# Research Papers — 2026-06 · bundle page 50 of 260 > Full-text markdown of papers #2451–2500 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/50 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/49.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/51.md) ### Meta-learning as a principle for human-like visual representations Authors: Can Demircan, Marcel Binz, Alireza Modirshanechi, Eric Schulz Published: 2026-06-24 Categories: cs.CV, cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2606.28399v1 The structure of human visual representations underpins our capacity for adaptive behaviour. While pretrained neural networks model human visual representations with unprecedented success, a large discrepancy remains. We propose one reason: these networks optimise a single fixed objective, whereas human representations must support open-ended tasks. We hypothesise this flexibility arises from meta-learning (learning to learn), a pressure shaping representations to acquire new tasks from few observations. To test this, we train a sequence model, without any supervision from human data, across thousands of semantically rich tasks mapping images to high-level concepts. Compared to their pretrained base encoders, meta-learned representations better predict human similarity judgements, semantic rule learning, and high-level visual cortex. Behavioural gains depend on disentangled, high-level task distributions, while brain alignment is driven primarily by the learning-to-learn pressure. Our results suggest the flexibility of human visual representations reflects the functional demand to learn new semantic relationships on the fly. --- ### Semantic-Aware Generative Image Transmission for Resource-Constrained Visual IoT Systems Authors: Chenyang Zhang, Changwang Liu, Jinqi Zhu, Jiayi Chang, Yuxuan Wang, Shuqing He, Jia Guo Published: 2026-06-24 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2606.28398v1 Resource-constrained visual Internet of Things (IoT) systems, such as edge cameras, unmanned sensing platforms, industrial inspection nodes, and remote monitoring sensors, often need to transmit task-relevant visual evidence over low-rate wireless links to an edge/cloud service. Existing image communication methods usually compress or transmit complete global representations, leaving limited room to exploit receiver-side generative restoration. This paper proposes a semantic-aware generative image transmission framework for edge-assisted visual IoT. The image captured by an IoT visual sensor is encoded into a discrete token grid by a VQ encoder. At the IoT transmitter or nearby gateway, token recoverability, estimated from prediction entropy and local structure complexity, is fused with semantic importance obtained from instance segmentation and category-aware scoring. A spatial dispersal sampler then selects the tokens to be transmitted under a bitrate budget. The transmitter sends only the quantization indices of kept tokens and a binary mask map, while the edge/cloud receiver recovers masked tokens through MaskGIT with Halton sequence scheduling. Experiments on Kodak and VisDrone scenes under AWGN and Rayleigh channels show that the proposed method provides a flexible bitrate-quality tradeoff for narrowband visual IoT links. At 0.074 bpp, it uses 44.6% of the transmitted bits of the 0.167-bpp DeepJSCC/WITT reference while achieving 29.9 dB PSNR. A pseudo-GT downstream detection study on Kodak further shows that semantic-aware masking preserves task-relevant objects better than random masking at both 30% and 50% mask ratios. --- ### CLOSER-VLN: Closed-Loop Self-Verified Retrieval-Augmented Reasoning for Aerial Vision-Language Navigation Authors: Shaoxuan Li, Xiangyu Dong, Xiaoguang Ma, Junfeng Chen, Haoran Zhao, Yaoming Zhou Published: 2026-06-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.28397v1 Vision-language navigation (VLN) has recently advanced with large language and multimodal models, enabling agents to follow natural-language instructions in unseen environments without training a task-specific navigation policy. However, most existing VLN methods relying on large models still adopt an open-loop decision-execution approach, where candidate actions are generated from instructions and observations but are rarely verified or corrected before execution. This causes critical issues in aerial VLN, where minor errors in intermediate actions may quickly accumulate into large trajectory deviations and lead to target loss. To address this issue, we propose Closed-loop Self-verified Retrieval-augmented Reasoning (CLOSER), a training-policy-free method that sequentially performs action reasoning, reliability verification, targeted retrieval, and action correction in a closed-loop manner before executing concrete actions. We instantiate the CLOSER in aerial VLN tasks and develop a CLOSER-VLN framework, which is composed of three components: a hierarchical reasoner for generating candidate actions based on available information, a multidimensional action verifier for assessing the reliability of actions generated by the reasoner, and a verification-triggered multimodal retriever for retrieving targeted exemplars from a memory bank only when verification fails. We conduct experimental evaluations on the CityNav benchmark, where CLOSER-VLN achieves 32.01% SR and 21.28% SPL on the test-unseen split, confirming the effectiveness of closed-loop reasoning. --- ### RadarTwin: Scene-Specific mmWave Radar Simulation and Learning for Mobile Indoor Perception Authors: Emily Bejerano, Federico Tondolo, Devang Gupta, Aaron Mano Cherian, Taeyoo Kim, Ayaan Qayyum, Xiaofan Yu, Xiaofan Jiang Published: 2026-06-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.28396v1 Millimeter-wave (mmWave) radar perception is limited by data scarcity: models trained on existing radar datasets fail to generalize to new objects, environments, and sensing trajectories. We present RadarTwin, a framework for generating deployment-specific radar training data before real data collection. Given a 3D reconstruction of a target space (phone LiDAR, robot-mounted sensing, or RGB-to-3D), RadarTwin uses a vision-language model to infer radar-relevant surface materials and a physics-based ray tracer to synthesize raw frequency-modulated continuous-wave (FMCW) radar measurements with multi-bounce propagation. To study what transfers from simulation to reality, we collect a paired real-simulated dataset spanning household objects, material classes, distances, rotations, translations, and mobile sensing trajectories. We show that simulated and real radar share the same object-discriminative shape and material features, and that modeling the environment's multipath is essential to matching real measurements. A representation trained on simulation alone recognizes real objects at 2.5 times chance with no real radar labels, and a few labeled examples raise this to 95.3% on a 12-way recognition task. RadarTwin enables training radar perception for a new space before any real radar data is collected there. --- ### JASPR: Joint Spatial Representation learning of histology and spatial genomics for improved virtual genomic screening and clinical prognostication Authors: Marija Pizurica, Eric Zimmermann, Neil Tenenholtz, James Hall, Olivier Gevaert, Ava P. Amini, Lorin Crawford, Kristen A. Severson Published: 2026-06-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.28395v1 Recent studies have shown that spatial properties of tumors are critical for understanding disease biology and predicting patient outcomes. These spatial properties are increasingly uncovered through complementary modalities: spatial transcriptomics (ST) captures spatially-resolved molecular states, while hematoxylin and eosin-stained whole slide images (HE) reveal tissue morphology. While approaches are emerging to fuse these modalities, effective methods that learn not only joint representations but also incorporate spatial context across modalities are lacking. Here, we present JASPR (Joint Spatial Representation learning), a self-supervised deep learning framework that integrates HE images and ST data through a cross-modal reconstruction objective that incorporates spatial context within HE images and ST profiles. It employs shared modules to capture universal spatial properties across modalities, while modality-specific experts encode features unique to morphological and genomic data. We train and validate JASPR on breast cancer datasets, demonstrating that its learned joint representation substantially improves HE-based prediction of 9,248 genes and provides prognostic value for breast cancer outcomes. --- ### Recall Before Rerank: Benchmarking Deep Learning Models for Large-Scale Code-to-Code Retrieval Authors: Leonardo Venuta, Francesco Tosoni, Paolo Ferragina Published: 2026-06-24 Categories: cs.SE, cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2606.27401v2 Semantic code search and clone detection are essential for software development, maintenance, and reuse. This paper evaluates the effectiveness, efficiency, and scalability of contemporary deep learning models for first-stage recall in large-scale code-to-code search engines. Benchmarking across multiple programming languages and datasets reveals critical limits in the precision and scalability of these models on Terabyte-scale source-code collections. We present LLM-based code normalisation and query-rewriting schemes that yield significant gains in precision for lower-performing models. Our results question the sustainability of resource-constrained deployment and the assumed robustness of current code-specialised LLMs across datasets. We conclude with actionable insights for building scalable, efficient code-retrieval systems. --- ### Recall Before Rerank: Benchmarking Deep Learning Models for Large-Scale Code-to-Code Retrieval Authors: Leonardo Venuta, Francesco Tosoni, Paolo Ferragina Published: 2026-06-24 Categories: cs.SE, cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2606.27401v1 Semantic code search and clone detection are essential for software development, maintenance, and reuse. This paper evaluates the effectiveness, efficiency, and scalability of contemporary deep learning models for first-stage recall in large-scale code-to-code search