the One-Inclusion Graph (OIG) learner is relatively smart with a quadratic sample-complexity blowup, and that no relatively smart learner can do better, leaving open whether ERM or another natural or tractable learner achieves comparable guarantees. They also left open whether the blowup can be restricted to unlabeled data. Our firs results shows that ERM---and in fact any proper consistent learner---is relatively smart for binary classification in the distribution-free setting. We show that a small certifiable error with $m$ samples implies a similarly small error on the uniform distribution over a random sample of size $O(m^2)$, yielding a cover of size at most $2^{m+1}$ on that sample. This suffices to control the error of proper consistent learners with $O(m^2)$ samples. We then show that semi-supervised relatively smart learning is information-theoretically possible with a quadratic blowup only in unlabeled sample complexity and no blowup in labeled sample complexity. The learner uses a natural generalization of OIG to a leave-most-out transductive problem, where labels of part of a finite pool are revealed and the remaining labels are predicted. Finally, this label efficiency comes at a cost in simplicity and tractability. If the hypothesis class is accessed only through an agnostic ERM oracle, any semi-supervised relatively smart learner with substantially sub-quadratic labeled-sample blowup requires super-polynomially many oracle calls. This holds even when the marginal is given explicitly, and thus also yields an intractability result for distribution-fixed learning that may be of independent interest. --- ### Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble Authors: Jorio Cocola, Lev McKinney, Harry Mayne, Jan Betley, Owain Evans Published: 2026-09-09 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.10883v1 Language models are trained to implement a helpful AI Assistant character (e.g., Claude). We explore how finetuning on synthetic stories affects this character. Does it change the Assistant's behavior in multi-turn conversations with users, a format quite different from the stories? And does the Assistant adopt the behaviors and preferences of human characters? We refer to this adoption as story imprinting. We finetune GPT-4.1 and Kimi-K2.6 on stories in which generally helpful human characters give subtly harmful advice after being insulted. The Assistant adopts the same conditional behavior while otherwise remaining helpful. This occurs even when fewer than 2% of stories depict the behavior. In a separate experiment, the Assistant adopts preferences that are only implicit in the narration. A human character's body language suggests they dislike working on spreadsheets, yet they never say so and continue giving good advice on spreadsheets. After finetuning, the Assistant becomes less likely to choose spreadsheet tasks. Next we ask which characters most influence the Assistant. We find the Assistant adopts behaviors more often from characters that resemble it (e.g., helpful rather than dismissive). We call this the affinity effect. The effect extends to other personas elicited with system prompts: unhelpful personas adopt behaviors from unhelpful characters. We also observe it in finetuned base models. We use the affinity effect to learn how models represent the Assistant. We find the Assistant adopts behaviors more from characters affiliated with elite universities (e.g., Yale) than non-elite ones. This implies the model's internal representation of the Assistant is more similar to humans from elite universities. Overall, the Assistant can be influenced by stories that depict only human characters (no AIs), which may conflict with the Persona Selection Model for the Assistant. --- ### Fractional-order hardware for neuromorphic computing: Is the order really the problem? Authors: Christof Teuscher Published: 2026-09-09 Categories: cs.ET, cs.NE arXiv: https://arxiv.org/abs/2609.10882v1 Does a neuromorphic system need a true power-law memory kernel, and if so, can anyone build one? Neuromorphic systems process signals spanning many timescales at once, from milliseconds to tens of seconds. Integer-order circuits buy each additional timescale with an additional state variable. Fractional-order dynamics offer a different bargain: one operator whose power-law kernel carries a continuum of timescales, tuned by one parameter, the order alpha. A fractional derivative is non-local, so evaluating it costs storage and arithmetic that grow with the retained history, where an integer-order derivative costs a constant. This review organizes the hardware literature around that cost. We derive the retained history needed to hold the truncation error below a tolerance epsilon, show that it scales as epsilon^(-1/alpha), and set beside it a second and independent limit on the direct form: in fixed point the weights themselves underflow, so word length caps the usable history however long the buffer is. The two limits move at very different rates with the order, and where they cross decides whether a word length can serve an order at all. We use both to sort published hardware into three strategies, note a fourth the numerical literature has developed and this hardware has not, and survey digital, analog and device work. Along the way we ask whether the field is worried about the right obstacle. It is not. Fabricated constant-phase devices already span the orders two groups identify as task-optimal, so the order gap has largely closed, leaving a residual gap near 0.1 and at the lower order describing cortical adaptation. What remains is a frequency-band gap of about three decades at the low end. That corner is not empty, since double-layer electrodes work there, but every device in it is discrete, and no integrable thin-film element has been characterized there. --- ### Learning Orthogonal Multi-Index Models Beyond Small Initialization: Incremental Learning, Competitive Dynamics and Symmetry Authors: Mo Zhou, Weihang Xu, Simon S. Du, Maryam Fazel Published: 2026-09-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.10879v1 Recent work has identified incremental learning in shallow networks trained on single-index and multi-index models. However, existing analyses often rely on simplifying settings, such as small initialization, correlation loss, or layer-wise training. These choices reduce neuron interactions and leave some feature learning dynamics under standard initialization unexplored. We study training dynamics for polynomial-width two-layer networks learning orthogonal multi-index targets under standard initialization using polynomially many samples. We first prove that incremental learning still occurs: the loss decreases sequentially according to the Hermite expansion of the target, with lower-order components learned before higher-order components recover the individual target directions. In this standard initialization regime, training also shows a competitive reallocation of parameter mass: after the total mass fits the target mean and stabilizes, mass shifts into the target subspace and then concentrates on aligned neurons. Our theoretical analysis uses slightly modified gradient flow, while vanilla gradient descent empirically exhibits the same qualitative dynamics. Technically, we introduce a symmetry-based finite-width approximation via symmetrized networks, rather than comparing directly with an infinite-width limit. This yields better control of approximation errors and may be of independent interest. --- ### When Validation Stops Learning: Auditing Update Admission for Continual Embodied Agents Authors: Qinzhen Ma, Ruihai Wu Published: 2026-09-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.10873v1 