arXiv:2609.16366v2 Announce Type: replace-cross Abstract: When foundation models describe people, recent work in AI fairness, accessibility, and ethics recommends avoiding inferred identity labels (e.g., "she", "his") in favor of seemingly…
arXiv:2609.10854v2 Announce Type: replace-cross Abstract: Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts auditing closed-source, remotely hosted…
arXiv:2609.08133v2 Announce Type: replace-cross Abstract: In nonconvex optimization problems arising in geometric machine learning, data augmentation is commonly used to promote invariance by averaging empirical losses over transformations of the…
arXiv:2609.06027v2 Announce Type: replace-cross Abstract: Search-augmented LLM agents are increasingly used for consumer decisions, making them vulnerable to Generative Engine Optimization (GEO) poisoning. Existing benchmarks largely measure…
arXiv:2609.02998v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) accelerates post-training by providing dense token-level supervision from a frozen teacher on the student's own rollouts. Vanilla OPD applies this supervision…
arXiv:2608.28843v2 Announce Type: replace-cross Abstract: We show that smooth two-layer feed-forward networks (FFNs) expose an additional structural model extraction channel under a chosen-input raw-output oracle at the FFN branch; consider…
arXiv:2608.24987v2 Announce Type: replace-cross Abstract: Multi-teacher on-policy distillation (MOPD) distills several domain-expert teachers into a single student by minimizing per-domain reverse-KL divergence on the student's own rollouts…
arXiv:2608.24115v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) can integrate long visual histories and infer behavior from a few examples, yet vision-language-action models rarely use this capacity as episode…
arXiv:2608.22223v3 Announce Type: replace-cross Abstract: Anti-amyloid therapies and blood-based biomarkers are changing Alzheimer disease workups into a two-stage measurement workflow: screen broadly with cheaper information, then spend scarce…
arXiv:2608.18265v3 Announce Type: replace-cross Abstract: We introduce a general, easy-to-implement AI-based modeling technique for analyzing human behavior. A key feature of this approach, which contrasts with existing modeling techniques, is that…
arXiv:2608.17209v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) and world-action models typically absorb unfamiliar manipulation tasks through additional robot data collection and policy optimization. This recurring…
arXiv:2608.07663v2 Announce Type: replace-cross Abstract: When videos extend from hours to days, directly processing them end-to-end becomes impractical for current Multi-modal Large Language Models (MLLMs). This ultra-long setting necessitates a…
arXiv:2607.25667v2 Announce Type: replace-cross Abstract: Psychotherapists need repeated training and supervision; however, scalability is problematic. We present MyMentorLLM, a multimodal voice- and text-based deliberate-practice environment with…
arXiv:2607.20712v2 Announce Type: replace-cross Abstract: Security protocols verification relies on formal tools such as ProVerif and OFMC. This study evaluates whether large language models (LLMs) can perform comparable analysis. We test GPT and…
arXiv:2607.17986v2 Announce Type: replace-cross Abstract: Self-hosted AI agents maintain persistent memory, instructions, and configuration that influence their future behavior. If an agent is compromised, an attacker can exploit the agent's…
arXiv:2607.16682v2 Announce Type: replace-cross Abstract: The widespread adoption of high-level deep learning libraries, while accelerating model development, has increasingly abstracted away the internal mechanics of neural networks, creating a…
arXiv:2607.14962v2 Announce Type: replace-cross Abstract: Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes. This limits…
arXiv:2607.14112v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are trained and evaluated as though perfect reliability is achievable for any task given sufficient scale. We show that this assumption is…
arXiv:2607.10116v2 Announce Type: replace-cross Abstract: We study robust generalization under spurious correlations: tasks where a shortcut feature is correlated with the true label in training but anti-correlated in an adversarial held-out split…
arXiv:2607.08837v3 Announce Type: replace-cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject stochasticity in the action space, but such…
arXiv:2606.31672v4 Announce Type: replace-cross Abstract: Despite rapid progress in interactive world models (IWMs), existing benchmarks evaluate action following only at trajectory level and ignore memory and interaction physics. We introduce…
arXiv:2606.29806v3 Announce Type: replace-cross Abstract: Action values are foundational to many control algorithms such as Q-learning. Therefore, efficient action-value learning is central to reinforcement learning (RL). However, learning them can…
arXiv:2606.23937v2 Announce Type: replace-cross Abstract: Exact-match retrieval recall is often used as a proxy for whether a retriever supplies useful policy context to a downstream decision model. We test this proxy for pre-action policy…
arXiv:2606.22790v4 Announce Type: replace-cross Abstract: Large automatic speech recognition (ASR) models such as Whisper must be deployed across hardware with widely varying memory and inference-speed constraints. We present a compression…
Pick what should wake you up. We only push stories the AI rates as genuinely urgent.