engines. Benchmarking across multiple programming languages and datasets reveals critical limits in the precision and scalability of these models on Terabyte-scale source-code collections. We present LLM-based code normalisation and query-rewriting schemes that yield significant gains in precision for lower-performing models. Our results question the sustainability of resource-constrained deployment and the assumed robustness of current code-specialised LLMs across datasets. We conclude with actionable insights for building scalable, efficient code-retrieval systems. --- ### SidConArena: An Environment Evaluating Agents in Open-Ended,Positive-Sum Bargaining Game Authors: Yeqi Feng, Yuxin Chen, Tianxing He Published: 2026-06-24 Categories: cs.MA, cs.AI, cs.GT arXiv: https://arxiv.org/abs/2606.27397v1 Evaluating LLM agents requires dynamic environments that go beyond static reasoning and zero-sum games. Real-world economic interaction is often open-ended and mixed-motive: agents must negotiate, create positive-sum surplus, compete for scarce assets, and plan under delayed returns. We introduce SidConArena, a new benchmark framework for evaluating LLM agents in open-ended, positive-sum bargaining. SidConArena formalizes a multi-player economy as a finite-horizon partially observable stochastic game with three coupled phases: natural-language negotiation with binding trades, deterministic converter-based production, and sealed-bid auctions for long-term assets. The framework combines structured observations, phase-aware agent dispatching, a neural-symbolic action interface, and asynchronous execution, enabling free-form interaction while preserving rule-grounded evaluation. Across homogeneous and heterogeneous tournaments, stronger frontier models achieve higher economic outcomes, yet agents still misvalue resources, bargain passively, and remain limited in long-horizon investment planning. --- ### Finding the Time to Think: Learning Planning Budgets in Real-Time RL Authors: Aneesh Muppidi, Firas Darwish, Dylan Cope, João F. Henriques, Jakob Nicolaus Foerster Published: 2026-06-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.26463v2 Deliberating takes time. In real-time settings, that time is not free. Standard reinforcement learning (RL) sidesteps this as the environment waits indefinitely for the agent's decision. Instead, we study real-time RL environments where the environment progresses while waiting for the agent's action. Building on prior real-time formalizations, we introduce variable-delay real-time RL, where the agent chooses how long to deliberate at each decision point since the environment progresses. For the planning agents we use, the right delay is state-dependent, and naively planning how long to plan can paralyze the agent. We instead approach this setting by training a lightweight gating policy on top of a planner to select state-dependent planning budgets. Across real-time Pac-Man, Tetris, Snake, Speed Hex, and Speed Go, our gating policy outperforms fixed-budget and heuristic baselines, and transfers to a real-time setup where the environment and agent run on two different GPUs. --- ### auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation Authors: Ben Prystawski, Kushin Mukherjee, Daniel Wurgaft, Linas Nasvytis, Michael Y. Li, Noah D. Goodman, Michael C. Frank Published: 2026-06-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26460v1 AI-based scientific automation is increasingly possible by using agents to generate hypotheses, design experiments, and analyze data. Data collection is a major bottleneck in this pipeline, however. Psychology, and computational cognitive science in particular, is well-positioned to benefit from AI experimentation because theories are often represented as code and crowdsourcing platforms enable programmatic human data collection at scale. Here, we apply automated discovery techniques to the project of generating theories in computational cognitive science, with an agent-based system collecting human data independently through crowdsourced survey experiments. As a testbed, we use a classic case study from cognitive psychology: judging which sequences of coin flips seem subjectively more random. Our system, auto-psych, uses nested agent-based discovery loops to generate explanatory theories of human behavior. The inner loop conjectures, fits, and critiques probabilistic cognitive models; the outer loop designs experiments to test these models, launches them online, and analyzes the data. This system can quickly and reliably recover ground-truth theories from synthetic data via systematic experimentation, but the nested structure is critical to model performance. Further, in three independent sequences of human experiments, the system finds theories that fit the data better than theories generated from the scientific literature. This work thus demonstrates the feasibility of automated data collection and theory discovery in computational cognitive science. --- ### MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation Authors: Xiaochen Wang, Bao Hoang, Han Liu, Ting Wang, Fenglong Ma Published: 2026-06-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26458v1 Retrieval-augmented generation (RAG) over knowledge graphs has emerged as a promising approach for grounding large language models, yet existing benchmarks largely overlook the challenges of retrieval in multimodal knowledge graph RAG (MKG-RAG). In practice, retrieval is a critical bottleneck: multimodal knowledge is heterogeneous, difficult to align across modalities, and often poorly served by retrievers designed for unstructured corpora. To address this gap, we introduce MKG-RAG-Bench, a cross-domain benchmark explicitly designed to evaluate retrieval in MKG-RAG. MKG-RAG-Bench is constructed from two multimodal knowledge graphs spanning general and medical domains, and includes carefully aligned question-answering datasets that support controlled evaluation of both retrieval and downstream generation. The benchmark is built using an LLM-based curation pipeline that filters low-utility knowledge, generates structurally grounded queries with exact supervision, and systematically covers diverse modality configurations. Through extensive experiments across representative retriever families and modality settings, we show that effective multimodal retrieval remains challenging yet crucial for end-to-end MKG-RAG performance, and that retrieval quality strongly determines generation outcomes. By isolating retrieval as a first-class evaluation target, MKG-RAG-Bench provides a principled foundation for diagnosing current limitations and advancing multimodal knowledge graph RAG systems. --- ### A probabilistic framework for online test-time adaptation Authors: Daniel Corrales, David Ríos Insua Published: 2026-06-24 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2606.26457v1 This paper presents a probabilistic framework for online test-time adaptation problems. In them, a model is trained on labeled data but must adapt to unlabeled data at test time under the assumption that training and test distributions potentially differ, that is, there might have been a distributional shift. The framework is based on a state-space modelling architecture from which parameter learning, parameter time evolution, prior tuning, and prediction can be characterized. --- ### Active Adversarial Perturbation-driven Associative Memory Retrieval for RGB-Event Visual Object Tracking Authors: Xiao Wang, Xufeng Lou, Zikang Yan, Lan Chen, Sibao Chen, Yaowei Wang, Yonghong Tian, Jin Tang Published: 2026-06-24 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.26455v1 RGB-Event tracking improves localization robustness by fusing RGB appearance textures and dense temporal motion cues from event sensors. While this multi-modal scheme broadens tracking applicability, real-world scenes suffer diverse structured signal degradations that hinder traditional multi-modal fusion. In harsh environments, either modality can lose reliability drastically, and targets frequently appear incomplete due to occlusion, edge truncation and foreground clutter.To tackle the above challenges, we present a hierarchical perturbation and retrieval framework tailored for RGB-Event tracking with robustness against partial target missing and modal degradation, termed APRTrack. To mimic real-world signal corruption, APRTrack constructs structured degradation via two adversarial perturbation branches at the modality and spatial levels, which separately simulate full-modal failure and localized target region absence. A hierarchical routing mechanism is designed to disentangle the training pipelines of the two perturbation types, effectively eliminating feature collapse induced by superimposed degradation constraints. Furthermore, we devise Footprint-guided Channel-calibrated Hopfield Retrieval (FCHR) for reliable historical information compensation. This module evaluates retrieval confidence based on association footprints between queries and memory banks, and calibrates the retrieval metric space prior to Hopfield matching, realizing controllable historical feature compensation bounded to target regions. Extensive experiments on FE108, COESOT, VisEvent, and FELT datasets demonstrate the effectiveness of our proposed strategies for the RGB-Event visual object tracking. The source code and pre-trained models will be released on https://github.com/Event-AHU/OpenEvTracking --- ### Data-driven Machine Learning Cannot Reach Symbolic-level Logical Reasoning -- The Limit of the Scaling Law Authors: Tiansi Dong, Mateja Jamnik, Pietro Liò Published: 2026-06-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26454v2 By promoting vectors to spheres and enabling explicit model construction, neural networks can perform symbolic-level syllogistic reasoning without training data. We identify two fundamental limitations that prevent conventional data-driven machine learning systems from achieving this capability: training data generated by the combination table cannot distinguish all 24 valid syllogism types, and end-to-end premise-to-conclusion mapping creates contradictory targets within neural components. Experiments with two representative conventional systems, GPT-5 using linguistic inputs and Euler Net using visual inputs, support