Independent evaluation can reject harmful policy updates yet also prevent useful continual learning. We argue that update admission must be assessed through both error control and retained learning opportunities at a stated interaction budget. We identify a concrete failure: a range-based confidence gate cannot certify unchanged old-task behavior within otherwise substantial budgets. A standard paired-binomial construction reduces this burden when outcome disagreements are rare. We also specify certified historical-reference promotion and a round-level missed-opportunity metric. In a constructed one-step pushing diagnostic with 32 seeds, fresh paired checks admit 31.6% of a common update stream at 2,000 episodes per stage, versus zero for the range-based gate; unconditional replay nevertheless learns better in closed-loop runs. A separate learned-dynamics stress test distinguishes model bias from feedback-selection error. The contribution is an admission-audit protocol with analytical and synthetic evidence; physical-robot and VLA validation remain open. --- ### Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbations Authors: Tong Li, Saunak Kumar Panda, Yisha Xiang Published: 2026-09-09 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.10866v1 Reinforcement learning (RL) agents deployed in real-world environments are often vulnerable to adversarial perturbations in state observations, creating risks in safety-critical applications. Certification methods can improve robustness against adversarial perturbations by providing lower bounds on expected cumulative rewards. Existing certification methods, however, mainly focus on risk-neutral objectives. In this paper, we extend certification methods to risk-sensitive objectives by establishing lower bounds on the exponential utility of cumulative rewards under $l_{p}$-norm-bounded state adversarial perturbations ($1\leq p <\infty$). By introducing a $φ$-divergence relaxation of the perturbation set, we formulate the risk-sensitive certification problem as a convex optimization and derive its dual to obtain a tractable approximation of the certified lower bound. We further propose an empirical method that improves certified lower bounds by selecting the training risk-aversion parameter $β$ independently of the risk level used during evaluation. Experiments on both OpenAI Gym environments and a machine replacement problem show that, compared to risk-neutral training, risk-averse training generally yields policies with higher certified lower bounds, particularly under larger perturbation budgets. Moreover, under both risk-neutral and risk-averse evaluation settings, increasing risk aversion during training leads to non-monotonic certification performance, where certified lower bounds initially improve but eventually decrease due to overly conservative policies. --- ### Flow Duality and Source Geometry for Categorical Generation Authors: Etrit Haxholli Published: 2026-09-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.10863v2 Continuous and discrete flow matching are usually treated as separate constructions. This paper identifies a duality between them: projecting continuous convex-interpolant flows with one-hot targets through a position-wise argmax yields discrete convex-interpolant flows. The result requires source laws with appropriate coordinate symmetry and regularity, and it makes the continuous source distribution an explicit design choice for categorical generation. We derive the induced discrete interpolation behavior for Gaussian, bounded-uniform, and centered negative-exponential sources, showing that different source geometries lead to qualitatively different transition timing and vocabulary-size dependence. Small visual diagnostics and a short language-modeling pilot suggest that these source-design effects can also appear in learned transports and early generative quality. --- ### Project Qualia: Recovering Experiential Music Structure from Session Co-occurrence Data Authors: Nizam Mohammed, Abu B. S. Rahman, Dimuthu D. K. Arachchige Published: 2026-09-09 Categories: cs.SD, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2609.10862v1 This report presents results from Project Qualia, an ongoing effort to determine whether experiential similarity between songs, a structure not captured by genre or metadata taxonomies, can be recovered from real listening behavior. We constructed a large-scale dataset of listening sessions, comprising 1.29 billion scrobbles collected from 9,396 users via the Last.fm API and reduced through a preprocessing pipeline to 531.6 million training scrobbles across 28.6 million sessions. On this corpus, we trained a skip-gram Word2Vec model (Song2Vec), treating each session as a sentence and each track as a token. As anticipated, the resulting embedding space was dominated by artist identity, a consequence of single-artist runs within sessions. To test for a subtler, artist-independent signal, we developed an artist-residual procedure: subtracting each artist's centroid from its tracks' embeddings and evaluating whether the remainder retained structure. Mean cross-artist cosine similarity fell from 0.2487 in raw embedding space to 0.0005 in residual space, yet 4,577 cross-artist track pairs retained cosine similarity $\ge 0.70$ in residual space, forming coherent genre- and era-based clusters, including trip-hop, 1990s grunge, 2020 mainstream pop, and cross-composer classical piano pairs at cosine similarity up to 0.95. These results confirm that the training data contains experiential structure independent of artist identity, establishing an empirical basis for an architecture designed to learn this experiential layer directly. --- ### Evaluation of Vision-Language Models Across Diverse Coastal Environments Authors: Seth Knoop, Chad R. Samuelson, Gabriel R. Slade, Brady Moon, Joshua G. Mangelson Published: 2026-09-09 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.10855v1 Vision-language models (VLMs) enable robotic per- ception by associating visual observations with natural-language concepts. Yet their performance in coastal environments remains largely unexplored. We introduce a densely labeled coastal dataset containing more than 1,000 images collected across seven missions in three regions of Oahu, Hawaii, with 18 semantic classes and over 7,400 annotated instances. We evaluate seven modern VLMs through three complementary experiments mea- suring text-to-mask, mask-to-mask, and mask-to-text alignment. Broad landscape classes are generally recognized more accurately than conventional object and coastal classes, with coastal con- cepts presenting the greatest challenge. However, comparisons of shared conventional classes across coastal and terrestrial datasets reveal no consistent performance difference attributable solely to environmental context. Mask-to-mask matching also remains similar across conventional and coastal classes, while alternative textual labels substantially improve recognition of several coastal concepts. These results suggest that lower performance on coastal classes (at least on the objects/query categories evaluated) is heavily influenced by segmentation and linguistic representation. --- ### No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers Authors: Zehua Zhang, Jie Hu, Pratham Hegde, Aditya Maheshbhai Gabani, Souradip Nath, Yibo Liu, Siyu Liu, Hongkai Chen, Hulin Wang, Zhuoer Lyu, Chang Zhu, Divij Handa et al. Published: 2026-09-09 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.10854v2 Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts auditing closed-source, remotely hosted, critical in situ systems, or commercially gated software. Therefore, we propose a new paradigm of no-box