# Research Papers — 2026-05 · bundle page 258 of 326

> Full-text markdown of papers #12851–12900 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-05/page/258
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/257.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/259.md)

### Towards Billion-scale Multi-modal Biometric Search

Authors: Arka Koner, Chetan S. Naik, Lokesh Kurre, Vivek Raghavan, Barada P. Sabut, Tanusree Deb Barma, Anoop M. Namboodiri, Anil K. Jain
Published: 2026-05-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.07655v1

Searching a multi-biometric database of a billion records for a country-level identity system requires pushing the limits of all aspects of a biometric system, including acquisition, preprocessing, feature extraction, accuracy, matching speed, presentation attack detection, and handling of special cases (e.g., missing finger digits). This is the first paper that gives insights into such a large-scale multimodal biometric search system, called Bharat ABIS, based on open-source architectures. The end-to-end pipeline of Bharat ABIS processes fingerprint, face and iris modalities through modality-specific stages of preprocessing (segmentation), quality assessment, presentation attack detection, and learning an embedding (feature extraction), producing a concatenated template of 13.5KB per person. We present a detailed analysis of the modalities and how they are integrated to create an efficient and effective solution for 1:N search (de-duplication). Evaluations on a demographically stratified gallery of 220 million identities, randomly sampled from 1.55 billion records in India's Aadhaar database, yield an FNIR of 0.3% at an FPIR of 0.5%, for adult probes (over 18 years). We also compare the performance of Bharat ABIS against three state-of-the-art COTS systems on a 20M gallery. Our system achieves a throughput of 100 searches per second on a gallery of 40M on a single server (8xNvidia H100 GPUs, 2TB RAM).

---

### Reliable Chain-of-Thought via Prefix Consistency

Authors: Naoto Iwase, Yuki Ichihara, Mohammad Atif Quamar, Junpei Komiyama
Published: 2026-05-08
Categories: stat.ML, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2605.07654v1

Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority voting (MV), a test-time technique called self-consistency. When we truncate a CoT partway through and regenerate the remainder, we observe that traces with correct answers reproduce their original answer more often than traces with wrong answers. We use this difference as a reliability signal, prefix consistency, that weights each candidate answer by how often it reappears under regeneration. It requires no access to token log-probabilities or self-rating prompts. Across five reasoning models and four math and science benchmarks, prefix consistency is the best correctness predictor in most settings, and reweighting votes by it reaches Standard MV plateau accuracy at up to 21x fewer tokens (median 4.6x). Our code is available at https://github.com/naoto-iwase/prefix-consistency.

---

### Aquatic Neuromorphic Optical Flow

Authors: Pei Zhang, Yunkai Liang, Kaiqiang Wang
Published: 2026-05-08
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2605.07653v2

Underwater environments impose severe constraints on conventional imaging systems and demand solutions that balance high-quality sensing with strict resource efficiency. While emerging event cameras offer a promising alternative, their potential in aquatic scenarios remains largely unexplored. Through the lens of neuromorphic vision, this work pioneers the investigation of motion fields that serve as key media for agile underwater perception. Built upon spiking neural networks, we introduce a self-supervised framework to estimate per-pixel optical flow from asynchronous event streams, elegantly bypassing the long-standing bottleneck of underwater data scarcity. Extensive evaluations demonstrate that our method achieves competitive visual and quantitative results against leading techniques while operating with superior computational efficiency. By bridging neuromorphic sensing and aquatic intelligence, this work opens new frontiers for lightweight, real-time, and low-cost perception on resource-constrained underwater edge platforms.

---

### Breaking Spatial Uniformity: Prior-Guided Mamba with Radial Serialization for Lens Flare Removal

Authors: Zijia Fu, Yuanfei Huang, Lizhi Wang, Hua Huang
Published: 2026-05-08
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2605.07650v1

Lens flares, caused by complex optical aberrations, severely degrade image quality especially in nighttime photography. Although recent restoration methods have made remarkable progress, most still rely on spatially uniform processing. They are failing to handle the region-dependent restoration demands of flare scenes, where saturated light sources should be preserved, flare artifacts removed, and background details recovered. To address this challenge, we propose DeflareMambav2, a prior-guided Mamba framework for lens flare removal. Specifically, we introduce a Flare Prior Network (FPN) to estimate flare priors and guide adaptive restoration. Besides, a novel radial serialization strategy breaks spatially homogeneous processing by performing flare-aware targeted sampling, and better supports long-range modeling in State Space Models (SSMs). Based on these priors, the backbone adopts a dual-level adaptive scheme. It explicitly preserves light-source regions to avoid over-processing, and applies curriculum-based restoration to the remaining contaminated areas while calibrating restoration intensity at the pixel level. Extensive experiments demonstrate that DeflareMambav2 achieves state-of-the-art performance with reduced parameter burden. Code is available at https://github.com/BNU-ERC-ITEA/DeflareMambav2.

---

### Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language Models

Authors: Berkehan Ünal, Hauke Dierend, Dren Fazlija, Christopher Plachetka
Published: 2026-05-08
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2605.07649v2

Over the last few years, research on autonomous systems has matured to such a degree that the field is increasingly well-positioned to translate research into practical, stakeholder-driven use cases across well-defined domains. However, for a wide-scale practical adoption of autonomous systems, adherence to safety regulations is crucial. Many regulations are influenced by the Operational Design Domain (ODD), which defines the specific conditions in which an autonomous agent can function. This is especially relevant for Automated Driving Systems (ADS), as a dependable perception of ODD elements is essential for safe implementation and auditing. Vision-language models (VLMs) integrate visual recognition and language reasoning, functioning without task-specific training data, which makes them suitable for adaptable ODD perception. To assess whether VLMs can function as zero-shot "ODD sensors" that adapt to evolving definitions, we contribute (i) an empirical study of zero-shot ODD classification and detection using four VLMs on a custom dataset and Mapillary Vistas, along with failure analyses; (ii) an ablation of zero-shot optimization strategies with a cost-performance overview; and (iii) a suite of reusable prompting templates with guidance for adaptation. Our findings indicate that definition-anchored chain-of-thought prompting with persona decomposition performs best, while other methods may result in reduced recall. Overall, our results pave the way for transparent and effective ODD-based perception in safety-critical applications.

---

### Learning Large-Scale Modular Addition with an Auxiliary Modulus

Authors: Hanato Kikuchi, Ryosuke Masuya, Kazuhiko Kawamoto, Hiroshi Kera
Published: 2026-05-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.07648v1

Learning parity functions, more general modular addition, is a challenging machine learning task due to its input sensitivity. A recent study substantially scaled modular addition learning in both the number of summands and the modulus. Its key idea is to increase zeros in training sequences, reducing the effective number of summands and thus controlling training difficulty; however, this induces covariate shift between training and test input distributions. This study theoretically and empirically analyzes this side effect and proposes a covariate-shift-free method for modular addition. Specifically, we introduce an auxiliary modulus $Kq$ during training, which reduces wrap-around frequency and problem difficulty while preserving the same input distribution across training and testing. Experiments show strong scalability and sample efficiency: even for large input length $N$, large modulus $q$, and small datasets -- where the sparse method fails to learn -- our method achieves equal or better match accuracy and relaxed $τ$-accuracy. For example, at $N=64$ and $q=974269$, our method trained on 100K samples achieves $97.0\%$ $τ$-accuracy at $τ=0.05$, while the sparse method achieves only $9.5\%$ with the same data size and $93.9\%$ even when extended to 1M samples.

---

### Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation

Authors: Abigail Victoria Gurin Schleifer, Moriah Ariely, Beata Beigman Klebanov, Asaf Salman, Giora Alexandron
Published: 2026-05-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.07647v2

Automated short answer scoring (ASAS) is shifting from discriminative, fine-tuned models to large language models (LLMs) used in few-shot settings. This paradigm leverages LLMs broad world knowledge and ease of deployment, but limited task-specific data may reduce alignment on complex scoring tasks. In particular, its impact on scoring partially correct responses that require nuanced interpretation remains underexplored. We investigate the relationship between the degree of task-specific adaptation of different models and quality-conditioned scoring agreement. We compare three LLMs (GPT-5.2, GPT-4o, Claude Opus 4.5) in few-shot mode, a fine-tuned BERT-based encoder, and a human expert on two open-ended biology items, using several hundred student responses and ground truth scores provided by a biology education expert. The results show that human-human agreement is highest and stable across the full quality spectrum. All AI models perform well on fully correct and fully incorrect responses, but exhibit substantial degradation on mid-range responses. This mid-range degradation is conditioned on task-specific adaptation: It is most severe in few-shot LLMs with few examples and decreases as task-specific data increases, with fine-tuned encoder models performing best. This mid-range degradation may lead to inequitable evaluation of responses produced by students with developing understanding. Our findings highlight the importance of quality-conditioned fairness, with particular attention to mid-range responses.