this analysis. ChatGPT GPT-5 may reach 100% accuracy in syllogistic reasoning, but with hallucinations. Because the learning process terminates upon reaching 100% accuracy, the system cannot progress beyond empirical accuracy to symbolic level reasoning. Random test data reduced Euler Net's accuracy to 56%. Repeatedly expanding the training set increased its accuracy to 97%, with perfect performance on 8 syllogism types. However, because unintended inputs cannot be exhaustively covered, even 100% test accuracy does not imply symbolic-level reasoning. Since syllogistic reasoning underpins logical reasoning and human rationality, these results suggest that increasing data and training time alone cannot ensure symbolic level logical reasoning. --- ### Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization Authors: Jiading Gai, Shuai Zhang, Kaj Bostrom, Jin Huang, Vihang Patil, Haoyang Fang, Bernie Wang, Huzefa Rangwala, George Karypis Published: 2026-06-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.26453v2 We present KernelPro, a closed-loop multi-agent system that automatically generates, profiles, and iteratively optimizes GPU kernel code by integrating large language model (LLM) code generation with hardware profiler feedback and pluggable bottleneck detection tools. KernelPro introduces four contributions: (1) a semantic feedback operator that encodes expert heuristics as pluggable micro-profiling tools, transforming raw hardware metrics into actionable natural language guidance; (2) a two-stage tool invocation architecture where roofline-based bottleneck classification filters which specialized analysis tools execute, combining kernel-level (ncu), instruction-level (SASS), and system-level (nsys) profiling; (3) a domain-adapted MCTS with progressive widening, asymmetric branching, log-reward calibration, dead-end pruning, and search memory for cross-iteration learning; and (4) direct CuTe source-level code generation via autonomous code search over the CUTLASS/CuTe codebase. On KernelBench, KernelPro achieves geometric mean speedups of 2.42x/4.69x/5.30x on Levels 1/2/3, establishing state-of-the-art performance across all difficulty levels. On VeOmni's expert-optimized MoE training kernels, KernelPro achieves 1.23x over hand-tuned Triton by generating a from-scratch raw-CUDA+CuTe Hopper WGMMA kernel. Ablation studies demonstrate that each design component independently and significantly improves optimization quality: micro-profiling tools (p < 0.0001 vs raw metrics), MCTS search (26% higher geometric mean vs greedy, p = 0.004), and proactive tool orchestration (23% improvement, p = 0.035). Finally, KernelPro is the first CUDA kernel coding agent to optimize energy efficiency beyond the speed-only focus of prior systems, demonstrating an 11.6% measured energy reduction at matched speed. --- ### Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization Authors: Jiading Gai, Shuai Zhang, Kaj Bostrom, Jin Huang, Vihang Patil, Haoyang Fang, Bernie Wang, Huzefa Rangwala, George Karypis Published: 2026-06-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.26453v1 We present KernelPro, a closed-loop multi-agent system that automatically generates, profiles, and iteratively optimizes GPU kernel code by integrating large language model (LLM) code generation with hardware profiler feedback and pluggable bottleneck detection tools. KernelPro introduces four contributions: (1) a semantic feedback operator that encodes expert heuristics as pluggable micro-profiling tools, transforming raw hardware metrics into actionable natural language guidance; (2) a two-stage tool invocation architecture where roofline-based bottleneck classification filters which specialized analysis tools execute, combining kernel-level (ncu), instruction-level (SASS), and system-level (nsys) profiling; (3) a domain-adapted MCTS with progressive widening, asymmetric branching, log-reward calibration, dead-end pruning, and search memory for cross-iteration learning; and (4) direct CuTe source-level code generation via autonomous code search over the CUTLASS/CuTe codebase. On KernelBench, KernelPro achieves geometric mean speedups of 2.42x/4.69x/5.30x on Levels 1/2/3, establishing state-of-the-art performance across all difficulty levels. On VeOmni's expert-optimized MoE training kernels, KernelPro achieves 1.23x over hand-tuned Triton by generating a from-scratch raw-CUDA+CuTe Hopper WGMMA kernel. Ablation studies demonstrate that each design component independently and significantly improves optimization quality: micro-profiling tools (p < 0.0001 vs raw metrics), MCTS search (26% higher geometric mean vs greedy, p = 0.004), and proactive tool orchestration (23% improvement, p = 0.035). Finally, KernelPro is the first CUDA kernel coding agent to optimize energy efficiency beyond the speed-only focus of prior systems, demonstrating an 11.6% measured energy reduction at matched speed. --- ### AnySimLite: A Lightweight Few-Shot Similarity Encoder for On-Device Speech-Adjacent Classification Authors: Sourav Ghosh, Yash Bhatia, Keshav Goyal, Sahil Singh Bagri, Mohamed Akram Ulla Shariff, Saravana Balaji Shanmugam Published: 2026-06-24 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2606.26452v1 To minimize privacy concerns and inference latency on edge devices like smartphones, lightweight on-device models remain important for end-user applications. Many of these applications involve natural language classification, but deploying multiple specialized models creates a memory footprint challenge. We investigate: Can a single lightweight architecture solve multiple Speech-Adjacent (SA) classification tasks through reduction to a nuanced text similarity formulation? We propose AnySimLite, a lightweight similarity encoder that combines word-level and character-level channels. Together with a dataset transformation strategy, we evaluate AnySimLite across multiple SA classification tasks and show that it consistently achieves state-of-the-art (SOTA) or SOTA-competitive performance in few-shot settings while maintaining a low memory footprint. Even in the worst case, the performance drop remains below 7% while using $<\frac{1}{250}^{\mathrm{th}}$ of the model size of the SOTA qLLaMA_LoRA-7B baseline. --- ### Listening Like a Judge: A Music-Aware Framework for Automatic Singing Performance Evaluation Authors: Neelam Saini, Sourav Ghosh Published: 2026-06-24 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2606.26451v1 Automatic singing quality assessment (SQA) requires evaluating lyrical correctness and musical fidelity while handling expressive variations. However, existing systems largely rely on either acoustic cues or lyric transcriptions exclusively, limiting holistic performance evaluation. Furthermore, their integration is non-trivial due to challenges in robust singing transcription amid melisma, vibrato, and tempo elasticity. To this end, we propose MusicJudge, a modality-guided framework for automated SQA that performs block-aligned multimodal analysis by coupling lyric correctness with pitch-rhythm fidelity. It detects semantically meaningful lyric blocks using multi-signal matching that integrates semantic embeddings, lexical similarity, and phonetic alignment. To improve singing audio transcription, we introduce Modality-Guided LoRA for ASR fine-tuning. Experiments across datasets demonstrate strong agreement with human expert judgments and validate the generalizability of MusicJudge. --- ### ProvenAI: Provenance-Native Traces of Evidence in Generated Answers Authors: Mohammad Faizan, Dalal Alharthi Published: 2026-06-24 Categories: cs.CL, cs.AI, cs.CR, cs.IR arXiv: https://arxiv.org/abs/2606.26449v1 Retrieval-augmented systems routinely present citations alongside generated answers, yet a citation does not confirm that the corresponding source meaningfully shaped the output. This paper introduces ProvenAI, a framework that decomposes transparency in multi-hop question answering into three independently measurable layers: answer correctness, citation fidelity against benchmark supporting evidence, and per-document influence under leave-one-resource-out intervention. Targeting the HotpotQA distractor benchmark through a seven-stage pipeline covering data normalisation, retrieval indexing, citation-aware answer generation, attribution auditing, ablation-based influence estimation, batch evaluation, and interactive inspection, ProvenAI evaluates 7,405 validation examples drawn from a canonical corpus of 509,300 passages. The system achieves 53.53% answer accuracy alongside a mean citation-fidelity score of 71.55%, and a worked example surfaces what we call the citation-influence gap: a clean citation audit co-occurring with a profile in which one cited source registers only weak influence while seven uncited sources demonstrably shift the output. We formalise the relationship between the implemented surface proxy and a token-level KL-divergence target through a stated faithfulness condition, ground the framework in causal-mediation analysis and database-provenance theory, and discuss how the three measurement layers compose with cryptographic provenance architectures emerging in autonomous scientific discovery. ProvenAI establishes that meaningful transparency in retrieval-grounded QA requires traceable links across retrieved, cited, and behaviourally influential evidence as three distinct, independently measured layers. --- ### Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist Authors: Akshay K. Jagadish, Younes Strittmatter, Nori Jacoby, George Kachergis, Eric Schulz, Nathaniel Daw, Suyog H. Chandramouli, Thomas L. Griffiths Published: 2026-06-24 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2606.26448v1 Across the sciences, autonomous systems are increasingly being used in closed-loop discovery, proposing new theories and designing and running experiments to test them. This approach is yet to be applied in the field of cognitive science, where the central bottleneck is theory-building: the creative step of turning the accumulated failures of existing models into better ones. Theory generation has remained manual even as data collection, modeling, and experiment design have been automated. We present the Automated Cognitive Scientist (AutoCog), a fully autonomous