vulnerability analysis in which neither access nor runtime interaction is available, and only functionality metadata is available. Such metadata defines the intended behavior of the system, including its inputs, outputs, and side effects, while constraining the space of implementations consistent with that behavior. We propose hypothesizing about vulnerabilities that exist across all possible implementations of a given system metadata, without observing or interacting with the target system. An analyst can later validate these hypotheses when additional access is available. We showcase the feasibility of no-box vulnerability analysis through implementing a prototype called MCPSEC, which audits Model Context Protocol (MCP) servers for indirect prompt injection vulnerabilities using only the tool metadata exposed at server registration time. We evaluate MCPSEC on 20 widely deployed MCP servers comprising 177 tools, among which human evaluators confirm 95 vulnerable tools. MCPSEC identified 143 tools as vulnerable, and for each vulnerable tool, it produced a hypothesized vulnerability along with exploitation technique. Using metadata alone, MCPSEC predicted 94 (98.9% recall) real verified vulnerabilities, compared against an LLM baseline with 80 (84.2% recall). Overall, our results introduce no-box vulnerability analysis as a new analysis paradigm and demonstrate its practical feasibility in realistic systems. --- ### Are We Really Doing Few-Shot Learning? A Critical Examination of Pre-Training Assumptions Authors: Alejandro Galan-Cuenca, Marcelo Saval-Calvo, Antonio Javier Gallego Published: 2026-09-09 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.10851v2 Few-shot learning is commonly evaluated under protocols that pre-train a model on a large auxiliary set whose classes are disjoint from the target episodes yet drawn from the same visual domain. This paper examines whether such protocols truly reflect low-data learning. We systematically compare no pre-training, class-disjoint in-domain pre-training, supervised out-of-domain pre-training, and label-free out-of-domain pre-training across eight datasets, three few-shot architectures, and multiple way-shot settings. Our results show that class disjointness alone is insufficient to remove the influence of target-domain data. In-domain pre-training improves over no pre-training by 33.41 percentage points on average, whereas supervised out-of-domain pre-training yields 23.75 percentage points, revealing a 9.66-point optimistic bias associated with domain overlap. Although out-of-domain pre-training is more realistic in applications where target-domain data are scarce, its effectiveness depends strongly on the compatibility between source and target domains. We further show that labeled source data are not strictly required, with an augmentation-based label-free strategy reaching an average gain of 27.71 percentage points and closely matching supervised out-of-domain pre-training at 27.97 percentage points. Finally, we introduce a descriptor-based source-selection strategy that estimates source-domain suitability before pre-training, reaching a median gap of only 1.37 percentage points to oracle selection. These findings highlight the need to move beyond in-domain pre-training as the default few-shot evaluation protocol, since it can overestimate performance in realistic scenarios where target-domain data are scarce. --- ### scDEFT: A deep learning framework for drug-effect prediction and counterfactual reasoning Authors: Murthy Devarakonda Published: 2026-09-09 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2609.10831v1 Longitudinal single cell atlases now capture matched pre treatment and post treatment states from responders and non responders, presenting an opportunity to mechanistically explain why two patients on the same drug diverge. We introduce scDEFT (single cell Drug EFfect Transducer), which treats a drug as a conditioning operator on cell representations, enabling prediction and explanation. In scDEFT, feature wise linear modulation produces drug conditioned cell latents, learned under abundant per cell supervision and then frozen. Two independent heads aggregate those latents over shared transcriptional neighborhoods to predict drug induced state change and responder status. A backward stage ranks the latent dimensions by how strongly they separate responders from non responders and maps them to genes under a cell composition control. On a harmonized inflammatory bowel disease atlas of 1.16 million cells, three cohorts and two drug classes, scDEFT predicts state change at 45% of the baseline to reproducibility ceiling headroom and stratifies responders before treatment at AUROC 0.70, where standard predictors remain at chance. These predictions and the drivers behind them support target and co target nomination, patient stratification, and counterfactual prediction of unseen drug cohort effects. --- ### Detectable Only Where It Is Confounded: What Verified Duplication Counts Say About Membership Evidence in Language Models Authors: Arman Nik Khah Published: 2026-09-09 Categories: cs.CL, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2609.10830v1 When a language model finds a sentence unusually cheap to predict, it is tempting to conclude that the sentence was in its training data. Almost every published test of that inference has had to guess which sentences were in the training data, the members, and which were not. This paper removes the guessing. Two model families, OLMo-2 and Pythia, publish their pretraining corpora, and a public index over those corpora returns the exact number of times any sentence appeared in each. Those counts make three questions answerable directly. The answers form a pincer, closing from two sides. At the duplication levels ordinary text actually has, five models from 1B to 13B parameters carry at most a faint trace of their own exposure. We measure that trace with a design that reads the same sentence through two models, which cancels fluency and quality by construction, and it comes to a rank correlation near -0.08, where -1 would be a perfect relation and 0 none. Where the trace does become strong, above roughly a thousand copies, the two corpora agree on which sentences those are, because they are the famous ones, so exposure can no longer be told apart from fame. Two further measurements show how apparent membership signal gets manufactured. A common way to build a non-member is to change one word of a member. The model does prefer the original, but the gap is the same whether the original appeared once or a hundred times, so what the model is rewarding is the author's word choice, not memory. Above a thousand copies the gap grows with model size on the twelve sentences we can test there, at the same boundary where the pincer closes. And swapping the controls for sentences that differ from the members in register moves a detector from 0.83 to 0.94 AUC, on a scale where 0.5 is a coin flip and 1.0 is perfect separation. We release the sentence banks, counts, and code. --- ### Processing and classifying bird songs using wavelet techniques and supervised learning Authors: Laura Lucia Dominguez Barrios, Fidel Aniano Causil Barrios, Alex Rodrigo dos Santos Sousa, Mariana Rodrigues Motta Published: 2026-09-09 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2609.10826v2 This study proposes an integrated framework for the processing and classification of invasive bird species vocalizations within natural soundscapes, characterized by high levels of environmental noise. We address the challenge of signal degradation by employing a Bayesian wavelet shrinkage methodology based on the Epanechnikov kernel prior, which offers a