arXiv:2605.19329v1 Announce Type: cross Abstract: Conventional vision-language models (VLMs) struggle to interpret scenes captured under adverse conditions (e.g., low light, high dynamic range, or fast motion) because standard RGB images degrade in such environments. Event cameras provide a complementary modality: they asynchronously record per-pixel brightness changes with high temporal resolution and wide dynamic range, preserving […]
The Insurability Frontier of AI Risk: Mapping Threats to Affirmative Coverage, Silent Exposures, and Exclusions
arXiv:2605.18784v1 Announce Type: cross Abstract: The rapid diffusion of agentic AI has created a new coverage problem for commercial insurance: some AI-mediated losses are now affirmatively insured, some create silent-AI exposure under legacy cyber, technology errors-and-omissions (E&O), directors-and-officers (D&O), employment practices liability (EPLI), crime, and media policies, and others are being actively excluded. This paper […]
Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization
arXiv:2605.08659v3 Announce Type: replace-cross Abstract: Biomolecular generators are often adapted with reward feedback to improve task-specific utility, but pushing utility alone can concentrate generation on a narrow family of candidates. Maintaining diversity is difficult because sample diversity is a set-level property. We introduce Supergroup Relative Policy Optimization (SGRPO), a flexible GRPO-style framework that directly constructs […]
Towards Multi-Model LLM Schedulers: Empirical Insights into Offloading and Preemption
arXiv:2605.19593v1 Announce Type: new Abstract: Modern deployments of Large Language Models (LLMs) increasingly require serving multiple models with diverse architectures, sizes, and specialization on shared, heterogeneous hardware. This setting introduces new challenges for resource allocation, dispatching, and scheduling, particularly under GPU memory constraints where partial CPU-GPU offloading and preemption become necessary. While existing systems primarily […]
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors
arXiv:2605.16626v2 Announce Type: replace-cross Abstract: Since autonomous coding agents generate complex behaviors at high-volume, we may want to use other LLMs to monitor actions to reduce the risk from dangerous misaligned behavior. To better understand the limitations of such monitors against the diverse attack strategies that a coding agent could use, we present SLEIGHT-Bench (Subtle […]
EMO-BOOST: Emotion-Augmented Audio-Visual Features for Improved Generalization in Deepfake Detection
arXiv:2605.19630v1 Announce Type: new Abstract: With every advancement in generative AI models, forensics is under increasing pressure. The constant emergence of new generation techniques makes it impossible to collect data for each manipulation to train a deepfake detection model. Thus, generalizing to deepfakes unseen during training is one of the major challenges in current deepfake […]
Toward Training Superintelligent Software Agents through Self-Play SWE-RL
arXiv:2512.18552v2 Announce Type: replace-cross Abstract: While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub issues and pull requests) and environments (e.g., pass-to-pass and fail-to-pass tests) heavily depend on human knowledge or curation, posing a fundamental barrier to superintelligence. In this […]
When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach
arXiv:2605.19662v1 Announce Type: new Abstract: Tabular foundation models based on pretrained prior-data fitted networks~(PFNs) have shown strong generalization on diverse tabular tasks, but they are typically designed for emphnon-strategic settings where data distributions are independent of deployed classifiers. In many real-world decision scenarios, however, individuals may strategically modify their features after deployment to obtain favorable […]
Motif-Video 2B: Technical Report
arXiv:2604.16503v2 Announce Type: replace-cross Abstract: Training strong video generation models usually requires massive datasets, large parameter counts, and substantial compute. In this work, we ask whether strong text-to-video quality is possible at a much smaller budget: fewer than 10M clips and less than 100,000 H200 GPU hours. Our core claim is that part of the […]
Transforming Constraint Programs to Input for Local Search
arXiv:2605.19671v1 Announce Type: new Abstract: Applying local search algorithms to combinatorial optimization problems is not an easy feat. Typically, human intervention is required to compile the constraints to input data for some metaheuristic algorithm. In this paper, we establish a link between symmetry properties of constraint optimization problems and local search neighborhoods, and we use […]
How does longer temporal context enhance multimodal narrative video processing in the brain?
arXiv:2602.07570v2 Announce Type: replace Abstract: Understanding how humans and artificial intelligence systems process complex narrative videos is a fundamental challenge at the intersection of neuroscience and machine learning. This study investigates how the temporal context length of video clips (3–24 s clips) and the narrative-task prompting shape brain-model alignment during naturalistic movie watching. Using fMRI […]
Projecting Latent RL Actions: Towards Generalizable and Scalable Graph Combinatorial Optimization
arXiv:2605.19721v1 Announce Type: new Abstract: Graph combinatorial optimization (GCO) has attracted growing interest, as many NP-hard problems naturally admit graph formulations, yet their combinatorial explosion renders exact methods computationally intractable. Recent advances in Reinforcement Learning (RL) combined with Graph Neural Networks (GNNs) have significantly improved learning-based GCO solvers. However, existing approaches face limitations in both […]