---

### MAVEN: Multi-Agent Verification-Elaboration Network with In-Step Epistemic Auditing

Authors: Yinsheng Yao, Jiehao Tang, Zhaozhen Yang, Dawei Cheng
Published: 2026-05-08
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.07646v1

While explicit reasoning trajectories enhance model interpretability, existing paradigms often rely on monolithic chains that lack intermediate verification, allowing early errors to cascade unchecked. This lack of modularity impedes granular auditing and compromises the epistemic trust required for high-stakes applications. We propose MAVEN (Multi-Agent Verification-Elaboration Network with In-Step Epistemic Auditing), a blackboard-inspired framework designed to transform LLMs into deliberate reasoners through explicit role-decoupling. At its core, MAVEN operationalizes an adversarial Skeptic-Researcher-Judge loop, simulating expert deliberation by functionally separating logical defense from factual grounding. Experiments on OpenBookQA, TruthfulQA, HALUEVAL and StrategyQA benchmarks demonstrate that MAVEN delivers superior reasoning quality across four fine-grained metrics. Notably, MAVEN consistently outperforms latent reasoning models such as GEMINI-3.1-Pro and consensus-based baselines (e.g., ReConcile) by generating explicitly structured, modular, and verifiable deliberation trajectories, rather than relying on implicit internal states or post-hoc consensus. Moreover, comprehensive evaluations confirm that MAVEN is fully model-agnostic, serving as a strong and transferable reasoning booster that yields substantial performance improvements across diverse backbone models.

---

### EggHand: A Multimodal Foundation Model for Egocentric Hand Pose Forecasting

Authors: Jaeyoung Choi, Hyeondong Kim, Yujin Kim, Daehee Park
Published: 2026-05-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.07642v1

Forecasting future 3D hand pose sequences from egocentric video is essential for understanding human intention and enabling embodied applications such as AR/VR assistance and human-robot interaction. However, this task remains a highly challenging problem because egocentric hand motion is driven by complex human intent, exhibits highly dexterous articulations, and is observed under drastic viewpoint shifts induced by ego-motion. In this work, we introduce EggHand, a foundation-model-based framework for egocentric hand pose forecasting that unifies multimodal semantic reasoning with dynamic motion modeling. Our approach couples an action decoder from a Vision-Language-Action (VLA) model, which captures the structured temporal dynamics of hand motion, with an egocentric video-text encoder that provides viewpoint-aware contextual information learned from large-scale first-person video. Together, these components overcome the brittleness of generic visual encoders under ego-motion and enable joint reasoning over motion, context, and high-level intent-without relying on body pose or external tracking. Experiments on the EgoExo4D dataset show that EggHand sets a new state of the art in forecasting accuracy, remains robust under severe ego-motion, and further enables controllable prediction via language-based task prompts. Project page: https://jyoun9.github.io/EggHand

---

### LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretation

Authors: Jun Wang, Fengpeng Li, Hang Dong, Tianjin Huang, Wei Han
Published: 2026-05-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.07640v1

Remote sensing lithology interpretation is fundamental to geological surveys, mineral exploration, and regional geological mapping. Unlike general land-cover recognition, lithology interpretation is a knowledge-intensive task that requires experts to infer rock types from various features, e.g., subtle visual, spectral, textural, geomorphological, and contextual cues, making reliable automated interpretation highly challenging. Geological knowledge-guided large multimodal models offer new opportunities, yet their evaluation remains constrained by the lack of benchmarks that capture lithological annotations, multi-level geological semantics, and expert-informed assessment. Here, we propose LithoBench, a multi-level benchmark for evaluating geological semantic understanding in remote sensing lithology interpretation. LithoBench contains 10,000 expert-annotated interpretation instances across 12 representative lithological categories, including 4,000 multiple-choice and 6,000 open-ended tasks organized into five cognitive levels: Identification and Description, Comparative Analysis, Mechanism Explanation, Practical Application, and Comprehensive Reasoning. We further develop an expert-in-the-loop, knowledge-grounded semi-automated construction pipeline, coupling multi sub-processes, e.g., structured geological image descriptions, to enhance geological validity and evaluation reliability. Experiments with multiple large vision-language models eveal substantial limitations in geological semantic understanding, particularly on higher-order explanation, application, and reasoning tasks.

---

### Tacit Knowledge Extraction via Logic Augmented Generation and Active Inference

Authors: Lorenzo Lamazzi, Aldo Gangemi, Alessio Giberti, Andrea Giovanni Nuzzolese, Vittorio Andrea Rocca, Mattia Torta, Francesco Poggi
Published: 2026-05-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.07639v1

Tacit knowledge plays a central role in human expertise, yet it remains difficult to capture, formalize, and reuse in machine-interpretable form. This challenge is especially relevant in procedural domains, where successful execution depends not only on explicit instructions, but also on implicit assumptions, contextual constraints, embodied skills, and experience-based judgments rarely documented. As a result, current knowledge engineering pipelines struggle to transform tacit and process-centric knowledge into formally specified, machine-interpretable representations that can be queried, validated, reasoned over, and reused. In this paper, we introduce a neuro-symbolic framework that combines Logic-Augmented Generation and an Active-Inference-inspired approach for ontology-grounded Knowledge Graph construction. We evaluate the approach in a knowledge transfer case study in manufacturing, using assembly-like repair procedures from instructional videos as a reproducible proxy domain. Results show that the proposed solution improves completeness and semantic quality, advancing neuro-symbolic knowledge engineering for industrial domains.

---

### Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding

Authors: Valeriy Vyaltsev, Alsu Sagirova, Anton Andreychuk, Oleg Bulichev, Yuri Kuratov, Konstantin Yakovlev, Aleksandr Panov, Alexey Skrynnik
Published: 2026-05-08
Categories: cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2605.07637v2

Multi-agent pathfinding (MAPF) is a widely used abstraction for multi-robot trajectory planning problems, where multiple homogeneous agents move simultaneously within a shared environment. Although solving MAPF optimally is NP-hard, scalable and efficient solvers are critical for real-world applications such as logistics and search-and-rescue. To this end, the research community has proposed various decentralized suboptimal MAPF solvers that leverage machine learning. Such methods frame MAPF (from a single agent perspective) as a Dec-POMDP where at each time step an agent has to decide an action based on the local observation and typically solve the problem via reinforcement learning or imitation learning. We follow the same approach but additionally introduce a learnable communication module tailored to enhance cooperation between agents via efficient feature sharing. We present the Local Communication for Multi-agent Pathfinding (LC-MAPF), a generalizable pre-trained model that applies multi-round communication between neighboring agents to exchange information and improve their coordination. Our experiments show that the introduced method outperforms the existing learning-based MAPF solvers, including IL and RL-based approaches, across diverse metrics in a diverse range of (unseen) test scenarios. Remarkably, the introduced communication mechanism does not compromise LC-MAPF's scalability, a common bottleneck for communication-based MAPF solvers.

---

### Multi-Dimensional Evaluation of LLMs for Grammatical Error Correction

Authors: Adnan Labib, Qiao Wang, Yixuan Huang, Zheng Yuan
Published: 2026-05-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.07635v1

Automated assistants for Grammatical Error Correction are now embedded in educational platforms serving millions of learners, yet three critical gaps remain in this domain: (1) latest-generation Large Language Models (LLMs) lack comprehensive evaluation on grammar correction tasks; (2) whether combining these LLMs improves correction quality is unexplored; and (3) the extent to which reference-based metrics underestimate GEC system performance has not been adequately quantified. In this study, first, we evaluate latest-generation LLMs on edit precision, fluency preservation, and meaning retention, showing fine-tuned GPT-4o achieves state-of-the-art performance across all three dimensions. Second, through grammatical error type analysis we demonstrate that individual LLMs exhibit highly similar error correction patterns ($ρ=0.947$). Third, we show that reference-based metrics underestimate GEC performance with 73.76% of GPT-4o corrections different from gold standards being equally valid or even superior. These GEC evaluation findings equip educators with guidance for selecting GEC assistants that enhance rather than constrain student linguistic development. We make our data, code, and models publicly available.