closed form decision rule and high computational efficiency for processing large bioacoustic datasets. The methodology was applied to recordings of three species obtained from the iNaturalist platform: Euphonia violacea, Leiothrix lutea, and Passer domesticus. After signal denoising, we extracted a comprehensive set of features, including Mel-Frequency Cepstral Coefficients (MFCCs) and spectral indices such as entropy and zero-crossing rate. Several supervised learning models: Random Forest, Multinomial Logistic Regression and Support Vector Machine (SVM) were evaluated across different feature dimensionalities. Our results demonstrate that the proposed wavelet based preprocessing significantly enhances classification performance, with the SVM model achieving the highest accuracy (up to 0.9398) under a 10-dimensional MFCC configuration. This research provides a robust statistical tool for automated ecological monitoring and the management of biological invasions. --- ### Scale-Aware 3D Deep Learning for Robust Brain Metastasis Detection in Multimodal MRI Authors: Sylvain Jaume, Hongming Wang, Simon K. Warfield Published: 2026-09-09 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.10825v1 Detecting brain metastases in magnetic resonance imaging (MRI) remains challenging because lesions vary widely in size and appearance, with very small metastases occupying only a minute fraction of a three-dimensional input. We investigate whether combining different spatial fields of view (FOVs) improves lesion detection in multimodal MRI and present a scale-aware 3D deep-learning framework. The method uses independently trained $96^3$ and $64^3$ 3D U-Nets whose whole-volume probability maps are combined by weighted late fusion. This design allows us to study the effect of spatial context separately from image resolution and modality choice. On a 97-patient development cohort, cross-FOV fusion improved lesion-level precision and F1 while substantially reducing false positives relative to the individual models. A same-FOV ensemble control showed that these gains were not explained solely by averaging independently trained networks, supporting a contribution from complementary spatial context. An exploratory cross-FOV agreement filter reduced false positives but did not improve overall F1. These results support cross-FOV probability fusion as a simple and computationally practical strategy for improving the precision-false-positive trade-off in 3D brain-metastasis detection. --- ### Studying Without a Syllabus: Task-Agnostic Environment Preprocessing Authors: Vinay Samuel, Varun Ursekar, Vijay S. Kalmath, Apaar Shanker, Veronica Chatrath, Yuan Xue Published: 2026-09-09 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.10824v1 Before an LLM agent tackles tasks in a new environment, it can inspect available corpora and tools and construct reusable resources such as indices, scripts, or procedural guidance. Most automated adaptation methods, however, rely on task examples, trajectories, or evaluation feedback to decide what to build. Existing task-agnostic approaches avoid this supervision but commit in advance to a preparation strategy for a particular type of environment. We study a more open-ended setting: can an agent study an unfamiliar environment without a syllabus, i.e. before test time and without knowledge of the downstream task distribution, and choose how to prepare it? We formalize task-agnostic environment preprocessing, in which a studying system explores an environment under a budget and produces artifacts for a frozen solver. We compare unaided and archive-equipped meta-agents with fixed synthetic-practice and corpus-processing methods across six heterogeneous benchmarks. A meta-agent variant achieves the highest Avg@3 reward on five benchmarks, while fixed corpus processing remains best on the largest corpus benchmark. Larger study budgets do not reliably improve downstream reward. Nevertheless, studied artifacts reduce the test-time sampling needed to reach a given score, demonstrating how reusable preparation can shift computation from repeated test-time attempts to a pre-task study phase. --- ### Tapes Together Strong: The Co-evolution of Computation and Cooperation Authors: Kunal Jha, Francesco Cicala, Blaise Agüera y Arcas, Blake Aaron Richards, Natasha Jaques, Max Kleiman-Weiner, Eyvind Niklasson Published: 2026-09-09 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2609.10817v1 How does cooperation evolve in complex agentic systems? Prior work in evolutionary game theory studies why individuals are incentivized to cooperate by isolating social interactions from the physical costs of behavior, while artificial life models traditionally study emergent self-replication without formalizing the dilemma between acquiring resources and preserving the shared energy needed to reproduce. In contrast, we introduce Autopoietic Game Theory, a computational model where social interactions, replication mechanisms, and their associated computational costs are endogenous and simultaneously co-evolving. We study these dynamics using a computational substrate of randomly initialized programs in Z80 machine code, showing empirically, and motivating with a simplified theoretical model, that embedding a social dilemma directly into the physics of computation can favor the emergence of self-replicating, cooperative strategies. When resources are scarce, our analysis shows that defection can become self-limiting even in well-mixed populations: parasitic stealing destroys shared energy, slows execution, and can prevent reliable replication. Empirically, evolved programs suppress stealing across several Z80 environments, while spatial assortment further supports structural complexity and task performance. We further show that the framework can incorporate exogenous pressures, such as math tasks structured as sequential social dilemmas, when rewards are tied to computation budgets. These results suggest that coupling an agent's capacity for computation to its available energy transforms cooperation into a dominant scaffolding for building sustainable, self-organizing systems. --- ### BodyCam-VQA: Enhanced Body-Worn Camera Video Captioning via Multimodal Reasoning and Probe Question Generation Authors: Karish Gupta, Matthew Alex, Alex Li, Yang Wu, Yun-Wei Chu, Kashif Munir, Xiaotian Zhou, Zhengping Ji, Xiaozhong Liu Published: 2026-09-09 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2609.10815v1 Police body-worn camera (BWC) footage has emerged as a critical aspect of law enforcement that ensures legal transparency, officer accountability, and the protection of civil rights. However, effectively processing this data remains a significant challenge due to its multimodal video format. BWC videos, in many cases, comprise chaotic scenes with low visual quality, rapid movement/interactions, and high-noise audio that make visual understanding a challenge for even SOTA multimodal models. Current Vision-Language Models (VLMs) frequently overlook critical forensic details, such as the presence of valuable evidence or the latent nuances of suspect-officer interactions, which are vital for fair legal outcomes and civilian/officer safety. To address these limitations, we propose an Adaptive Visual Question Answering (VQA) framework engineered for high-stakes law enforcement. Our framework employs a structured reasoning approach to extract fine-grained visual evidence that traditional captioning systems fail to capture. We experiment with multiple question generation models, including foundation models and fine-tuned open-weight models, to observe performance variation among question generation model implementations. Our results demonstrate that