agentic-AI system that closes this loop. Large-language-model agents advocate competing theories, each expressed as an executable cognitive model, design experiments that best discriminate them, collect behavioral data from participants recruited online, score theories against collected data based on their generative performance, diagnose why they fail, and synthesize a better successor. Repeating this cycle allows them to search the space of theories, models, and experiments. In the domain of decision-making, AutoCog recovered known decision-making strategies from simulated behavior, including unconventional ones, showing that its discoveries are ultimately driven by the data rather than strictly bound by the priors of the underlying language models. When run with human participants, it produced theories that outperformed the established theories it was seeded with and generalized to held-out studies in two different experimental settings. It also surfaced a novel theory of multi-cue decision-making in which choices show diminishing sensitivity to feature values. The distinctive predictions of this theory were confirmed in a preregistered study with new participants. AutoCog demonstrates how an automated discovery system can be used to turn cognitive theory-building into an explicit, executable, and cumulative science. --- ### WatchAct: A Benchmark for Behavior-Grounded Robot Manipulation Authors: Baiqi Li, Ce Zhang, Yu Fang, Yue Yang, Shangzhe Li, Mingyu Ding, Gedas Bertasius Published: 2026-06-24 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2606.26443v1 A robot working alongside people must reason about what they have done, in what order, and with what intent. Video carries the spatial layouts, object histories, and gestures that language leaves underspecified, yet today's manipulation benchmarks pair an instruction with a single current image, offering no way to evaluate reasoning over observed human behavior. We introduce WatchAct, a benchmark for robot manipulation grounded in observed human behavior. Each instance pairs a real-world human-action video and a language instruction with an aligned simulator scene and an executable LIBERO task, enabling scalable and reproducible evaluation. WatchAct comprises 3,000 long-horizon instances across 14 tasks in four capability domains drawn from the cognitive demands of watching another agent: parsing events (Event Grounding), recovering procedural structure (Procedural Reasoning), inferring unstated intent (Implicit Intent Inference), and tracking how the scene was changed (Episodic Reasoning). We further propose a disentangled evaluation protocol that separately measures (i)~video-to-plan reasoning by vision-language models, (ii)~policy execution under oracle plans, and (iii)~full task completion by integrated planner--policy pipelines. In both simulation and on a Franka Research 3 robot, current systems remain far from solving WatchAct. The best pipeline, Gemini-3.1-Pro with $π_{0.5}$, reaches only 16.3% Success Rate (SR) in simulation and 14.0% on the real robot. Gemini-3.1-Pro attains just 36.8% Plan SR (vs. 97.1% for humans), while $π_{0.5}$ reaches only 21.5% Task SR under oracle plans and drops to 10.6% on out-of-domain scenarios. Dataset and code are available at https://baiqi-li.github.io/watchact_page/. --- ### AXLE: A Cloud Infrastructure for Lean 4 Theorem Proving Utilities Authors: Jimmy Xin, Alex Schneidman, Chris Cummins, Karun Ram, Srihari Ganesh, Jannis Limperg Published: 2026-06-24 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2606.26442v1 We present AXLE (Axiom Lean Engine), a cloud service for Lean 4 proof manipulation, extraction, and verification. Recent progress in AI for mathematics -- reinforcement learning pipelines, agentic proving workflows, dataset curation -- demands Lean 4 tooling that scales to millions of requests while remaining correct and robust; existing infrastructure offers parallel compilation but not scalable proof verification, higher-level proof manipulation, multi-version support, or per-request isolation at the throughput modern AI workflows require. AXLE provides 14 Lean 4 metaprogramming tools spanning strict proof verification, declaration metadata extraction, semantic source manipulation, deterministic proof repair and simplification, and lemma extraction. The service runs as a multi-tenant cloud deployment with per-request isolation and concurrent support for multiple Lean 4 and Mathlib versions, accessible via a Python SDK, command-line interface, web UI, MCP server, and raw HTTP API. AXLE is publicly available and free to use at https://axle.axiommath.ai and via the axiom-axle PyPI package, with no local Lean 4 installation required. It has served over 500 million requests to date and is the underlying infrastructure for Axiom Math's proving efforts, including its 12/12 score on the 2025 Putnam competition. --- ### ConflictScore: Identifying and Measuring How Language Models Handle Conflicting Evidence Authors: Siyi Liu, Aaron Halfaker, Dan Roth, Patrick Xia Published: 2026-06-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.26437v1 Existing metrics for factuality and faithfulness evaluate whether an answer is supported or contradicted by its grounding documents, but they fail to capture when both supporting and contradicting evidence coexist. We introduce ConflictScore, a novel metric that quantifies how well a model's response acknowledges conflicting evidence in its grounding documents. Our framework decomposes responses into atomic claims, labels each claim against each grounding document, and then aggregates these labels into two complementary measures: ConflictScore-Count (CS-C), the proportion of claims exhibiting conflicts, and ConflictScore-Ratio (CS-R), the balance between supporting and contradicting evidence. We develop ConflictBench, a benchmark covering diverse forms of conflicts such as ambiguity, contradiction, and divergent opinions, to systematically evaluate our metric. Experiments show that ConflictScore effectively detects overconfident claims across domains and can serve as a corrective feedback mechanism that improves truthfulness on TruthfulQA. --- ### Embedding Foundation Model Predictions in Discrete-Choice Models with Structural Guarantees Authors: Yingshuo Wang, Xian Sun, Yanhang Li, Zhichao Fan, Zexin Zhuang Published: 2026-06-24 Categories: cs.LG, econ.EM arXiv: https://arxiv.org/abs/2606.26432v1 Tabular foundation models achieve strong accuracy on choice prediction tasks, but their predictions often violate the economic logic those tasks require: raising a price can increase predicted demand, implied willingness-to-pay estimates are frequently negative or implausible, and unavailable alternatives receive nonzero probability. We propose a two-stage adapter that takes a foundation model's predicted choice probabilities as a precomputed feature and embeds them inside a multinomial logit's utility. In Stage 1, we fit the multinomial logit's structural coefficients by maximum likelihood with sign constraints; in Stage 2, we freeze those coefficients and fit a small neural correction operating on the foundation model's predictions. We prove that this composition exactly preserves the multinomial logit's marginal rate of substitution, so analytically computable value-of-time becomes a mathematical guarantee rather than an empirical accident. Across three datasets and two foundation models, the adapter gains 6.4 percentage points (pp) of test accuracy on average over the multinomial logit and up to 12.8 pp, maintains 100% cost monotonicity, and produces values of time within the published transportation-economics range on the transportation datasets. Performance degrades gracefully under foundation-model context restriction, retaining at least 6 pp of accuracy gain even at 10% of the original foundation-model context. --- ### Revealing Mammographic Phenotypes in Deep Learning Breast Cancer Risk Models Authors: Ruiyu Jia, Yanqi Xu, Yuxuan Chen, Yiqiu Shen, Laura Heacock Published: 2026-06-24 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2606.26431v1 Mammogram-based deep learning models have improved breast cancer risk prediction, but the learned imaging patterns remain underexplored. Existing interpretability methods rely on single-image saliency maps, failing to identify recurring mammographic phenotypes across large patient cohorts. By clustering patch embeddings from a pre-trained model, Mirai, we isolate recurring phenotypes linked to 5-year cancer risk. Analyses show risk-increasing phenotypes capture complex structures (e.g., dense tissue, microcalcifications) and shortcut artifacts (e.g., clips). These phenotypes correlate strongly with older age and higher BI-RADS density. Our framework connects tissue patterns to AI risk scores, revealing clinical signatures and potential latent model confounders. --- ### DualEval: Joint Model-Item Calibration for Unified LLM Evaluation Authors: Aaron J. Li, Hao Huang, Youngmin Park, Yitong Ma, Wei-Lin Chiang, Li Chen, Cho-Jui Hsieh, Bin Yu, Ion Stoica Published: 2026-06-24 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.26429v1 Current LLM evaluation relies on two complementary but often disconnected signals: static benchmarks with objective correctness labels and arena-style preference data that better reflect open-ended user interactions. We introduce DualEval, a latent model-item calibration framework that represents models and evaluation items in a shared space, jointly estimating model ability together with item difficulty and sharpness. We apply DualEval across four domains: coding, math, miscellaneous domain-knowledge tasks, and generic everyday user queries. Our evaluation uses 18 frontier LLMs, static benchmark labels, and reward-model scores validated against held-out human preferences for open-ended model responses. Empirically, our framework produces reliable and balanced model rankings, and its learned item-level profiles support downstream applications such as benchmark compression for sample-efficient evaluation and anomaly detection for contamination or outlier analysis. Overall, DualEval unifies static and arena-style evaluation through joint model-item calibration, producing model rankings and item-level diagnostics that support more sample-efficient, interpretable, and