---

### Robust stochastic first order methods in heavy-tailed noise via medoid mini-batch gradient sampling

Authors: Manojlo Vukovic, Dusan Jakovetic
Published: 2026-05-08
Categories: math.OC, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2605.07634v1

We consider a first order stochastic optimization framework where, at each iteration, $K$ independent identically distributed (i.i.d.) data point samples are drawn, based on which stochastic gradients can be queried. We allow gradient noise to be heavy-tailed, with possibly infinite variances. For the considered heavy-tailed setting, many algorithmic variants have recently been proposed based on gradient clipping or other nonlinear operators (e.g., normalization) applied over noisy gradients. In this paper, we take an alternative approach and propose a novel stochastic first order method dubbed Robust Stochastic Gradient Descent with medoid mini-batch gradient sampling, R-SGD-Mini for short. The core idea of R-SGD-Mini is to split the $K$-sized data batch into $M$ distinct data chunks, form for each chunk the stochastic gradient, and update the solution estimate with respect to the stochastic gradient direction of the chunk that is medoid of gradients of all data-chunks. Under a general class of symmetric heavy-tailed gradient noises and a standard non-convex setting, we establish explicit bounds on the expected time-averaged squared gradient norm. More precisely, we show that the latter quantity converges at rate $\mathcal{O}(T^{-1})$ to a small neighborhood of zero; we explicitly characterize this neighborhood in terms of noise and algorithm's parameters. Moreover, if the time horizon is known in advance, we establish the rate of $\mathcal{O}(T^{-\frac{1}{2}}).$ Furthermore, when clipping is incorporated, we obtain convergence guaranties in the high-probability sense and recover the same rate. Experimental results indicate that R-SGD-Mini and its clipped variant consistently perform favorably compared to SGD, clipped SGD and Median-of-Means based methods.

---

### Post-training makes large language models less human-like

Authors: Marcel Binz, Elif Akata, Abdullah Almaatouq, Mohammed Alsobay, Oleksii Ariasov, Franziska Brändle, David Broska, Jason W. Burton, Nuno Busch, Frederick Callaway, Vanessa Cheung, Brian Christian et al.
Published: 2026-05-08
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.07632v2

Large language models (LLMs) are increasingly used as surrogates for human participants, but it remains unclear which models best capture human behavior and why. To address this, we introduce Psych-201, a novel dataset that enables us to measure behavioral alignment at scale. We find that post-training -- the stage that turns base models into useful assistants -- consistently reduces alignment with human behavior across model families, sizes, and objectives. Moreover, this misalignment widens in newer model generations even as base models continue to improve. Finally, we find that persona-induction -- a popular technique for eliciting human-like behavior by conditioning models on participant-specific information -- does not improve predictions at the level of individuals. Taken together, our results suggest that the very processes that are currently employed to turn LLMs into useful assistants also make them less accurate models of human behavior.

---

### Inference Time Causal Probing in LLMs

Authors: Sadegh Khorasani, Saber Salehkaleybar, Negar Kiyavash, Matthias Grossglauser
Published: 2026-05-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.07631v1

Causal probing methods aim to test and control how internal representations influence the behavior of generative models. In causal probing, an intervention modifies hidden states so that a property takes on a different value. Most existing approaches define such interventions by training an auxiliary probe classifier, which ties the method to a specific task or model and risks misalignment with the model's predictive geometry. We propose Hidden-state Driven Margin Intervention (HDMI), a probe-free, gradient-based technique that directly steers hidden states using the model's native output. HDMI applies a margin objective that increases the probability of a target continuation while decreasing that of the source, without relying on probe classifiers. We further introduce a lookahead variant (LA-HDMI) for text editing that backpropagates through the softmax embeddings, modifying the current hidden state so that the likelihood of user-specified tokens increases in next token generations while preserving fluency. To evaluate interventions, we measure completeness (whether the targeted property changes as intended) and selectivity (whether unrelated properties are preserved), and report their harmonic mean as an overall measure of reliability. HDMI consistently achieves higher reliability than prior methods on the LGD agreement corpus and the CausalGym benchmark, across Meta-Llama-3-8B-Instruct, and Pythia-70M.

---

### Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents

Authors: Zhengyang Tang, Yi Zhang, Chenxin Li, Xin Lai, Pengyuan Lyu, Yiduo Guo, Weinong Wang, Junyi Li, Yang Ding, Huawen Shen, Zhengyao Fang, Xingran Zhou et al.
Published: 2026-05-08
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.07630v1

When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may be avoided because the agent recognized the risk and chose the safe action, or because it failed to understand the screen or execute any relevant action at all. These cases have different causes and call for different fixes, yet current benchmarks often merge them under task success, refusal, or final harmful outcome. We address this problem with PhoneSafety, a benchmark of 700 safety-critical moments drawn from real phone interactions across more than 130 apps. Each instance isolates the next decision at a risky moment and asks a simple question: does the model take the safe action, take the unsafe action, or fail to do anything useful? We evaluate eight representative phone-use agents under this framework. Our results reveal two main patterns. First, stronger general phone-use ability does not reliably imply safer choices at risky moments. Models that perform better on ordinary app tasks are not always the ones that behave more safely when the next action matters. Second, failures to do anything useful behave like a capability signal rather than a safety signal: they are concentrated in more visually and operationally demanding settings and remain stable when the evaluation protocol changes. Across models, failures split into two recurring patterns: unsafe choices in settings where the model can act but chooses wrongly, and inability to act in more visually and operationally demanding screens. Overall, a harmless outcome is not enough to count as evidence of safety. Evaluating phone-use agents requires separating unsafe judgment from inability to act.

---

### Statistical Convergence of Spherical First Hitting Diffusion Models

Authors: Simon Bienewald, Lukas Trottner
Published: 2026-05-08
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2605.07625v1

Denoising diffusion models have evolved into a state-of-the-art method for tasks in various fields, such as denoising and generation of images, text generation, or generation of synthetic data for training of other machine learning models. First hitting diffusion models (FHDM) are a particular class of denoising diffusion models with \textit{random} adaptive generation time tailored to generate data on a known manifold. Building on the conditioning framework of Doob's $h$-transform these models leverage the given information on the target data manifold to demonstrate strong performance across tasks while offering distinct features such as time-homogeneous dynamics of the generating process and a reduced average simulation time. Even though the theoretical investigation of standard forward-backward diffusion models has attracted much attention in the recent past, the statistical convergence properties of FHDMs are not yet understood. In this work, we show that, up to logarithmic factors, FHDMs achieve the minimax optimal convergence rate in total variation for spherically supported Sobolev smooth data distributions. In particular, this is the first statistical optimality result for denoising diffusion modelling with random generation time.

---

### Is She Even Relevant? When BERT Ignores Explicit Gender Cues

Authors: Jonas Klein, Chiara Manna, Eva Vanmassenhove
Published: 2026-05-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.07622v1

Gender bias in large language models has primarily been investigated for English, while languages with grammatical or morphological gender remain comparatively understudied. This paper investigates how and when gender information emerges in a Dutch BERT model trained from scratch, offering one of the first checkpoint-level analyses of bias formation in a Transformer architecture for a language combining overt morphological gender marking and generic forms. By extracting contextual embeddings throughout training, we construct dynamic gender subspaces using linear SVMs to trace when gender becomes linearly encoded and how this encoding evolves over time. Contextual embeddings are often assumed to integrate contextual cues robustly, allowing models to adjust the representation of a word depending on its more local usage. We therefore test whether explicit gender cues in controlled sentence templates (e.g., Zij is een loodgieter ('She is a plumber')) can override learned statistical associations (plumber -> male). Our findings challenge this assumption: although gender becomes clearly linearly separable around epoch 20 and is distributed across multiple embedding dimensions, the model struggles to update its internal gender representation in light of explicit contextual cues in short sentence templates. Stereotypical gender-profession pairings are predicted far more accurately than anti-stereotypical ones, and generic forms in Dutch systematically default to a male interpretation, even when the context explicitly denotes a female referent. Together, our results seem to indicate that contextualization in the representations learned by our Dutch BERT model is not sufficiently dynamic along the probed gender direction: explicit gender cues in anti-stereotypical contexts are not reliably reflected in the resulting representations, resulting in persistent male-default behaviour.