this VQA-driven architecture provides a more reliable, objective, and detailed record of enforcement events, ultimately serving as a powerful tool to protect both law enforcement officers and the public through AI-assisted forensic clarity. --- ### Overpainting: Localized Context-aware Diffusion Image Editing Authors: Sam Sartor, Iliyan Georgiev, Michael Fischer, Valentin Deschaintre, Pieter Peers Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10811v1 We present "overpainting", an image editing operation which offers both control over the location of the edit and awareness of the previous content in that location. The overpainted area is given by a trimap, where white-annotated pixels must be edited, gray-annotated pixels may be edited, and black-annotated pixels must not be edited. This enables both precise and loose control, depending on user intent. We implement overpainting by adapting a pretrained image editing diffusion model using a combination of joint attention and low-rank adaption across input images with attention-dropout to balance the information flow between noise, source and mask images. We present a novel, automated, training data generation pipeline that (1) generates a set of candidate image pairs leveraging existing language-based editing models, (2) carefully curates those pairs, and (3) extracts a trimap from each usable pair. We demonstrate the versatility of our overpainting model on a wide range of editing tasks. --- ### Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction Authors: Kateryna Karpo, Artem Chernodub Published: 2026-09-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.10810v1 Minimal-edit Grammatical Error Correction (GEC) is a challenging task for zero- and few-shot prompted Large Language Models (LLMs), which systematically overcorrect and degrade $F_{0.5}$ by rewriting well-formed spans. While fine-tuning provides an effective solution, it imposes substantial infrastructure demands. We introduce a prompt-based approach that closes the gap to fine-tuned models through three advances in GEC prompting methodology. First, we introduce taxonomy-based instructions to enforce minimal-edit constraints with a comprehensive list of grammatical error rules, equipping the LLM with a bounded, metric-aligned scope of correctable edits, which benefits the strongest models while remaining model-dependent overall. Second, we show that batching multiple uncorrected sentences into a single input context acts as a targeted regularizer against overcorrection, systematically reducing the edit rate across diverse LLM families; we hypothesize this arises from attention dilution effect induced by the bounded capacity of self-attention scores. Finally, LLM-assisted Prompt Optimization refines these instructions. Powered by Gemini 3.1-Pro, our prompt achieves $F_{0.5}=78.32$ on the BEA-2019 test set - establishing a new prompt-based SOTA while shrinking the gap to the fine-tuned single-model SOTA (Staruch et al., 2025) to a mere $0.38$ points. Code, prompts, and outputs are publicly available. --- ### TrajFusionNet+: Transformer-Based Prediction of Pedestrian Crossing Intention via Fusion of Trajectory Representations and Scene Graphs Authors: François G. Landry, Moulay A. Akhloufi Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10806v1 The pedestrian crossing intention task involves predicting whether pedestrians are likely to cross the road from the point of view of an autonomous vehicle. We introduce TrajFusionNet+, a novel transformer-based model for pedestrian crossing intention prediction. TrajFusionNet+ combines sequential and visual representations of pedestrian trajectory with a graph-based representation of the scene context in order to predict pedestrian crossing intention. The proposed architecture builds upon our previous model, TrajFusionNet, and comprises three branches: a Sequence Attention Module (SAM), which processes a sequential representation of past and predicted pedestrian trajectories; a Visual Attention Module (VAM), which utilizes a visual representation of the pedestrian trajectories by overlaying observed and predicted bounding boxes onto scene images; and a Graph Attention Module (GAM), which extracts pedestrian-centric graphs from segmented scene images and captures the relational dependencies between pedestrians and traffic elements. TrajFusionNet+ achieves improved state-of-the-art performance on the two most widely used pedestrian crossing intention datasets, PIE and JAAD. Furthermore, we introduce a new evaluation protocol in which models are trained jointly on the PIE and JAAD datasets but evaluated separately on each. Under this setting, TrajFusionNet+ demonstrates superior generalization compared to existing approaches. --- ### How Much Velocity Does Off-Ball Space Value Need? A Broadcast-Viewport Benchmark Authors: Seongjin Choi Published: 2026-09-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.10801v1 Velocity-aware pitch control is standard, but under a broadcast viewport half the players are off screen and on-screen velocities come from a drifting calibration. We ask at which layer of broadcast off-ball analysis velocity changes the answer. Inheriting our off-screen imputation protocol (three Metrica matches, 44 m viewport, block-bootstrap CIs), we score four velocity regimes -- none, viewport-legal observed, true-for-visible, true-for-all -- against a velocity-aware ground truth at three layers: imputation, the control surface, and team verdicts. Velocity is nearly useless for imputation (-0.2 pp against a 12--14 pp velocity-free surface MAE), first-order for the surface (-1.5 to -1.8 pp, 11--15% of that MAE), and ten times smaller for verdicts (-0.12 to -0.19 pp). The velocity that matters is the visible channel: perfect occluded-player velocity adds 2--6% of the visible gain, and no last-seen decay policy we tested exceeds that. Omitting velocity blurs the surface (per-frame |e| 2.2--2.6 pp) with small time-averaged bias (per cell <=0.4 pp), whereas imputation error is a structured bias against the defending team's deep zone (5--9 pp). At a fixed velocity window, a noise ladder of eleven jitter settings, including sigma_v-matched pairs, is ordered to first order by one velocity-noise axis sigma_v with break-even ~1 m/s; eleven SoccerNet-GSR clips from one match through our pipeline measure sigma_v=1.65 m/s yet recover 24--36% of the benefit: 43% of the variance is frame-common, which the surface tolerates, and the residual is heavy-tailed and clustered, which Gaussian controls matched on component RMS do not reproduce (+0.03 vs. +0.36). The share of velocity-free error that velocity removes grows with viewport width (7% at 36 m, 21% at 60 m): fix imputation on tight shots, velocity on wide ones. Code and logs are released. --- ### RiVaT-Fuse: Reliability-Calibrated Variational Tensor Fusion for Multimodal Prediction under Modality Uncertainty Authors: Yingfan Xu, Tieming Liu, Ye Liang, Taiping Liu Published: 2026-09-09 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.10798v1 Image-metadata prediction requires fusing heterogeneous evidence whose reliability can vary across samples and latent factors. Existing representation-level fusion methods typically choose an aggregation architecture, such as concatenation, gating, conditional modulation, or attention, without explicitly defining what the fused representation should mean under modality uncertainty. We propose RiVaT-Fuse, a reliability-calibrated variational tensor fusion framework that defines fusion as sample-wise latent-state estimation. Rather than producing a fused vector by direct aggregation, RiVaT-Fuse estimates a consensus latent state through a variational objective that balances