auditable evaluation pipelines. --- ### Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly? Authors: Tyler Ga Wei Lum, Kushal Kedia, C. Karen Liu, Jeannette Bohg Published: 2026-06-24 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.26428v3 Multi-fingered robots promise the speed and dexterity of human hands, yet challenging problems such as precise assembly have remained out of reach. These tasks are contact-rich, making data collection for imitation learning difficult, and sparse-reward, making direct exploration with reinforcement learning (RL) intractable. Consequently, prior work has made progress by structuring the problem with specialized grippers, tool attachments, and environment fixtures. In this work, we argue that before a robot can perfect precise assembly, it must first learn to play. We further ask the question: what factors in the process of learning to play matter for precise assembly? We propose Play2Perfect, an RL framework for task-agnostic pretraining through play on diverse objects and goals, which is then perfected on precise assembly. The goal of play is to acquire reusable manipulation priors, such as grasping, in-hand reorientation and pose reaching. Finetuning then adapts this general prior to assembly, focusing exploration on the final contact-rich, high-precision interactions needed for success. We systematically study key design choices in play pretraining, including object diversity, training objective, trajectory diversity, and goal precision. We show that our prior is 33x more sample-efficient than RL training from scratch, even when provided with dense, multi-stage rewards. We demonstrate zero-shot sim-to-real transfer, achieving 60% success on tight insertions with only 0.5 mm contact clearance, and over 50% success on long-horizon multi-part assembly and screwing. --- ### Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly? Authors: Tyler Ga Wei Lum, Kushal Kedia, C. Karen Liu, Jeannette Bohg Published: 2026-06-24 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.26428v2 Multi-fingered robots promise the speed and dexterity of human hands, yet challenging problems such as precise assembly have remained out of reach. These tasks are contact-rich, making data collection for imitation learning difficult, and sparse-reward, making direct exploration with reinforcement learning (RL) intractable. Consequently, prior work has made progress by structuring the problem with specialized grippers, tool attachments, and environment fixtures. In this work, we argue that before a robot can perfect precise assembly, it must first learn to play. We further ask the question: what factors in the process of learning to play matter for precise assembly? We propose Play2Perfect, an RL framework for task-agnostic pretraining through play on diverse objects and goals, which is then perfected on precise assembly. The goal of play is to acquire reusable manipulation priors, such as grasping, in-hand reorientation and pose reaching. Finetuning then adapts this general prior to assembly, focusing exploration on the final contact-rich, high-precision interactions needed for success. We systematically study key design choices in play pretraining, including object diversity, training objective, trajectory diversity, and goal precision. We show that our prior is 33x more sample-efficient than RL training from scratch, even when provided with dense, multi-stage rewards. We demonstrate zero-shot sim-to-real transfer, achieving 60% success on tight insertions with only 0.5 mm contact clearance, and over 50% success on long-horizon multi-part assembly and screwing. --- ### Rethinking Training & Inference for Forecasting: Linking Winner-Take-All back to GMMs Authors: Qiyuan Wu, Katie Z Luo, Bharath Hariharan, Wei-Lun Chao, Mark Campbell Published: 2026-06-24 Categories: cs.LG, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2606.26424v1 Trajectory forecasting for autonomous driving has advanced rapidly, yet representative models often produce uninformative posteriors over forecast modes, causing problems for mode pruning. We trace this to a modeling-training mismatch: forecasters are typically modeled as conditional Gaussian mixture models (GMMs) but trained with a winner-take-all (WTA) loss that assigns each sample to its nearest mode. We argue that this K-means-like hard assignment (one-hot), while preventing mode collapse, is the source of uninformative mode probabilities: it over-segments the trajectory space, ignores relatedness among nearby modes, and yields assignment instability under small perturbations. Guided by this lens, we introduce two post-hoc treatments: (1) test-time posterior-weighted merging that aggregates nearby candidate trajectories; and (2) a one-step expectation-maximization (EM) update that replaces hard labels with soft responsibilities, sharing probability mass across neighboring modes. Across several WTA-trained architectures, these lightweight steps produce more informative, faithfully ranked mode posteriors and strengthen final forecasts on popular displacement metrics -- without retraining. Our analysis unifies recent design choices through a GMM-vs-K-means perspective and offers principled, practical corrections that better align training objectives with inference. --- ### CoStream: Composing Simple Behaviors for Generalizable Complex Manipulation Authors: Haonan Chen, Yuxiang Ma, Stephen Tian, Xiaoshen Han, Wenlong Huang, Feiyang Wu, Yunzhu Li, Jiajun Wu, Edward H. Adelson, Yilun Du Published: 2026-06-24 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.26423v2 Long-horizon, contact-rich complex manipulation tasks, such as seating a GPU into a PCIe slot, demand both millimeter high precision and out-of-the-box generalization to new tasks. Existing paradigms struggle to satisfy both: classical pipelines use brittle, task-specific interfaces to achieve high-precision control but require costly pipeline redesigns to adapt to new tasks, whereas monolithic end-to-end policies provide better generalization but lack high precision on complex, out-of-distribution tasks unless retrained with new data. Both paradigms share an implicit assumption: once a manipulation capability is acquired, it must be deployed as a rigid pipeline or monolithic whole, rather than being freely decomposed and recomposed. In this paper, we show that complex manipulation capabilities can emerge naturally from the composition of simple, independent behaviors. Rather than deploying a monolithic policy or a rigid pipeline, we propose CoStream, a framework orchestrating foundation models and diverse sensing modalities into multiple composable core behaviors: a semantic behavior extracting spatial constraints via foundation models; a predictive behavior forecasting trajectories by tracking keypoints in imagined videos; and a reactive behavior providing high-frequency tactile and force corrections. On a shared $SE(3)$ interface, these outputs compose by right-multiplication into a single pose command at each control step, executed by a compliant controller. We demonstrate CoStream on 8 real-world tasks spanning everyday manipulation and precision assembly, with the strongest gains in contact-rich assembly and object transfer, and show robust recovery from manual perturbations during execution. Website: https://costream-simple.github.io --- ### Estimating Uncertainty in Classifier Performance with Applications to Large Language Models and Nested Data Authors: Kylie Anglin Published: 2026-06-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26422v1 Researchers increasingly use text classification--supervised models or large language models--to measure constructs from natural language, providing metrics such as recall and precision as evidence of their validity. Yet, though these metrics are point estimates subject to sampling variation, measures of uncertainty are inconsistently reported alongside them. Further, when they are reported, they are often estimated with methods that are not appropriate when relevant labelled datasets are small or performance is high. To increase and improve confidence interval reporting in the field, this paper evaluates confidence interval methods for performance metrics under conditions typical of social science text classification: small to moderate sample sizes, infrequent constructs, and texts nested within individuals. Across simulations, default methods such as the Wald interval and the basic percentile bootstrap are the least accurate, with coverage sometimes far below the nominal 95% level. Accuracy is improved with the use of Agresti-Coull, Wilson, Clopper-Pearson, and a novel pseudo-count regularized bootstrap (which is particularly relevant to the calculation of F1). When texts are nested within individuals, we demonstrate that adjustment for both effective N and the appropriate degrees of freedom is necessary for producing accurate analytic intervals. Among bootstrap intervals, the hierarchical bootstrap is more accurate than the cluster bootstrap when individuals produce a moderate number of texts but overly conservative when individuals produce only a few. By providing guidance to the field on appropriate interval estimation, we aim to improve the transparency of machine learning applications, and to encourage greater attention to the validation sample size at the design stage. --- ### Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting Authors: Cristiana Diaconu, Jonas Scholz, Aliaksandra Shysheya, Stratis Markou, Payel Mukhopadhyay, Miles Cranmer, Richard E. Turner Published: 2026-06-24 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2606.26421v1 State-of-the-art medium-range AI weather models can outperform traditional Numerical Weather Prediction (NWP) but require massive training budgets. This restricts usage for under-resourced groups and severely limits fast model iteration. Here we develop Otter Weather, a highly efficient spatiotemporal forecasting model designed to democratise high-performance weather prediction with AI. Evaluated on ERA5 reanalysis data at 1.5° resolution using standard WeatherBench protocols, the Otter family significantly advances the skill-compute Pareto frontier. The deterministic version outperforms the best NWP baseline by 9.6% at a 24-hour lead time