---

### Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation

Authors: Hongyang Su, Beibei Kong, Lei Cheng, Chengxiang Zhuo, Zang Li, Chenyun Yu
Published: 2026-05-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.07613v1

Conversational news recommendation requires grounding each suggestion in a rapidly evolving article corpus while addressing implicit user intents that lack explicit retrievable keywords. To characterize this scenario, we identify 6 intent types from production dialogues: five are implicit and pose fundamental challenges to standard RAG pipelines, forming a critical retrieve-first bottleneck. To address these issues, we introduce intent-driven Semantic ID (SID) generation under a Generate-then-Match paradigm. With two-stage training that consists of multi-task SID alignment and GPT-4 Chain-of-Thought distillation, an LLM maps diverse intents to hierarchical SID prefixes, which are then fuzzy-matched to the current news pool to guarantee fully grounded recommendations. Profile-Aware Dual-Signal Reasoning (PADR) further enables cold-start users to obtain valid recommendations using only profiles. On a mainstream Chinese news platform, our 7B model achieves 0% hallucination and 12.4% L1 match in the 152K open-generation SID space (4x random baseline). It matches GPT-4+Hybrid RAG on L1 while surpassing it on finer-grained metrics (L2 2x, Category +1.2pp) at ~100x lower cost. Cold-start users, where existing baselines score 0%, achieve 18.0% L1 (6x random), the highest among all user groups.

---

### FS-I2P:A Hierarchical Focus-Sweep Registration Network with Dynamically Allocated Depth

Authors: Zhixin Cheng, Yujia Chen, Xujing Tao, Bohao Liao, Xiaotian Yin, Baoqun Yin, Tianzhu Zhang
Published: 2026-05-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.07607v2

Image-to-point cloud registration is often challenged by viewpoint changes, cross-modal discrepancies, and repetitive textures, which induce scale ambiguity and consequently lead to erroneous correspondences. Recent detection-free methods alleviate this issue by leveraging multi-scale features and transformer-based interactions. However, they still suffer from attention drift across layers and intra-scale inconsistencies, hindering precise registration. Inspired by human behavior, we propose a ``Focus--Sweep'' paradigm and develop a Hierarchical Focus--Sweep Interaction Module within an SSM-based framework to enhance multi-level cross-modal feature association. In addition, we introduce a Dynamic Layer Allocation Strategy that adaptively determines the iteration depth to better exploit geometric constraints and improve matching robustness. Extensive experiments and ablations on two benchmarks, RGB-D Scenes V2 and 7-Scenes, demonstrate that our approach achieves state-of-the-art performance.

---

### Nürnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification

Authors: Philipp Steigerwald, Eric Rudolph, Jens Albrecht
Published: 2026-05-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.07606v1

Detecting levels of psychological defence mechanisms in supportive conversations is inherently ambiguous. In the PsyDefDetect shared task at BioNLP 2026 the eight positive defence categories share surface language and differ only in pragmatic function and trained raters reach only moderate inter-annotator agreement. On such a task the decisive lever is not a stronger single model but error independence, since any single representation will waver on the overlapping defence boundaries. We translate this insight into a 9-voter ensemble spanning three orthogonal axes: class granularity (all nine classes for the gatekeeper, only the eight defence classes for the specialists), training method (generative and discriminative) and base model. The system reaches $F1_{test}{=}.420$ on the hidden test set, placing first among 21 registered teams.

---

### SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild

Authors: Xuyi Hu, Jin Lyu, Jiuming Liu, Yebin Liu, Silvia Zuffi, Liang An, Stefan Goetz
Published: 2026-05-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.07604v1

3D animal reconstruction in the wild remains challenging due to large species variation, frequent occlusions, and the prevalence of multi-animal scenes, while existing methods predominantly focus on single-animal settings. We present SAM 3D Animal, the first promptable framework for multi-animal 3D reconstruction from a single image. Built on the SMAL+ parametric animal model, our method jointly reconstructs multiple instances and supports flexible prompts in the form of keypoints and masks which enable more reliable disambiguation in crowded and occluded scenes. To train such a model, we further introduce Herd3D, a multi-animal 3D dataset containing over 5K images, designed to increase diversity in species, interactions, and occlusion patterns. Experiments on the Animal3D, APTv2, and Animal Kingdom datasets show that our framework achieves state-of-the-art results over both existing model-based and model-free methods, demonstrating a scalable and effective solution for prompt-driven animal 3D reconstruction in the wild.

---

### Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators

Authors: Tsuyoshi Okita
Published: 2026-05-08
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.07600v1

Recent methods for improving LLM mathematical reasoning, whether through MCTS-based test-time search or causal graph-guided knowledge injection, cannot identify which concepts causally contribute to a correct answer, as the observed association may be spurious, driven by confounders such as problem difficulty. We propose CIKA (Causal Intervention for Knowledge Activation), a framework that uses the LLM itself as an interventional simulator: a prompt sets the concept state to ``mastered'' and the correctness change estimates the causal effect. We formalize this quantity as an Interventional Capability Probe (ICP), which diagnoses whether the LLM can use a given concept -- distinct from merely possessing knowledge. Because the intervention exogenously sets the concept state independently of problem difficulty, ICP separates confounding that observational methods cannot. On 67 screened problems, the ICP of the top-ranked concept (+0.219) is significantly larger than that of the negative control (+0.039; paired $t$-test, $p < 10^{-6}$, Cohen's $d = 0.86$), confirming that the probe discriminates causally relevant concepts from irrelevant ones. Analysis of 601 Omni-MATH problems further shows that solved problems have 6.1$\times$ higher ATE than unsolved ones (0.338 vs. 0.055), confirming that ICP is predictive of problem-solving success. With a 7B-parameter LLM whose weights are entirely frozen, CIKA achieves 69.7\% on the contamination-free Omni-MATH-Rule benchmark and 64.0\% overall, compared to 60.5\% for o1-mini, and 97.2\% on GSM8K, 46--50\% on AIME 2024--2026, and 46.2\% on MathArena. The Causal Knowledge Activation component contributes 33.8\% of correct answers on problems where the base model alone fails, demonstrating that the LLM already possessed but had not activated the requisite knowledge.

---

### Optimal Recourse Summaries via Bi-Objective Decision Tree Learning

Authors: Ioannis Chatzis, Jason Liartis, Athanasios Voulodimos, Giorgos Stamou
Published: 2026-05-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.07598v2

Actionable Recourse provides individuals with actions they can take to change an unfavorable classifier outcome. While useful at the instance level, it is ill-suited for global auditing and bias detection, since aggregating local actions is costly and often inconsistent. Recourse Summaries address this limitation by partitioning the population and assigning one shared action per subgroup, enabling comparison across subgroups. Designing summaries involves a fundamental trade-off between recourse effectiveness and recourse cost, which existing methods do not adequately address. We introduce Summaries of Optimal and Global Actionable Recourse (SOGAR), which formulates recourse summary learning as an optimal decision tree learning problem and finds the Pareto front -- the complete set of solutions where improving one objective necessarily worsens the other. SOGAR enables post-hoc selection of the desired trade-off without retraining. Using shallow axis-parallel decision trees and sparse leaf actions, SOGAR produces stable, low-cost, and effective recourse summaries that outperform existing approaches across effectiveness and cost metrics.

---

### A Refined Generalization Analysis for Extreme Multi-class Supervised Contrastive Representation Learning

Authors: Nong Minh Hieu, Antoine Ledent
Published: 2026-05-08
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2605.07596v3

Contrastive Representation Learning (CRL) has achieved strong empirical success in multiple machine learning disciplines, yet its theoretical sample complexity remains poorly understood. Existing analyses usually assume that input tuples are identically and independently distributed, an assumption violated in most practical settings where contrastive tuples are constructed from a finite pool of labeled data, inducing dependencies among tuples. While one recent work analyzed this learning setting using U-Statistics to estimate the population risk, the techniques used therein require the risk of each class to concentrate uniformly, making excess risk bounds scale in the order of $ρ_{\min}^{-{1}/{2}}$ where $ρ_{\min}$ denotes the probability of the rarest class. Such a dependency can be overly pessimistic in the extreme multiclass settings where there are many tail classes which contribute minimally to the overall population risk. Our contributions are two-fold. Firstly, we improve upon the previous work and prove a bound with a sample complexity of the same order as the number of classes $R$, regardless of the distribution over classes. Furthermore, we formulate a different estimator that captures the concentration of the risk \textit{across classes}, enabling sharper bounds in extreme multi-class learning scenarios, especially where class distributions are long-tailed. Under mild assumptions on the class distributions, the resulting sample complexity is $\mathcal{O}(k)$ where $k$ is the number of samples per tuple.