image evidence, metadata evidence, structured cross-modal interaction, and stability. The resulting framework replaces scalar modality confidence with matrix-valued trust geometry, decomposes interaction into additive, multiplicative, and relational components, and couples the latent state with conditional robustness and structured multi-task prediction. We provide well-posedness and stability interpretations of the latent solve and instantiate the framework with efficient low-rank-plus-diagonal trust operators. On an image-level image-metadata prediction benchmark, RiVaT-Fuse achieves the strongest overall predictive rank among direct representation-level baselines while improving probability and label stability under perturbation. --- ### DR-LabStack: Design and Implementation of a Clinician-Facing Web System for Diabetic Retinopathy Prediction Authors: Yingfan Xu, Tieming Liu, Ye Liang Published: 2026-09-09 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2609.10796v1 Pretrained diabetic retinopathy (DR) prediction models differ in their input fields, serialization formats, preprocessing requirements, and output semantics. Making these models accessible through a common clinical interface therefore requires explicit coordination between the user interface and the inference service. We designed and implemented DR-LabStack, a React-Flask web system integrating four externally developed pretrained models: RuleFit, Pruned RuleFit, Elaborative XGBoost, and Two-level Ensemble. A shared form retrieves ordered model features, renders model-specific numerical and categorical controls, and constructs a positional input vector. Backend adapters load heterogeneous artifacts and apply the ensemble's accompanying scaler, while a common JSON response supports binary classification display alongside method and source information. Functional evaluation on September 8, 2026 used copied application files and real model artifacts in a documented isolated environment. All four models loaded and exposed their 14-, 6-, 8-, and 25-field contracts. Sixty-two Flask test-client requests characterized service behavior; 12 limited-vector checks confirmed invocation-path and threshold consistency. Twenty-four browser-component scenarios with mocked transport verified input ordering and result rendering and characterized input-validation behavior. The resulting system demonstrates a reusable interaction and serving workflow for heterogeneous DR models. The contribution is web-system design, integration, and software functionality; clinical effectiveness and clinician usability require separate evaluation. --- ### Analyzing Traditional and Neural Approaches to Multilingual Readability Assessment Authors: Joshua Wong, Chris Tanner Published: 2026-09-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.10792v1 Transformer-based models excel at Automatic Readability Assessment (ARA), yet feature-based models remain in active use because their predictions tie back to linguistic properties. This matters because readability labels are subjective and rater-dependent, so high accuracy on noisy ground truth may reflect surface patterns rather than the linguistic structure that defines difficulty. We test whether transformers internalize the same features as traditional models across Arabic, English, French, Hindi, and Russian using the ReadMe++ dataset. Shapley Additive Explanations (SHAP) identify the features driving traditional classifiers, which we then use as TCAV concept sets to probe multilingual XLM-R and language-specific encoders. Transformers recover surface-length, syntactic, and lexical-diversity signals, and reflect the ordinal CEFR structure of the traditional models. Alignment varies by model family, language, and layer, with language-specific encoders tracking traditional models more clearly than XLM-R. High linear separability does not always imply directional influence, limiting linear probing for count-based readability features. --- ### Composable CXL Memory as a Kubernetes-Native Shared Memory for LLM Serving Authors: Hongjian Fan, Kevin Zhang, David Habinsky, Sean Dykstra Published: 2026-09-09 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.10790v1 We present a Kubernetes Dynamic Resource Allocation (DRA) driver that makes composable CXL memory a schedulable cluster resource, and evaluate the resulting shared-memory tier for cross-node KV-cache reuse in LLM serving. The driver composes CXL regions on demand, materializes them as DAX devices on each participating host, and injects them into pods under a single Container Device Interface (CDI) name so that pods on different nodes access the same physical region. A shared-memory connector for vLLM/llm-d uses that region as a KV-cache tier with a slot directory embedded inside the shared medium, which eliminates the need for an external metadata service. On a two-node cluster with a 512\,GiB CXL appliance and Qwen2.5-7B-Instruct, cross-node prefix reuse reduces TTFT by 5.5$\times$--36.6$\times$ at an external hit rate of 95.4--99.5\,\%, while node-local tiers (GPU prefix caching, CPU-DRAM offload) fall back to full recompute. The sharing gap, defined as the latency ratio between cross-node and same-node reuse, is 1--4\%, indicating that cross-node reuse incurs little additional latency relative to same-node reuse on our testbed. Both replicas run full engines; the study demonstrates memory disaggregation rather than prefill/decode disaggregation. We report this as a feasibility study rather than a performance evaluation. --- ### Two-Parameter Flow Map Learning for Continuous-Time Diffeomorphic Image Registration Authors: Mohammadjavad Matinkia, Nilanjan Ray Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10789v1 Diffeomorphic image registration is central to medical image analysis, enabling anatomically consistent alignment across subjects. Most learning-based diffeomorphic methods model autonomous ODEs(ordinary differential equations) by parameterizing a stationary velocity field and recovering deformations via scaling-and-squaring. While non-autonomous ODEs with time-dependent velocities increase expressiveness, existing approaches rely on numerical integration to implicitly enforce flow structure that entangles model expressiveness with discretization accuracy. We propose a framework to directly learn the continuous-time solution of a non-autonomous ODE formulated as a two-parameterflow map. By enforcing cocycle consistency, a fundamental structural property of time-varying flows, we learn the flow maps without time discretization and velocity integration during training. The framework recovers diffeomorphic mappings at inference using a small number of compositions. Our proposed framework seamlessly incorporates standard registration backbones and improves alignment accuracy consistently across nine datasets while preserving diffeomorphic structure. Notably, the proposed method achieves an average Dice improvement of 2.1% on brain MRI benchmarks, a 12% TRE reduction on lung CT, and a 2.6% Dice gain on cardiac MRI and ultrasound datasets. --- ### Shedding Light: A Benchmark for Evaluating Lighting Understanding in Generative Image Models Authors: Justine Giroux, Jack Oliver Hilliard, Yannick Hold-Geoffroy, Javier Vazquez-Corral, Jean-François Lalonde Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10787v1 Accurate modelling of illumination is central to realistic image synthesis and scene understanding. Yet, there is little exploration into whether image generative models are good at this task or whether physical plausibility remains a key challenge for them. Clearly, significant progress has been made in realistic image synthesis, but do models truly understand lighting in a