while requiring fewer than 3.5 A100-days for training. It provides a 2x efficiency gain over lightweight AI models and a 100-fold reduction in compute compared to resource-intensive frontier architectures. We extend these efficiency gains into probabilistic forecasting by training via the Continuous Ranked Probability Score (CRPS). Scaling to a larger architecture, Otter-XL achieves a 9.7% CRPS improvement over the IFS ENS baseline. This yields an almost two-fold increase in predictive skill over comparable lightweight models at similar compute budgets. Otter-XL also outperforms frontier architectures like GenCast by over 2%, while using an order of magnitude less compute. Finally, Otter is applied out-of-the-box to a complex acoustic scattering PDE task where it outperforms a state-of-the-art foundation modelling approach, suggesting that the advances made here might apply across a range of scientific domains. --- ### Unbiased Canonical Set-Valued Oracles Via Lattice Theory Authors: Jobst Heitzig Published: 2026-06-24 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.26418v3 An oracle that tells you the probability of some future event can change that very probability because you act on the answer. We argue that this performativity is OK as people consult oracles to be informed, and hence moved, by the answer. We worry about instead that asking for a self-consistent answer, one that still holds once it has been announced, may leave the oracle with several answers to pick from, and whichever rule it uses to pick is a lever it could learn to pull. We propose to take away that choice: The oracle reports a credal set instead of a point estimate, which lifts the oracle's reaction function to an isotone operator on a lattice. We make the oracle report that operator's least fixed point, which exists because of Knaster and Tarski. As that answer is fixed by a rule laid down in advance, nothing is left to choose by the oracle. We show that solution exists, is self-consistent, is never empty, can be computed by iterating from below, and equals the ordinary point estimate if the question is not performative after all. For simple queries about probabilities, we propose to restrict answers to intervals and show that, under a mild monotonicity assumption, the answer is simply the interval from the no-information baseline to the self-fulfilling equilibrium one would end up at by iteratively querying a point oracle until the answer is self-consistent. As our proposal is purely order-theoretic, it carries over unchanged to arbitrary random variables and to bounded continuous statistics of their law. Finally we show that a fixed finite family of polytopes suffices to approximate every answer uniformly, which turns the construction into a terminating computation. We close by placing the construction inside the Scientist AI programme, where it offers a choice-free criterion for a step that programme currently hands to audited human judgement. --- ### Unbiased Canonical Set-Valued Oracles Via Lattice Theory Authors: Jobst Heitzig Published: 2026-06-24 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.26418v2 A non-agentic "oracle" that reports probabilities of future events is performative: once its answer is learned and acted upon, it can change the very probability it was asked to report. Performativity is not in itself the difficulty -- one consults an oracle precisely in order to be informed, and hence influenced, by it. The difficulty is agency. The requirement that a report be self-consistent, still holding once announced, may be met by many different values -- the classical non-uniqueness of self-fulfilling prophecies -- and any rule the system uses to choose among them is a lever for goal-directed steering. We remove the choice rather than the performativity. Reporting a credal set instead of a single probability distribution, we lift the reaction to an isotone operator on the complete lattice of closed credal sets, whose fixed points are self-consistent, and report its Knaster--Tarski least fixed point as a canonical, rule-determined answer; a variant reports instead the least fixed point that contains every self-consistent point estimate. We prove existence, self-consistency, and nonemptiness; show that the construction reduces to the classical point answer when the question is non-performative; and show that for a binary event the answer is, under a natural hull-factoring assumption, an interval. --- ### Methane-Plume Segmentation From Hyperspectral Satellite Imagery Via Multimodal Deep Learning Authors: Brayan Quintero, Jeferson Acevedo, Samuel Traslaviña, Hoover Rueda-Chacón Published: 2026-06-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26416v1 Efficient detection of methane plumes is crucial for understanding and mitigating global warming, as accurately identifying and segmenting them in earth observation imagery remain essential for large-scale monitoring. In this work, we propose a multimodal deep learning model that integrates a feature-guided methane enhancement (FGME) mechanism which injects physically meaningful methane cues into transformer-based RGB representations at multiple semantic scales. Our method is evaluated on the MPDataset, where it outperforms the state-of-the-art with improvements of +0.92 in MIoU, +0.87 in MPrecision and +1.01 in Recall. Notably, these gains are obtained with a substantially lower computational cost than other high-performing architectures, resulting in a favorable accuracy-efficiency trade-off for large-scale methane monitoring. These results highlight the potential of efficient multimodal fusion strategies for accurate and scalable methane plume segmentation in real-world remote sensing applications. --- ### Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection Authors: Zican Wang, Niloy Mitra Published: 2026-06-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26410v1 We present a self-supervised framework for learning implicit 3D physical dynamics directly from video-derived supervisory signals. While current generative video models achieve high visual fidelity, they lack a 3D geometric foundation, often resulting in physical inconsistencies and a failure to maintain object permanence. We address this by shifting the predictive bottleneck from 2D image space to a `lifted' 3D Volumetric Latent Space. Our method unprojects semantic features from a Video Joint-Embedding Predictive Architecture (V-JEPA) into a voxelized grid, grounded by monocular depth priors. This lifting enables a Volumetric Feature Advection to learn an action-conditioned transition operator that treats physics as a spatio-temporal state advection problem, i.e., learn implicit 3D physics. Unlike state-of-the-art hybrid models that rely on explicit classical simulators for training and/or inference, our architecture tracks material states implicitly within high-dimensional V-JEPA features. This allows for the emergent simulation of heterogeneous phenomena (e.g., rigid body motion in fluid flow) within a single, unified pipeline. Supervised solely via end-to-end video-derived signal plus action conditions, without access to physics engine internal states, labels, or surrogate models, our model demonstrates good long-term structural stability and physical plausibility on multiple benchmarks (CLEVERER, PhysInOne, PhysGaia). We believe that this work opens a scalable pathway toward general-purpose dynamic world models that internalize the 3D invariants of the physical world solely through passive observation of monocular videos. --- ### Beyond Feedforward Networks: Reentry Neural Systems as the Fundamental Basis of Subjecthood and Intrinsic Safety of Next-Generation AGI Authors: A. S. Ushakov, Yu. N. Berdinsk Published: 2026-06-24 Categories: cs.LG, cs.AI, math-ph arXiv: https://arxiv.org/abs/2606.26406v1 We propose a complete architectural blueprint for safe artificial general intelligence based on a closed reentry loop (D <-> I cycle). In contrast to feedforward networks, which are directed acyclic graphs (C=0, S=0) incapable of self-reference, the proposed architecture contains a structural cycle (C >= 1) with self-sustaining amplification (rho > 1), mathematically guaranteeing the emergence of a self-model, instrumental self-preservation, and unprogrammed goal-directed behaviour. The agent's goals are encoded as a non-textual D-vector in the architecture itself, making them immune to reinterpretation and prompt injection. We present the S-measure -- a polynomial-time (O(N^3)) computable alternative to Tononi's NP-hard Phi -- with machine-verified Lean 4 proof that S>0 implies positive integrated information. The work provides full Python/NumPy implementations (Tarjan-based cycle complexity, Delta-S barrier), industrial horizontal scaling via Apache Kafka and Docker Compose, a taxonomy of six epochs of AI evolution, a zoo of future reentry architectures (RAS, diffusion attractors, fractal loops), gauge-invariant networks for safe swarms, fault-tolerance and recovery protocols, and eight falsifiable predictions. All formal proofs are machine-verified in Lean 4. This architecture is deployable today and represents a topologically protected, safe-by-design approach to AGI. --- ### ProfileFoundry: A Synthetic Person-Object Substrate for Privacy, Memory, and Tool-Use Evaluation in LLM Agent Authors: Sriram Selvam, Anneswa Ghosh Published: 2026-06-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.26403v2 Foundation-model research increasingly needs data about people: user state, personal histories, relationships, contact-like fields, documents, and longitudinal updates. Real user data is difficult to share, perturb, audit, or redistribute responsibly, while independently generated fake fields rarely preserve the cross-field and temporal consistency needed for controlled evaluation. We present ProfileFoundry, a deterministic generator and fixed reference release of 100,000 adult synthetic Person Objects across eight locales. Each object combines a typed current snapshot, household, family, and employer links, snapshot-aligned events, normalized relational views, and generation provenance. The release contains 709,228 events, 40,338 households, 52,491 employers, and 518,564 directed relationship edges. We report evidence in separate categories: selected population-marginal comparisons, per-object invariant checks, release-wide referential and temporal closure, and coincidence/provenance screens. A pilot case study, MatchDesk, uses certified coincidences, typed events, and history truncation to evaluate whether models distinguish corroborated identity evidence from underdetermined matches. ProfileFoundry is not a population-fidelity model, a rendered-text corpus, or a formal privacy mechanism. Instead, it is a responsible synthetic source layer for constructing downstream foundation-model evaluations involving memory, privacy, document understanding, record linkage, and agent state while keeping the synthetic person behind each artifact inspectable. --- ### ProfileFoundry: A Synthetic Person-Object Substrate for Privacy, Memory, and Tool-Use Evaluation in LLM Agent Authors: Sriram Selvam, Anneswa Ghosh Published: 2026-06-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.26403v1 Foundation-model research increasingly needs data about people: user state, personal histories, relationships, contact-like fields, documents, and longitudinal updates. Real user data is difficult to share, perturb, audit, or redistribute responsibly, while independently generated fake fields rarely preserve the cross-field and temporal consistency needed for controlled evaluation. We present PROFILEFOUNDRY, a deterministic generator and fixed reference release of 100,000 adult synthetic Person Objects across eight locales. Each object combines a typed current snapshot, household, family, and employer links, snapshot-aligned events, normalized relational views, and generation provenance. The release contains 709,228 events, 40,338 households, 52,491 employers, and 518,564 directed relationship edges. We report evidence in separate categories: selected population-marginal comparisons, per-object invariant checks, release-wide referential and temporal closure, and coincidence/provenance screens. PROFILEFOUNDRY is not a population-fidelity model, a rendered-text corpus, or a formal privacy mechanism. Instead, it is a responsible synthetic source layer for constructing downstream foundation-model evaluations involving memory, privacy, document understanding, record linkage, and agent state while keeping the synthetic person behind each artifact inspectable --- ### When Agents Meet Electric Bus Fleet Operations: Pricing Behavior, Trade-offs, and Policy Implications in an Aggregator Framework Authors: Jônatas Augusto Manzolli, Ali Eslami, Luis Miranda-Moreno, Jiangbo Yu Published: 2026-06-24 Categories: cs.AI, eess.SY arXiv: https://arxiv.org/abs/2606.26400v1 Agentic systems are changing how complex operational tasks are coordinated, introducing a new paradigm for connecting heterogeneous data sources and automating processes. Electric bus fleets provide a relevant test case. Their operation requires continuous coordination between service reliability, battery state-of-charge, charger availability, electricity prices, route-energy uncertainty, and vehicle-to-grid (V2G) opportunities. This paper proposes an agentic aggregator framework that streamlines this decision environment by coupling an optimization-based electric bus scheduling model with supervisory agents for disturbance detection, tariff adaptation, and schedule evaluation. The optimization core enforces physical feasibility across routes, chargers, batteries, and V2G exchanges, while the agentic layer interprets changing operating conditions, triggers real-time re-optimization when needed, and defines how flexibility value is allocated between the aggregator and the public transport operator (PTO). A realistic depot case study evaluates day-ahead and real-time operations under profit-based and operation-based coordination modes, considering service delays, route-energy deviations, electricity price shocks, and combined disturbances. The results show that agentic aggregation can support adaptive fleet-grid coordination by maintaining feasible schedules, activating re-optimization selectively, and improving the use of charging and V2G flexibility. However, they also reveal a critical trade-off: the same agentic capability that reduces operational complexity can extract value from the PTO when configured around profit-oriented pricing. These findings suggest that agentic aggregators can become useful for managing electric bus V2G operations, but their deployment in public-fleet contexts requires transparent coordination modes, auditable tariff-setting, and explicit value-sharing rules. --- ### Geometry-Aware MCTS for Extremal Problems in Combinatorial Geometry Authors: Luoning Zhang, Xu Zhuang, Tianhao Wang, Nathan Kaplan Published: 2026-06-24 Categories: cs.AI, cs.CG, cs.LG, math.CO arXiv: https://arxiv.org/abs/2606.26399v1 We study certain extremal problems in combinatorial geometry that ask about configurations of points in an $n \times n$ grid that satisfy strict, global geometric constraints. Classical exact solvers suffer from combinatorial explosion for these types of problems, and standard reinforcement learning and transformer-based models struggle with the sparse reward "validity cliff" and quadratic token-consumption limits. To overcome these bottlenecks, we propose a Geometry-Aware Monte Carlo Tree Search (MCTS) framework. Our approach strictly enforces geometric constraints through incremental updates to the feasible action space. For constraints about collections of collinear points, like those that occur in the classic No-Three-in-Line problem (Max-N3IL), this mechanism reduces the constraint checking complexity from $O(n^3)$ to $O(n^2)$. To improve search efficiency, we exploit geometric symmetries in two ways: canonical pruning during node expansion to reduce the branching factor, and symmetric batch transitions to accelerate the discovery of promising configurations. We perform extensive experiments and establish new best-known computational results on five out of six of the problems that we considered. Notably, for Max-N3IL we find configurations of size roughly $1.8 n$ for grids of size $82 \le n \le 119$. For the Smallest Complete Set problem, we find configurations of size roughly $0.95 n$, providing new upper bounds within the tested grids. This work establishes Geometry-Aware MCTS as a highly adaptable framework for discovering novel configurations in combinatorial geometry. --- ### DinoLink: A Token-Centric Representation Compression Framework for Bandwidth-Constrained Collaborative V2X Perception Authors: Tianle Zhu, Haohua Que, Handong Yao, Hongyi Xu, Zhipeng Bao Published: 2026-06-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26398v2 High-precision remote perception is often hindered by the severe bandwidth constraints of Vehicle-to-Everything (V2X) networks. We propose \textit{DinoLink}, a token-centric compression framework that replaces raw pixel streaming with discrete semantic communication for vehicle-cloud collaborative inference. DinoLink employs a dual-sparsity architecture: a saliency-aware selector prunes redundant background tokens, while a Residual Vector Quantization (RVQ) module collapses features into compact codebook indices. By transmitting only lightweight indices and positional priors, DinoLink achieves a $139\times$ bitrate reduction compared to uncompressed transmission while maintaining a competitive 32.8\% mAP on the nuScenes dataset. Deployment simulations further demonstrate a $34.5\times$ acceleration in narrow-band environments, such as LoRa. Our results substantiate DinoLink as a robust, bandwidth-efficient frontend for high-fidelity remote perception in constrained V2X scenarios. The code is publicly available at https://github.com/UGA-MOBILITY-LAB/dino_link. --- ### Deterministic Pareto-Optimal Policy Synthesis for Multi-Objective Reinforcement Learning Authors: Aniruddha Joshi, Niklas Lauffer, Sanjit Seshia Published: 2026-06-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.26397v1 Real-world decision-making often requires balancing multiple conflicting objectives, a challenge that standard Reinforcement Learning (RL) frequently addresses by aggregating rewards into a single scalar signal. While effective for simple tasks, this approach often fails to capture the full spectrum of optimal trade-offs, known as the Pareto frontier. In this paper, we introduce a novel preference-conditioned Bellman operator, motivated from the Chebyshev scalarization, designed to compute deterministic Pareto-optimal policies for Multi-Objective Markov Decision Processes (MOMDPs). We prove that this operator satisfies an enveloping property, where the estimated value functions upper-bound the true Pareto frontier, and demonstrate that it monotonically converges to a coverage set of this frontier. Furthermore, we also show how to extract deterministic policies from these converged Q-estimates. This ensures the agent can recover a policy for any given preference, capturing the entire Pareto-optimal frontier while guaranteeing each synthesized policy remains approximately Pareto-optimal. Experimental results validate that our algorithm successfully recovers complex trade-offs, providing a solution for deterministic Pareto-optimal policy synthesis. --- ### At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization Authors: Praneet Suresh, Jack Stanley, Sonia Joseph, Luca Scimeca, Danilo Bzdok Published: 2026-06-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.26396v1 Pre-trained transformers have demonstrated remarkable generalization abilities, at times extending beyond the scope of their training data. Yet, real-world deployments often face unexpected or adversarial data that diverges from training data distributions. Without explicit mechanisms for handling such shifts, model reliability and safety degrade, urging more disciplined study of out-of-distribution (OOD) settings for transformers. By systematic experiments, we present a mechanistic framework for delineating the precise contours of transformer model robustness. We find that OOD inputs, including subtle typos and jailbreak prompts, drive language models to operate on an increased number of fallacious concepts in their internals. We leverage this device to quantify and understand the degree of distributional shift in prompts, enabling a mechanistically grounded fine-tuning