---

### TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos

Authors: Hengyi Feng, Hao Liang, Mingrui Chen, Bohan Zeng, Meiyi Qiang, Zhengyang Zhao, Zimo Meng, Zeang Sheng, Wentao Zhang
Published: 2026-05-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.07593v2

Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory streams, whereas existing benchmarks largely fail to evaluate this capability. They restrict videos to short clips, isolate modalities, or reduce questions to one-hop perception. We introduce TraceAV-Bench, the first benchmark to jointly evaluate multi-hop reasoning over long audio-visual trajectories and multimodal hallucination robustness. TraceAV-Bench comprises 2,200 rigorously validated multiple-choice questions over 578 long videos, totaling 339.5 hours, spanning 4 evaluation dimensions and 15 sub-tasks. Each question is grounded in an explicit multi-hop evidence trajectory that averages 3.68 hops across a 15.1-minute temporal span. The dataset is built by a three-step pipeline followed by a strict quality assurance process. Evaluation of multiple representative OmniLLMs on TraceAV-Bench reveals that the benchmark poses a persistent challenge across all models, with the strongest closed-source model (Gemini 3.1 Pro) reaching only 68.29% on general tasks, and the best open-source model (Ming-Flash-Omni-2.0) reaching 51.70%, leaving substantial headroom. Further analysis shows that current models struggle to gather and combine evidence across long audio-visual videos, with performance varying across modalities and reasoning tasks. We hope TraceAV-Bench will facilitate progress toward reliable long-form audio-visual reasoning in OmniLLMs.

---

### TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos

Authors: Hengyi Feng, Hao Liang, Mingrui Chen, Bohan Zeng, Meiyi Qiang, Zhengyang Zhao, Zimo Meng, Zeang Sheng, Wentao Zhang
Published: 2026-05-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.07593v1

Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory streams, whereas existing benchmarks largely fail to evaluate this capability. They restrict videos to short clips, isolate modalities, or reduce questions to one-hop perception. We introduce TraceAV-Bench, the first benchmark to jointly evaluate multi-hop reasoning over long audio-visual trajectories and multimodal hallucination robustness. TraceAV-Bench comprises 2,200 rigorously validated multiple-choice questions over 578 long videos, totaling 339.5 hours, spanning 4 evaluation dimensions and 15 sub-tasks. Each question is grounded in an explicit reasoning chain that averages 3.68 hops across a 15.1-minute temporal span. The dataset is built by a three-step semi-automated pipeline followed by a strict quality assurance process. Evaluation of multiple representative OmniLLMs on TraceAV-Bench reveals that the benchmark poses a persistent challenge across all models, with the strongest closed-source model (Gemini 3.1 Pro) reaching only 68.29% on general tasks, and the best open-source model (Ming-Flash-Omni-2.0) reaching 51.70%, leaving substantial headroom. Moreover, we find that robustness to multimodal hallucination is largely decoupled from general multimodal reasoning performance. We anticipate that TraceAV-Bench will stimulate further research toward OmniLLMs that can reason coherently and faithfully over long-form audio-visual content.

---

### Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness

Authors: Pedro Alonso, Chongshou Li, Tianrui Li
Published: 2026-05-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.07590v2

Despite extensive progress in point cloud robustness, existing methods primarily rely on augmentation strategies or defense mechanisms while overlooking the geometric nature of adversarial fragility. We hypothesize that adversarial vulnerability in 3D networks arises from a manifold misalignment between the latent geometry learned by the model and the intrinsic geometry of the underlying surface. Small, geometry-preserving perturbations along the input manifold often induce disproportionate distortions in feature space, potentially leading to misclassifications. We formalize this phenomenon by developing a geometric interpretation of 3D robustness that links classical adversarial theory to the intrinsic structure of point clouds. Motivated by this analysis, we introduce Manifold-Aligned Point Recognition (MAPR), a framework that regularizes the latent geometry by aligning predictions across intrinsic perturbations. MAPR augments each point cloud with intrinsic features capturing local curvature and diffusion structure, and applies a consistency loss that preserves invariance to intrinsic, geometry-preserving perturbations. Without relying on adversarial training or additional data, MAPR consistently improves robustness under multiple adversarial attacks across several datasets, achieving average robustness gains of +20.02 and +8.83 percentage points over vanilla models on ModelNet40 and ScanObjectNN, respectively.

---

### Revisiting Transformer Layer Parameterization Through Causal Energy Minimization

Authors: Jin Xu, Camille Couturier, Victor Rühle, Saravan Rajmohan, James Hensman
Published: 2026-05-08
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2605.07588v1

Transformer blocks typically combine multi-head attention (MHA) for token mixing with gated MLPs for token-wise feature transformation, yet many choices in their parameterization remain largely empirical. We introduce Causal Energy Minimization (CEM), a framework that recasts Transformer layers as optimization steps on conditional energy functions while explicitly accounting for layer parameterization. Extending prior energy-based interpretations of attention, CEM shows that weight-tied MHA can be derived as a gradient update on an interaction energy, and that a gated MLP with shared up/down projections can be viewed through an element-wise energy. This perspective identifies a design space for Transformer layers that includes within-layer weight sharing, diagonal-plus-low-rank interactions, lightweight preconditioners, and recursive updates. We evaluate CEM-derived layers in language-modeling experiments at the moderate hundred-million-parameter scale. Despite their constrained parameterizations, these layers train stably and can match corresponding Transformer baselines. Overall, our results suggest that CEM provides a useful lens for understanding Transformer layer parameterization, connecting Transformer architectures to energy-based models and motivating further exploration of energy-guided layer designs.

---

### Parallel Lifted Planning via Semi-Naive Datalog Evaluation

Authors: Dominik Drexler, Oliver Joergensen, Jendrik Seipp
Published: 2026-05-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.07584v1

Lifted classical planners operate directly on first-order planning tasks to avoid the computationally demanding grounding step. However, lifted planning is typically slower, as planners must repeatedly instantiate ground structures during search. Many core components of lifted classical planning, such as successor generation, axiom evaluation, task grounding, and delete-relaxed heuristics, have previously been studied through the lens of Datalog evaluation. We build upon this line of work and extend it by developing and analyzing an execution model with two levels of parallelism: rule-level parallelism and grounding parallelism. We further specialize this solver for planning-specific workloads with a grounder based on clique enumeration, which we extend to support semi-naive Datalog evaluation. Our experimental evaluation using greedy best-first search with the FF heuristic shows that our implementation already solves more tasks than the baselines on a single core, and the gap widens as additional cores are used. Moreover, on hard-to-ground tasks where on average 97.6% of the total runtime is spent in Datalog execution, the proposed execution model exhibits an average parallel fraction of 92.4%, while achieving up to a 6-fold speedup on 8 cores in practice.

---

### Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States

Authors: Yunho Choi, Jongwon Lim, Woojin Ahn, Minjae Oh, Jeonghoon Shim, Yohan Jo
Published: 2026-05-08
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.07579v2

Reinforcement learning with verifiable rewards (RLVR) for Large Reasoning Models hinges on baseline estimation for variance reduction, but existing approaches pay a heavy price: PPO requires a policy-model scale critic, while GRPO needs multiple rollouts per prompt to keep its empirical group mean stable. We introduce Policy Optimization with Internal State Value Estimation), which obtains a baseline at negligible cost by using the policy model's internal signals already computed during the policy forward pass. A lightweight probe predicts the expected verifiable reward from the hidden states of the prompt and generated trajectory, as well as token-entropy statistics, and is trained online alongside the policy. To preserve gradient unbiasedness despite using trajectory-conditioned features, we introduce a cross-rollout construction that predicts each rollout's value from an independent rollout's internal states. Because POISE estimates prompt value using only a single rollout, it enables higher prompt diversity for a fixed compute budget during training. This reduces gradient variance for more stable learning and also eliminates the compute overhead of sampling costs for detecting zero-advantage prompts. On Qwen3-4B and DeepSeek-R1-Distill-Qwen-1.5B across math reasoning benchmarks, POISE matches DAPO while requiring less compute. Moreover, its value estimator shows similar performance to a separate LLM-scale value model and generalizes to various verifiable tasks. By leveraging the model's own internal representations, POISE enables more stable and efficient policy optimization.