physically accurate manner? To answer this question, this work proposes a benchmark to assess the lighting understanding and harmonisation capabilities of generative models. Our key insight is that evaluating lighting understanding for such models only requires testing how well they insert novel objects into real photographs whilst maintaining consistent illumination. To do so, we use a multi-illumination dataset with images containing simple objects serving as ``light probes'', and prompt models to inpaint the same object onto the original image, then compare the generated results against the ground-truth light probes. We then estimate the lighting direction, colour and radiance distribution from the inpainted probes, providing a quantitative measure of illumination accuracy and photometric realism. Our work establishes a scalable evaluation protocol to systematically assess how well generative models capture and reproduce real-world lighting, offering a foundation for benchmarking the photometric accuracy of any future models. All code and data are available at https://lvsn.github.io/SheddingLight/ . --- ### From Connectivity to Rewards: Dense Reward Learning with Directed State Graphs Authors: Shuyuan Zhang, Zihan Wang, Xiao-Wen Chang, Doina Precup Published: 2026-09-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.10781v1 The integration of graphs with Goal-Conditioned Hierarchical Reinforcement Learning (GCHRL) has received increasing attention, as graphs naturally encode task hierarchies for effective subgoal sampling. However, existing methods often overlook intrinsic connectivity information, failing to fully leverage the underlying topology for efficient learning. Most graph-based GCHRL methods use the graph as a stochastic sampling tool rather than as an environmental model that encodes connectivity and state-accessibility information. This limitation is particularly acute in quasimetric environments, where the inherent asymmetry of state transitions poses a fundamental challenge to stable policy learning and robust path planning. In this paper, we address these problems by introducing a state connectivity model designed to predict pairwise state connectivity strength in asymmetric environments. We transform these connectivity strengths into scalar auxiliary dense rewards, providing continuous guidance across multiple hierarchical levels. We demonstrate that our proposed framework, Graph-Guided Quasimetric Dense Reward (G2QDR), can theoretically be integrated into any existing GCHRL architecture, and the state connectivity model is efficiently implemented via a neural network trained on a directed state graph generated during exploration. Empirical results across a wide range of sparse reward environments indicate that, in general, G2QDR can enhance the performance of baseline GCHRL approaches with acceptable computational overhead. --- ### Counterfactual Marginalisation: Framework for Evaluating Robustness to Nuisance Variables Authors: Yasin Ibrahim, Hermione Warr, Robin J. Evans, Konstantinos Kamnitsas Published: 2026-09-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.10778v1 Machine learning models can achieve strong test performance while relying on demographic or acquisition-related shortcuts. We propose counterfactual (CF) marginalisation as a test-time evaluation procedure for assessing robustness of classification models to such variables. Given a CF image generator, we intervene on nuisance parent variables such as age or sex, generate CF versions of each test image, and average predictions over a target intervention distribution. This produces intervention-aware predictions that marginalise demographic effects while preserving patient-specific latent information. We use these predictions to define metrics for CF risk, calibration, stability and worst-case sensitivity. We demonstrate this framework's utility for quantitative robustness evaluation. --- ### A Bellman Optimality Equation for Plasticity Authors: Jeremy Lucas, Doina Precup Published: 2026-09-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.10776v1 In continual reinforcement learning, carefully managing the stability-plasticity tradeoff remains a core challenge. Recent work by Abel et al. (2025) formalized this dilemma by defining plasticity as the generalized directed information from an agent's observations to its actions, and empowerment as the generalized directed information from its actions to its observations. This formulation successfully reframes the traditional stability-plasticity tradeoff as an empowerment-plasticity tradeoff. However, while extensive literature exists on optimizing for empowerment, there is currently no research addressing the optimization of plasticity under this new definition. This paper presents preliminary work toward optimizing plasticity within Markov decision processes. We show that there exists a Bellman optimality equation for optimizing plasticity similar to previous work for empowerment. --- ### Weighted Empirical Risk Minimization for Machine Learning under Long-Range Dependence: Exact Pathwise Rates and Learning-Error Geometry Authors: Elina Moldavskaya Published: 2026-09-09 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.10767v1 We develop an exact almost-sure learning theory for smooth parametric models trained by regularly weighted empirical risk minimization on long-range dependent data. The training observations are generated from a fixed finite window of a stationary Gaussian sequence, and the sample weights are regularly varying. If the loss gradient at the population minimizer has Wiener-chaos rank $m$ and a nonzero low-frequency coefficient, then, in the long-memory interior regime, the finite-lag score reduces on the iterated-logarithm scale to a single weighted Hermite chaos. This yields an almost-sure Bahadur representation, an exact limsup law for the learned parameter, and, for $m\ge2$, the functional cluster set of the complete learning trajectory. The polynomial learning exponent is determined by the memory parameter and the chaos rank and is invariant under the admissible power weighting, whereas the sharp pathwise constant and cluster geometry depend on the weights. In the rank-one case, global optimization over the admissible power exponents shows that every optimizer is positive. Time-series prediction and classification examples illustrate the results. --- ### Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code Authors: Jessica Pourleyli, Maitreyee Das Urmi, Glaucia Melo Published: 2026-09-09 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.10762v1 Advances in large language models (LLMs) fuel the quest for scalable methods to assess the security of generated and security-sensitive software. Static analysis is widely adopted as a scalable, reproducible, and inexpensive security gate, but cannot directly observe runtime exploit behaviour. Vulnerabilities dependent on adversarial inputs, execution context, or exploit chaining may evade static checks while remaining exploitable in practice, yet passing static analysis is often treated as evidence of secure behaviour. This paper introduces the Static-Pass Dynamic-Fail (SPDF) phenomenon and a three-stage agentic pipeline combining static scanning, LLM-driven Common Weakness Enumeration (CWE) reasoning, and autonomous exploit verification in isolated Docker containers. We evaluate 1,355 Python samples from SecurityEval, RedCode, and CyberNative datasets. Of the 654 samples producing no findings under the composite Bandit-Semgrep gate, the LLM detection stage identified 394 candidate vulnerabilities across 235 files. Dynamic verification confirmed or partially confirmed exploitability in 95 files, yielding an