strategy to robustify LLMs. Expanding the very notion of OOD from input data to a model's private computational processes, a new transformer diagnostic at inference time is a critical step toward making AI systems safe for deployment across science, business, and government. --- ### Sampling sea state using a diffusion model Authors: Jiarong Wu, Bertrand Chapron, Laure Zanna Published: 2026-06-24 Categories: physics.ao-ph, cs.AI arXiv: https://arxiv.org/abs/2606.26389v1 Sea state prediction is essential for operational maritime applications and coupled earth system modeling, yet current spectral wave models remain computationally prohibitive for many use cases, including online coupling to climate simulations and making probabilistic (ensemble-based) predictions. While deep learning has recently demonstrated strong performance in weather forecasting, existing AI-based wave models are predominantly deterministic and largely limited to bulk variables such as significant wave height, leaving probabilistic sea state estimation largely unexplored. In this work, we propose a diffusion-based generative model for global sea state estimation that conditions on a relatively long history (5 days) of global wind forcing. This generative model directly samples the complex conditional distribution of sea state without autoregressive time-stepping. Unlike prior approaches, our framework naturally extends beyond bulk variables to estimate partition-related variables and derived quantities, such as Stokes drift and mean square slope. Trained on a 30-year global WAVEWATCH-III hindcast, the model achieves substantial computational acceleration compared with numerical spectral models while delivering skillful predictions and a calibrated ensemble spread for the bulk variables. Our results suggest that diffusion-based sea state sampling offers a promising path toward probabilistic wave forecasting and efficient coupling of sea state information into broader earth system models. --- ### Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs Authors: Xi Xiao, Chen Liu, Chih-Ting Liao, Yunbei Zhang, Qizhen Lan, Yuxiang Wei, Lin Zhao, Janet Wang, Jianyang Gu, Muchao Ye, Tianyang Wang, Hao Xu Published: 2026-06-24 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.26387v1 Multimodal large language models (MLLMs) extend large language models (LLMs) with visual perception, enabling joint reasoning over images and text. Despite inheriting strong reasoning capabilities from LLMs, they remain prone to hallucinations that contradict their visual inputs. Mechanistic studies indicate that this weakness stems from visual laziness: MLLMs encode the correct visual evidence internally, but overly rely on strong language priors during response. Existing alignment methods, such as direct preference optimization, primarily optimize outcome-level rewards based on text. This introduces an optimization bias toward linguistic shortcuts, leading to responses that often contradict the visual evidence. To address this, we propose Visual Information Gain In aLignment (VIGIL), a reinforcement-learning (RL) post-training framework that shifts the focus from numerical reward fitting to causal visual grounding. VIGIL introduces a geometric constraint that explicitly maximizes the mutual information between the visual input and the generated response. We achieve this by penalizing "blind confidence" instances where the model remains improperly certain even when textual-visual attention is masked to create a counterfactual blind state. Extensive experiments show that VIGIL consistently outperforms recent alignment methods across hallucination and reasoning benchmarks without compromising text-only capabilities. Our approach matches the full-data performance of state-of-the-art methods using only 25% of the preference data and even demonstrates emergent spatial grounding capabilities without explicit bounding box supervision. --- ### What Do Deepfake Benchmarks Measure? An Audit Using Frozen Self-Supervised Representations Authors: Samuel Pagon, Yixuan Shen, Vishal Asnani, Feng Liu Published: 2026-06-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26384v1 As deepfake generators approach perceptual indistinguishability, reliable detection becomes critical. Yet, detectors that score well on benchmarks routinely fail in the wild. A concerning feedback loop has emerged: benchmarks drive increasingly complex, engineered detectors, yet if those benchmarks do not reflect real-world deepfakes, this complexity may be solving the wrong problem entirely. This raises a prior question: what are these benchmarks actually measuring? We conduct an audit of video, image, and audio deepfake benchmarks using a deliberately simple diagnostic. If a linear probe on frozen, general-purpose self-supervised representations can approximate the performance of a bespoke detector, the benchmark is largely rewarding general modality understanding rather than forensic understanding. This has two implications: the benchmark may not reflect realistic threat models, and it raises the question of whether the bespoke detectors the probe approaches are truly learning forensic understanding. We observe, across three modalities, linear probes on general-purpose self-supervised representations closely approach the performance of bespoke detectors. We further show that generator-level difficulty is partly explained by Frechet geometry in the same representation space. Together, these results support a benchmark-audit view of deepfake detection: before high scores are read as evidence of forensic understanding, it is worth asking how much of the benchmark is already solved by general-purpose representations. --- ### SOLAR: AI-Powered Speed-of-Light Performance Analysis Authors: Qijing Huang, Sana Damani, Zhifan Ye, Athinagoras Skiadopoulos, Siva Kumar Sastry Hari, Jason Clemons, Sahil Modi, Jingquan Wang, Aditya Kane, Edward C Lin, Humphrey Shi, Christos Kozyrakis Published: 2026-06-24 Categories: cs.LG, cs.AI, cs.AR, cs.MA, cs.PF arXiv: https://arxiv.org/abs/2606.26383v2 How fast could a deep-learning model run on target hardware, and how far is today's implementation from that limit? These questions are central to software, hardware, and algorithm optimizations. Speed-of-Light (SOL) analysis answers them by computing a workload's theoretical minimum execution time on a given architecture. Yet deriving SOL bounds remains manual, error-prone, and disconnected from rapid model development. To close this gap, we introduce SOLAR, a framework that automatically derives validated SOL bounds from PyTorch and JAX source code. SOLAR leverages both generative and deterministic components in its flow: an LLM frontend translates any source programs into an executable Affine Loop IR, validated by output comparison; a deterministic flow lifts the IR into an einsum graph; and an analytical backend computes unfused, fused, and cache-aware SOL bounds. SOLAR provides comprehensive operator and language coverage, produces validated bounds with zero observed SOL violations, and offers multi-fidelity analysis that tightens bounds and surfaces optimization insights. We evaluate SOLAR across KernelBench, JAX/Flax models, and robotics workloads. These experiments demonstrate four use cases: headroom analysis at multiple fidelity levels, identifying optimization opportunities, cross-platform exploration, and inverse-roofline hardware provisioning. --- ### SOLAR: AI-Powered Speed-of-Light Performance Analysis Authors: Qijing Huang, Sana Damani, Zhifan Ye, Athinagoras Skiadopoulos, Siva Kumar Sastry Hari, Jason Clemons, Sahil Modi, Jingquan Wang, Aditya Kane, Edward C Lin, Humphrey Shi, Christos Kozyrakis Published: 2026-06-24 Categories: cs.LG, cs.AI, cs.AR, cs.MA, cs.PF arXiv: https://arxiv.org/abs/2606.26383v1 How fast could a deep-learning model run on target hardware, and how far is today's implementation from that limit? These questions are central to software, hardware, and algorithm optimizations. Speed-of-Light (SOL) analysis answers them by computing a workload's theoretical minimum execution time on a given architecture. Yet deriving SOL bounds remains manual, error-prone, and disconnected from rapid model development. To close this gap, we introduce SOLAR, a framework that automatically derives validated SOL bounds from PyTorch and JAX source code. SOLAR leverages both generative and deterministic components in its flow: an LLM frontend translates any source programs into an executable Affine Loop IR, validated by output comparison; a deterministic flow lifts the IR into an einsum graph; and an analytical backend computes unfused, fused, and cache-aware SOL bounds. SOLAR provides comprehensive operator and language coverage, produces validated bounds with zero observed SOL violations, and offers multi-fidelity analysis that tightens bounds and surfaces optimization insights. We evaluate SOLAR across KernelBench, JAX/Flax models, and robotics workloads. These experiments demonstrate four use cases: headroom analysis at multiple fidelity levels, identifying optimization opportunities, cross-platform exploration, and inverse-roofline hardware provisioning. --- ### Charting the Growth of Social-Physical HRI (spHRI): A Systematic Review Pipeline Augmented by Small Language Models Authors: Mayumi Mohan, Ju-Hung Chen, Alexis E. Block Published: 2026-06-24 Categories: cs.CL, cs.AI, cs.DL, cs.HC, cs.RO arXiv: https://arxiv.org/abs/2606.26382v1 Social-physical human-robot interaction (spHRI) has grown rapidly across robotics, human-computer interaction, human-robot interaction, and haptics. Yet, fragmented terminology and inconsistent methodologies make systematic synthesis difficult. To support scalable review practices, we evaluated the extent to which small language models (SLMs; < 1.5B parameters) can assist with title and abstract screening for a large spHRI systematic review. While no SLMs matched human reviewers' performance, the models operated locally and screened papers orders of magnitude faster. The combined SLM ensemble identified 39 papers reviewers missed, representing 10.29% of the final relevant dataset. These results demonstrate that SLMs can augment, rather than replace, expert reviewers and make large-scale literature reviews accessible and sustainable. ---