---

### Bilevel Graph Structure Learning, Revisited: Inner-Channel Origins of the Reported Gain

Authors: Minkyoung Kim, Beakcheol Jang
Published: 2026-05-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.07577v1

Bilevel graph structure learning is widely understood to improve graph neural networks by jointly optimizing model parameters and a learned graph structure, with the resulting performance gain attributed to the rewired adjacency. We find that this attribution may be overstated: training-dynamics effects in the inner loop, rather than the rewiring itself, capture a substantial share of the gain. To establish this, we introduce frozen-$φ$, a control that freezes the graph while retaining the inner-loop training schedule. This decomposes the bilevel gain into an inner channel of $T$-step training dynamics with implicit gradient regularization and a graph channel of the graph rewiring itself. On spatio-temporal flow forecasting the inner channel matches or exceeds the full bilevel pipeline, accounting for 78-101% of the gain; on node classification it accounts for 37-44% under a Bernoulli edge-level parameterization. We also verify that classical spectral diagnostics can dissociate from task gain. We propose frozen-$φ$ as a standardized diagnostic for bilevel graph structure learning, with graph distillation as a method-agnostic complement. A three-precondition framework further predicts the sign of the bilevel gain on all six benchmarks.

---

### Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding

Authors: Ke Ma, Jiaqi Tang, Bin Guo, Xueting Han, Ruonan Xu, Qingfeng He, Ziheng Wang, Xu Wang, Qifeng Chen, Zhiwen Yu, Yunhao Liu
Published: 2026-05-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.07575v2

Proactive streaming video understanding requires Video-LLMs to decide when to respond as a video unfolds, a task where existing methods often fall short due to their implicit, query-agnostic modeling of visual evidence. We introduce Response-G1, a novel framework that establishes explicit, structured alignment between the accumulated video evidence and the query's expected response conditions via scene graphs. The framework operates in three fine-tuning-free stages: (1) online query-guided scene graph generation from streaming clips; (2) memory-based retrieval of the most semantically relevant historical scene graphs; and (3) retrieval-augmented trigger prompting for per-frame "silence/response" decisions. By grounding both evidence and conditions in a shared graph representation, Response-G1 achieves more interpretable and accurate response timing decisions. Experimental results on established benchmarks demonstrate the superiority of our method in both proactive and reactive tasks, validating the advantage of explicit scene graph modeling and retrieval in streaming video understanding.

---

### PolarVLM: Bridging the Semantic-Physical Gap in Vision-Language Models

Authors: Yuliang Li, Chu Zhou, Heng Guo, Boxin Shi, Imari Sato, Zhanyu Ma
Published: 2026-05-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.07574v2

Mainstream vision-language models (VLMs) fundamentally struggle with severe optical ambiguities, such as reflections and transparent objects, due to the inherent limitations of standard RGB inputs. While polarization imaging captures polarimetric physical parameters that resolve these ambiguities, existing methods are constrained by fixed-format outputs and remain isolated from open-ended reasoning. To bridge this semantic-physical gap, we introduce PolarVLM, the first multimodal framework integrating polarimetric physical parameters into VLMs. By employing a dual-stream architecture and a progressive two-stage training strategy, PolarVLM effectively prevents physical misinterpretations while preserving general visual abilities. Complementing our architecture, we construct PolarVQA, the first benchmark for polarization-aware VQA, featuring 75K physics-grounded instruction-tuning pairs targeting reflective and transparent scenes. Experiments show that PolarVLM surpasses the RGB baseline by 25.4% overall across five evaluation tasks, with remarkable gains of 26.6% in reflection recognition and 34.0% in glass counting, successfully unlocking physics-aware semantic understanding.

---

### Open-Ended Task Discovery via Bayesian Optimization

Authors: Masaki Adachi, Yuta Suzuki, Juliusz Ziomek
Published: 2026-05-08
Categories: cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2605.07572v1

When applying Bayesian optimization (BO) to scientific workflow, a major yet often overlooked source of uncertainty is the task itself -- namely, what to optimize and how to evaluate it -- which can evolve as evidence accumulates. We introduce Generate-Select-Refine (GSR), a open-ended BO framework that alternates between task generation and task optimization. Starting from a user-provided seed task, GSR generates new tasks in a coarse-to-fine manner while a task-acquisition function schedules optimization. Asymptotically, it concentrates evaluations on the best task, incurring only logarithmic regret overhead relative to single-task BO. We apply GSR to new product development, chemical synthesis scaling, algorithm analysis, and patent repurposing, where it outperforms existing LLM-based optimizers.

---

### Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs

Authors: Peitao Han, Fei Cheng, Lis K. Pereira, Qianying Liu, Shigeru Kitazawa
Published: 2026-05-08
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2605.07568v1

The Arrow-of-Time (AoT) task, determining whether a video plays forward or backward by recognizing temporal irreversibility, is one humans solve with near-perfect accuracy, yet frontier Video Large Language Models (Video-LLMs) perform only modestly above chance. This gap raises a key question: do visual backbones fail to encode temporal information, or does information bottleneck lie elsewhere in the Video-LLM architecture? We address this question by isolating the vision encoder from the Video-LLM and tracing temporal information across the encoder, projector, and LLM. We find that video-centric encoders with explicit temporal modeling encode strong temporal signals, whereas frame-centric encoders do not. However, when video-centric representations are passed through a standard Video-LLM architecture, performance often collapses, revealing a bottleneck of temporal information flow. We identify projector design as a key factor: Q-Former disrupts temporal information, while a time-preserved MLP projection substantially improves the LLM's access to such information. Our layer-wise analysis further shows temporal representation dynamics across encoder layers. Guided by these findings, we build a Video-LLM with temporal-aware video-centric encoder, time-preserved projector, and AoT supervision, surpassing human performance on AoT$_{PPB}$ with 98.1\% accuracy, and improving broader temporal reasoning tasks by up to 6.0 points on VITATECS-Direction and 1.3 points on TVBench. Our results show that temporal reasoning in Video-LLMs requires both effective temporal encoding and reliable transfer of this information to the LLM.

---

### Ensemble Distributionally Robust Bayesian Optimisation with Continuous Context

Authors: Tigran Ramazyan, Denis Derkach
Published: 2026-05-08
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2605.07565v2

We study Bayesian Optimisation (BO) in settings where the objective function is influenced by uncontrollable environmental contexts governed by an unknown probability distribution. In practice, the contextual distribution must be estimated from empirical data, a process that inherently introduces distributional mismatch, producing sub-optimal results. While Distributionally Robust Optimisation (DRO) provides a framework to mitigate these risks, existing robust BO methods frequently suffer from high computational complexity, rely on discretisation of continuous context spaces, or impose restrictive assumptions on the structure of the ambiguity set. To overcome these limitations, we propose Ensemble Distributionally Robust Bayesian Optimisation (EDRBO). Our framework leverages the expressive power of ensemble surrogate models to approximate the black-box function while simultaneously accounting for contextual uncertainty. By utilising Wasserstein ball as ambiguity sets, EDRBO provides a robustified acquisition function that remains computationally tractable and natively handles continuous context spaces. We establish a rigorous theoretical foundation for our approach by proving sublinear cumulative regret guarantees of order $\mathcal{O}(γ_T \sqrt{T})$, where $γ_T$ represents the maximum information gain within the ensemble. Finally, we provide extensive empirical evaluations that corroborate our theory and demonstrate the state-of-the-art performance of EDRBO.

---

### Beyond GSD-as-Token: Continuous Scale Conditioning for Remote Sensing VLMs

Authors: Song Zhang, Yanlong Chen, Yilin Li, Yining Chen, Zili Yi, Xiaowei Zhang, Yawei Li
Published: 2026-05-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.07562v1

Remote sensing vision-language models (RS-VLMs) face a fundamental mismatch with natural-image counterparts: the same geographic object exhibits radically different visual evidence across ground sampling distances (GSDs) spanning multiple orders of magnitude. Yet existing RS-VLMs often discard GSD or inject it as a discrete text token, forcing a single static parameter set to absorb the entire scale spectrum. We introduce ScaleEarth, a parameter-efficient fine-tuning framework built on Qwen3-VL that treats GSD as a continuous conditioning variable governing the model's computation path. At its core, CS-HLoRA (Continuous Scale-Conditioned Hyper-LoRA) modulates the LoRA low-rank subspace through a GSD-driven gate, enabling the model to dynamically route computation by physical scale. To remove reliance on sensor metadata at deployment, we pair CS-HLoRA with SSE-U, a lightweight heteroscedastic sub-head that predicts GSD and its uncertainty from visual features. To provide matching supervision, we construct GeoScale-VQA, a 1.5M-sample scale-layered RS-VQA corpus whose question-answer generation is conditioned on the same physical scalar that drives CS-HLoRA, forming a closed method-data loop. Trained with QLoRA on an 8B backbone, ScaleEarth achieves state-of-the-art results on remote-sensing benchmarks covering diverse Earth-system tasks, including XLRS-Bench and OmniEarth-Bench.