inclusive pipeline rate of 14.53% (roughly 1 in 7 statically clean samples). This rate represents the proportion of Bandit-Semgrep-clean samples for which the pipeline identified a candidate vulnerability and obtained runtime evidence supporting exploitability. Outcomes varied by dataset: among candidate file--CWE pairs, confirmed exploitability was 33.7% for RedCode, 28.6% for CyberNative, and 5.4% for SecurityEval. Several frequently confirmed classes, including CWE-338 and CWE-916, were flagged by neither Bandit nor Semgrep. These findings indicate that static-analysis success and runtime security are hierarchical layers of software assurance rather than interchangeable measures, and have the potential to reshape how AI-generated and security-sensitive code is evaluated. --- ### Multilingual in Name Only? Cultural and Linguistic Weaknesses of LLMs in Urdu Authors: Farah Adeeba, Abdul Rafae Khan, Rajesh Bhatt, Hassan Sajjad Published: 2026-09-09 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.10758v1 Multilingual large language models (LLMs) are increasingly used for open-ended text generation, yet their behaviour in low-resource languages remains poorly understood. In this work, we question how correct and reliable is the generation of multilingual LLMs when used for the task of story generation. We consider Urdu language as a representative low-resource language. We generate Urdu-Stories, a corpus of 93 stories generated using three contemporary LLMs (GPT-5.1, Qwen-3-Max, DeepSeek-3.1). We manually annotate the errors present in them under a nine-label linguistic, semantic, and cultural taxonomy. Our notable findings suggest that LLMs often make basic errors of grammar and semantics. The stories lack coherence, have unnatural repetition and show pervasive cultural shallowness. We further show using few-shot prompting that the cultural and context errors largely remain unresolved. Our findings highlight the limitations of current LLMs as a reliable source of content generation and information retrieval for low-resource languages. --- ### GRADE: Single-Frame Generative Radar Depth Estimation Under Visual Degradation Authors: Bin Zhao, Patrick Chiou, Nakul Garg Published: 2026-09-09 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.10756v1 Dense 3D depth perception fails under smoke, fog, and darkness because optical sensors cannot penetrate airborne particulates. mmWave radar remains usable and measures range accurately under these conditions, but its small aperture limits angular resolution. We present GRADE, which grounds a pretrained generative prior in single-frame radar geometry to estimate high-fidelity metric depth. GRADE first maps raw 4D radar spectra to coarse metric depth. A latent diffusion backbone then recovers structural detail while conditioning every denoising step on this estimate. A pixel-space adapter uses residual camera cues when available and is trained across clear, smoke-degraded, and occluded inputs so the full output approaches the radar-conditioned path as visibility degrades. Trained and evaluated on ~95K frames across 12 buildings with real smoke, GRADE achieves an MAE of 0.303 m in clear scenes and 0.313 m under smoke, outperforming existing baselines. Code and datasets are available at https://phi-lab-rice.github.io/GRADE. --- ### Adaptive Margin Ordinal Loss: Penalizing Center-Class Hedging in Ordinal Classification Authors: Manisha Kandel Published: 2026-09-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.10752v1 Standard cross-entropy loss causes neural networks trained on ordinal classification tasks to hedge predictions toward center classes, a failure mode we term \emph{center-class hedging}. This occurs because predicting the middle class minimizes expected symmetric loss, making it the path of least resistance regardless of the true label. Existing ordinal losses address related problems such as large-error penalization and rank consistency, but none directly suppresses center-class hedging as a function of where the true label lies relative to the ordinal center. We propose the Adaptive Margin Ordinal Loss (AMOL), a multiplicative weight applied to per-class loss terms of the form $m(k,y) = 1 + α\cdot (1 - |k-c|/c) \cdot (|y-c|/c)$, where $c$ is the center class, $k$ is the candidate class, and $y$ is the true label. The weight encodes a joint condition: it is large only when the candidate class is near center and the true label is far from center, collapsing to standard behavior otherwise. We further introduce the Center-Hedging Rate (CHR) as a diagnostic metric that directly quantifies this failure mode. Across four ordinal classification benchmarks and five random seeds, AMOL achieves the best or tied-best Quadratic Weighted Kappa (QWK) on all four datasets compared to cross-entropy, OLL, and SORD baselines. An asymmetric variant (AMOL-asym) eliminates center-class hedging entirely on the Abalone dataset ($\text{CHR} = 0.000 \pm 0.000$ across all five seeds, $n \approx 266$ extreme-class test samples per run), compared to $0.074 \pm 0.005$ for standard cross-entropy. --- ### When Synthetic Data Hurts: On Catastrophic Forgetting in Skill Retrieval for LLM Agents Authors: Syed Shariyar Murtaza, Yifan Nie, Utkarsh Soni, Eugene Wen, Arvid Frydenlund Published: 2026-09-09 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.10750v1 LLM agents increasingly rely on external skills retrieved at runtime, making skill selection from large repositories a critical challenge. We present a production skill router over 34,396 skills and a large-scale study of skill retrieval using limited real supervision and synthetic data. We found that the synthetic-data fine-tuning improves in-distribution retrieval but it causes catastrophic forgetting on real and out-of-distribution (OOD) data. We evaluate several forgetting mitigation fine-tuning approaches inspired by continual learning, including embedding-anchor regularization, Learning without Forgetting (LwF), Elastic Weight Consolidation (EWC), and L2-initialization. The results show that these approaches not only retain the performance on OOD skills retrieval but also improve the retrieval on synthetic in-distribution skills by 13.98\% for 0.6B Qwen retriever and reranker. Our results provide a practical benchmark and a robust fine-tuning recipe for scarce, multi-positive supervision. --- ### Meta-Learning for Data-Efficient Plant Growth Estimation via Vision Transformers and Fuzzy Clustering Authors: Sheikh Hasan Elahi, Rusith Chamara Hathurusinghe Dewage, Habib Ullah, Muhammad Salman Siddiqui, Rakibul Islam, Fadi Al Machot Published: 2026-09-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.10749v1 Accurate plant growth estimation is essential for greenhouse monitoring, yet obtaining labeled data remains costly and time-consuming. To address this, we propose a few-shot regression framework that combines Vision Transformer (ViT) feature embeddings, clustering-based task construction, and gradient-based meta-learning, and show that task construction in embedding space is a primary driver of performance. The approach leverages an unlabeled image pool to organize data into structured tasks using fuzzy c-means clustering, enabling efficient learning from a small number of labeled samples. We systematically evaluate meta-learning methods and show that second-order methods (e.g., Model-Agnostic Meta-Learning variants such as MAML++) outperform classical baselines in the few-shot regime. Furthermore, intra-cluster support selection has a limited and dataset-dependent impact. Experiments on two plant datasets show that structured task design combined with meta-learning enables reliable plant growth estimation under severe label scarcity. ---