---

### Multimodal Stepwise Clinically-Guided Attention Learning for Pathological Complete Response Prediction in Breast Cancer

Authors: Alice Natalina Caragliano, Valerio Guarrasi, Michela Gravina, Carlo Sansone, Paolo Soda
Published: 2026-05-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.07561v1

Pathological complete response (pCR) is a key prognostic factor in breast cancer patients undergoing neoadjuvant therapy, strongly associated with long-term survival and treatment personalization. However, accurate pre-treatment pCR prediction remains challenging due to severe class imbalance and limited generalizability across diverse clinical settings. In this work, we propose a multimodal stepwise clinically-guided attention learning framework for pCR prediction from breast magnetic resonance imaging (MRI), designed to address these limitations through medically grounded spatial guidance and multimodal integration. The approach follows a stepwise training strategy inspired by physician reasoning: the model first learns global discriminative imaging patterns, then attention mechanisms are introduced to constrain the network toward tumor regions, and finally clinical variables are integrated to refine decision-making. This guidance strategy encourages prioritization of task-relevant features, improving identification of responders despite their limited representation in the dataset. Moreover, grounding attention in anatomically consistent tumor regions reduces reliance on dataset-specific patterns, thereby enhancing cross-institutional generalization. The framework is evaluated through external validation across heterogeneous MRI cohorts. Compared to non-guided single-stage baselines, the proposed approach improves sensitivity while maintaining competitive specificity, and produces anatomically coherent attention maps that support interpretation of the model's predictions. These findings highlight the potential of clinically-guided multimodal attention learning for robust and generalizable pCR prediction in breast cancer.

---

### Beyond Distribution Estimation: Simplex Anchored Structural Inference Towards Universal Semi-Supervised Learning

Authors: Yaxin Hou, Jun Ma, Hanyang Li, Bo Han, Jie Yu, Yuheng Jia
Published: 2026-05-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.07557v4

Semi-supervised learning faces significant challenges in realistic scenarios where labeled data is scarce and unlabeled data follows unknown, arbitrary distributions. We formalize this critical yet under-explored paradigm as Universal Semi-supervised Learning (UniSSL). Existing methods typically leverage unlabeled data via pseudo-labeling. However, they often rely on the idealized assumption of a uniform unlabeled data distribution or require sufficient labeled data to estimate it. In the UniSSL setting, such dependencies lead to numerous erroneous pseudo-labels, thereby triggering representation confusion. Fortunately, we observe that inter-sample relations captured by representations are more reliable than pseudo-labels. Leveraging this insight, we shift our focus to representation-level structural inference to bypass distribution estimation. Accordingly, we propose Simplex Anchored Graph-state Equipartition (SAGE), which captures high-order inter-sample dependencies to establish structural consensus for guiding representation learning. Meanwhile, to mitigate representation confusion, we employ vectors that satisfy a simplex equiangular tight frame to serve as a coordinate frame for guiding inter-class representation separation. Finally, we introduce a weighting strategy based on distribution-agnostic metrics to prioritize reliable pseudo-labels and an auxiliary branch to isolate potentially erroneous pseudo-labels. Evaluations on five standard benchmarks show that SAGE consistently outperforms state-of-the-art methods, with an average accuracy gain of $\textbf{8.52%}$.

---

### Dynamic Mode Decomposition along Depth in Vision Transformers

Authors: Nishant Suresh Aswani, Saif Eddin Jabari
Published: 2026-05-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.07556v1

Recent work has shown that contiguous vision transformer (ViT) blocks (a) can be replaced by a linear map and (b) organize into recurrent phases of computation. We ask whether these observations coincide: does ViT depth implement approximately \textit{autonomous linear} dynamics, admitting a single operator $K$ applied recurrently across a contiguous span? We test this using Dynamic Mode Decomposition (DMD), which fits $K$ from selected, consecutive hidden-state pairs and predicts $p$ steps ahead via $K^p$. On four pretrained DINO ViTs, we study the regularization, rank, and calibration budget required for stable fitting. For short spans ($p \leq 4$), $K^p$ tracks an unconstrained endpoint map to within $0.02$ cosine similarity on DINOv3-H/16+, while also recovering intermediate activations at each skipped block. At early cut starts, the fitted operators compress to rank $\ll d$ with minimal calibration data, and across tokens, \texttt{cls} is most amenable to linearization; both properties decay monotonically with depth. Yet this local fidelity does not transfer downstream. At the final hidden state, after propagating through the remaining blocks, an identity baseline becomes competitive.

---

### ProteinJEPA: Latent prediction improves protein language model pretraining

Authors: Dan Ofer, Dafna Shahaf, Michal Linial
Published: 2026-05-08
Categories: cs.LG, cs.AI, q-bio.BM, stat.ML
arXiv: https://arxiv.org/abs/2605.07554v2

Protein language models are trained primarily with masked language modeling (MLM), which predicts masked amino-acid identities. Joint-embedding predictive architectures (JEPA) instead predict latent representations, but have not been applied to proteins. ProteinJEPA supplements MLM with a cosine loss for predicting the half-depth hidden states of a teacher given the unmasked sequence. On 19 tasks, with ESM2 at 35M and 150M parameters and three pretraining seeds, MLM+JEPA outperforms compute-matched and step-matched MLM-only continued training in 78 and 76 of 114 comparisons (14 losses, 22 ties). The median compute-matched gain is $+0.0106$ on structure- and homology-sensitive tasks versus $+0.0041$ elsewhere, led by SCOPe-40 retrieval and remote homology with improvements of 6.1 percentage points in Recall@1 and 2.7 points in accuracy, respectively. Gains on these tasks increase with model size from 8M to 150M. Against the off-the-shelf checkpoint, MLM+JEPA wins 81 of 114 comparisons (median $+0.0068$) without improving MLM loss. In random initialization the gain is smaller and replicates inconsistently across seeds ($p{=}0.059$). The same recipe improves the causal ProGen3 model, beating a compute-matched next-token-prediction control on 12 of 16 tasks. Ablations show that cosine loss beats mean squared error, while adding shallower targets removes most of the task gain. JEPA-only training collapses downstream performance: latent prediction complements MLM rather than replacing it. Code: https://anonymous.4open.science/r/protJepa-FF24

---

### ProteinJEPA: Latent prediction complements protein language models

Authors: Dan Ofer, Dafna Shahaf, Michal Linial
Published: 2026-05-08
Categories: cs.LG, cs.AI, q-bio.BM, stat.ML
arXiv: https://arxiv.org/abs/2605.07554v1

Protein language models are trained primarily with masked language modeling (MLM), which predicts amino-acid identities at masked positions. We ask whether latent-space prediction can complement these token-level objectives under matched wall-clock budget. Across pretrained and random-init protein sequence encoders at 35--150M parameters, we find that the best protein-JEPA design is not all-position latent prediction but a variant: predicting latent targets only at masked positions, and retaining the MLM cross-entropy. We call this recipe masked-position MLM+JEPA. On a 16-task downstream suite (15 frozen linear probes plus SCOPe-40 zero-shot fold retrieval), under matched wall-clock budgets, this recipe wins more tasks than it loses against MLM-only continuation: 10 wins / 3 losses / 3 ties (hereafter W/L/T) on pretrained ESM2-35M, 11/2/3 on ESM2-150M while results in pretraining from scratch are mixed (6/8/2). Gains are seen for multiple models on 11 of 16 tasks, including stability, \b{eta}β\b{eta}-lactamase fitness, variant effect, intrinsic disorder, remote homology, enzyme classification, and SCOPe-40 fold retrieval. Tasks with more losses than wins are Fluorescence (TAPE) and Peptide-HLA Binding. All-position MLM+JEPA matches MLM-only overall but does not reproduce the masked-position gains. JEPA-only (no MLM) collapses in nearly every experiment. We conclude that JEPA, when combined with MLM, is competitive and can outperform pure MLM in pretraining and continued training, even under matched wall-clock budgets.

---

### VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Network

Authors: Zepeng Yang, Junxuan Bai, Hao Li, Ju Dai, Junjun Pan, Yongfeng Yin, Bin Li
Published: 2026-05-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.07552v2

The rapid advances in deep learning have significantly enhanced the accuracy of multimodal 3D human pose estimation (HPE). However, the state-of-the-art (SOTA) HPE pipelines still rely on Transformers, whose quadratic complexity makes real-time processing for long sequences impractical. Mamba addresses this issue through selective state-space modeling, enabling efficient sequence processing without sacrificing representational power. Nevertheless, it struggles to capture complex spatial dependencies in multimodal settings. To bridge this gap, we propose VIMCAN, a hybrid architecture that combines the efficient sequence modeling of Mamba with the spatial reasoning of Cross-Attention, and performs robust visual-inertial fusion and human pose estimation between RGB keypoints and wearable IMU data. By leveraging Mamba's dynamic parameterization for temporal modeling and Attention for spatial dependency extraction, VIMCAN achieves superior accuracy, with mean per-joint position errors (MPJPE) of 17.2 mm on TotalCapture and 45.3 mm on 3DPW. VIMCAN outperforms prior Transformer-based and other SOTA approaches while supporting real-time inference at over 60 frames per second on consumer-grade hardware. The source code is available at \href{https://github.com/Eddieyzp/VIMCAN}{this GitHub repository}.

---

### Disagreement-Regularized Importance Sampling for Adversarial Label Corruption

Authors: Csongor Horváth, Ida-Maria Sintorn, Prashant Singh
Published: 2026-05-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.07551v1

Standard Importance Sampling (IS) collapses under label corruption because high-norm examples, prioritized for variance reduction, are often adversarial outliers. We formalize this misalignment using an $\varepsilon$-contamination model and propose Disagreement-Regularized Importance Sampling (DR-IS), a sub-sampling method based on loss rank-disagreement across independent proxy ensemble. We prove finite-sample concentration bounds showing that the empirical rank disagreement of bulk corrupted examples is bounded above, and that of boundary-clean examples bounded below, both at rate $O(\sqrt{\log(N/δ)/K})$ with probability $1-δ$; when the structural expectation gap $Δ'$ between the two groups is positive and the boundary-clean set is at least as large as the selected subset, these bounds certify strict separation and control the contamination rate of the selected subset. Empirically, DR-IS remains robust under targeted high-norm attacks that break magnitude-based methods such as the Error $L_2$-norm (EL2N) on benchmark datasets. DR-IS complements training-dynamics approaches like Area Under the Margin ranking (AUM), offering improved robustness in the loss-aligned regime alongside explicit finite-sample concentration certificates and a contamination bound limiting noise leakage from the statistical tail of corrupted points.

---

### Mind the Gap: Geometrically Accurate Generative Reconstruction from Disjoint Views

Authors: Grzegorz Wilczynski, Mikołaj Zielinski, Bartosz Świrta, Dominik Belter, Przemysław Spurek
Published: 2026-05-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.07550v1

3D vision systems are fundamentally constrained by their reliance on visual overlap: reconstruction methods require it for geometric alignment, while generative models use it to enforce multi-view consistency. This limitation is particularly acute in real-world scenarios such as distributed swarm robotics or crowd-sourced data collection, where capturing overlapping perspectives, both in terms of spatial and appearance overlap, is often impossible. We introduce Generative Reconstruction from Disjoint Views as a new paradigm, establish a comprehensive dataset, and propose specialized evaluation metrics for zero-overlap scenarios. Our benchmarking demonstrates that existing state-of-the-art methods fail catastrophically on this task, producing disconnected geometries or semantically incoherent reconstructions. To address these limitations, we propose GLADOS, a general, modular framework that operates through three stages: (1) Generative Bridging, where foundation models synthesize intermediate perspectives to connect disjoint inputs; (2) Robust Coarse 3D Reconstruction, that establish coarse geometric scaffold via global alignment which absorbs local contradictions from generative process; and (3) Iterative Context Expansion and Consistency Optimization to fill missing regions and unify the reconstruction. As an architectureagnostic framework, GLADOS enables seamless integration of future advances in generation, reconstruction, and inpainting. The source code is available at: https://github.com/gwilczynski95/GLADOS.

---

### Probabilistic Object Detection with Conformal Prediction

Authors: Christopher Ries, Moussa Kassem Sbeyti, Nicolas Bianco, Nadja Klein
Published: 2026-05-08
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.07549v2

Conformal Prediction (CP) is a distribution-free method for constructing prediction sets with marginal finite-sample coverage guarantees, making it a suitable framework for reliable uncertainty quantification in safety-critical object detection. However, object detection introduces structured multi-output predictions, complicating the application of classical CP theory developed for single outputs. In addition, standard, unscaled CP produces fixed-width prediction intervals across inputs, leading to unnecessary width for low-uncertainty predictions. While scaled CP addresses this by adapting the interval width to an input-dependent uncertainty estimate, prior work has neither systematically compared unscaled and scaled CP for multi-class object detection, nor integrated CP with a complementary uncertainty quantification method in this setting. We fill this gap by: (i) applying CP coordinate-wise to bounding box corners with a Bonferroni correction for box-level guarantees; (ii) scaling the resulting intervals using per-prediction aleatoric uncertainty estimates derived from a probabilistic object detector trained with loss attenuation, evaluated in uncalibrated and two calibrated variants; (iii) extending to a two-step pipeline that constructs prediction sets for the class using RAPS and conditions the conformalized bounding boxes on the predicted class set. Across three autonomous driving datasets (KITTI, BDD, CODA), including a cross-domain setting under distribution shift, scaled CP consistently improves interval sharpness over unscaled CP, achieving up to 19% higher IoU and 39% lower interval scores, without sacrificing coverage. Class-wise calibration further improves coverage for both variants with a negligible effect on sharpness. Together, these improvements yield more actionable uncertainty estimates for real-time, real-world object detection.

---

### Probabilistic Object Detection with Conformal Prediction

Authors: Christopher Ries, Moussa Kassem Sbeyti, Nicolas Bianco, Nadja Klein
Published: 2026-05-08
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.07549v1

Conformal Prediction (CP) is a distribution-free method for constructing prediction sets with marginal finite-sample coverage guarantees, making it a suitable framework for reliable uncertainty quantification in safety-critical object detection. However, object detection introduces structured multi-output predictions, complicating the application of classical CP theory developed for single outputs. In addition, standard, unscaled CP produces fixed-width prediction intervals across inputs, leading to unnecessary width for low-uncertainty predictions. While scaled CP addresses this by adapting the interval width to an input-dependent uncertainty estimate, prior work has neither systematically compared unscaled and scaled CP for multi-class object detection, nor integrated CP with a complementary uncertainty quantification method in this setting. We fill this gap by: (i) applying CP coordinate-wise to bounding box corners with a Bonferroni correction for box-level guarantees; (ii) scaling the resulting intervals using per-prediction aleatoric uncertainty estimates derived from a probabilistic object detector trained with loss attenuation, evaluated in uncalibrated and two calibrated variants; (iii) extending to a two-step pipeline that constructs prediction sets for the class using RAPS and conditions the conformalized bounding boxes on the predicted class set. Across three autonomous driving datasets (KITTI, BDD, CODA), including a cross-domain setting under distribution shift, scaled CP consistently improves interval sharpness over unscaled CP, achieving up to 19% higher IoU and 39% lower interval scores, without sacrificing coverage. Class-wise calibration further improves coverage for both variants with a negligible effect on sharpness. Together, these improvements yield more actionable uncertainty estimates for real-time, real-world object detection.

---

### On the Invariance and Generality of Neural Scaling Laws

Authors: Xing Han, Liu Ziyin, Suchi Saria, Paul Pu Liang
Published: 2026-05-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.07546v2

Neural scaling laws establish a predictable relationship between model performance and data or compute, offering crucial guidance for resource allocation in new domains and tasks. Yet such laws are most needed precisely where they are hardest to obtain: fitting one for a new model task pair demands expensive sweeps that typically exhaust the very compute budget the law is meant to economize. This paper poses the research question of how to develop generalizable scaling laws: laws fit once on a well-resourced source domain and reliably transported to new domains where running a full sweep is infeasible, which requires a fundamental understanding of when and why scaling properties change. We address this by identifying the right invariants: scaling laws are preserved under bijective (information-preserving) transformations of the data and modified in predictable, information-theoretically grounded ways under non-bijective transformations that lower its information resolution $ρ$: a single axis along which a law fit in one domain can be transported to another. We validate this across language, vision, and speech, and demonstrate two cross-domain applications: predicting scaling for language models trained on electronic health records from laws fit on general text, and predicting time-series classification scaling under varying levels of noise injection, recovering the data-scaling exponents to within $3\%$ error.

---