Invisible failures in human-AI interactions
arXiv:2603.15423v2 Announce Type: replace Abstract: AI systems fail silently far more often than they fail visibly. In an analysis of 100K human-AI interactions from the WildChat dataset, we find that
Knowledge catalogue
arXiv:2603.15423v2 Announce Type: replace Abstract: AI systems fail silently far more often than they fail visibly. In an analysis of 100K human-AI interactions from the WildChat dataset, we find that
arXiv:2605.11385v1 Announce Type: new Abstract: Stochastic Human Trajectory Prediction (HTP) using generative modeling has emerged as a significant area of research. Although state-of-the-art models e
arXiv:2603.29057v2 Announce Type: replace Abstract: Skeleton-based isolated sign language recognition (ISLR) demands fine-grained understanding of articulated motion across multiple spatial scales, fr
arXiv:2605.11301v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have heterogeneous strengths across OCR, chart understanding, spatial reasoning, visual question answering, c
arXiv:2605.10980v1 Announce Type: new Abstract: Diffusion Language Models (dLLMs) have garnered significant attention for their potential in highly parallel processing. The parallel capabilities of ex
arXiv:2605.11931v1 Announce Type: new Abstract: Post-training with explicit reasoning traces is common to improve the reasoning capabilities of Multimodal Large Language Models (MLLMs). However, acqui
arXiv:2506.22809v4 Announce Type: replace-cross Abstract: Low-rank adaptation is effective partly because downstream updates lie in a low-dimensional subspace, but the latent rank coordinates of LoRA
arXiv:2605.12004v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) for Large Language Models (LLMs) critically depends on the exploration capability of the base policy, as training si
arXiv:2605.12427v1 Announce Type: new Abstract: For minimally rigid graphs, the same edge-length data can admit multiple realizations (up to translations and rotations). Finding graphs with exceptiona
arXiv:2605.11444v1 Announce Type: new Abstract: All-in-one image restoration seeks to recover clean images from inputs affected by diverse and unknown degradations using a unified framework. Recent me
arXiv:2605.11217v1 Announce Type: new Abstract: Large language model (LLM) alignment algorithms typically consist of post-training over preference pairs. While such algorithms are widely used to enabl
arXiv:2605.11591v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown strong performance in multi-image cross-modal retrieval, yet suffer from severe position bias, where
arXiv:2602.07668v2 Announce Type: replace Abstract: The looking-in-looking-out (LILO) framework has enabled intelligent vehicle applications that understand both the outside scene and the driver state
arXiv:2509.22414v4 Announce Type: replace Abstract: Image restoration (IR) aims to recover images degraded by unknown mixtures while preserving semanticsconditions under which discriminative restorers
arXiv:2603.05947v3 Announce Type: replace Abstract: Generative real-world image super-resolution (Real-ISR) can synthesize visually convincing details from severely degraded low-resolution (LR) inputs
arXiv:2511.11412v5 Announce Type: replace Abstract: This data paper introduces MajinBook, an open catalogue designed to facilitate the use of shadow libraries-such as Library Genesis and Z-Library-for
arXiv:2603.14094v2 Announce Type: replace-cross Abstract: We address the brittleness of Bayesian experimental design under model misspecification by formulating the problem as a max--min game between
arXiv:2605.12128v1 Announce Type: new Abstract: Large language models are increasingly deployed in safety-critical applications, where their ability to resist harmful instructions is essential. Althou
arXiv:2605.12070v1 Announce Type: new Abstract: Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy optimization
arXiv:2605.12119v1 Announce Type: new Abstract: Generative novel view synthesis faces a fundamental dilemma: geometric priors provide spatial alignment but become sparse and inaccurate under view chan
arXiv:2605.12410v1 Announce Type: cross Abstract: We propose and analyze a model-based bootstrap for transition kernels in finite controlled Markov chains (CMCs) with possibly nonstationary or history
More accurate statement IMHO would be: there won’t immediately be an AI jobpocalyspe. Saying there never will be one hardly seems plausible. Even less plausible is the claim that there will be an AI j
arXiv:2605.11402v1 Announce Type: new Abstract: Deep learning-based website fingerprinting has emerged as an effective technique for inferring the websites users visit. Although existing methods achie
arXiv:2605.12228v1 Announce Type: new Abstract: Mobile manipulation requires coordinated control of high-dimensional, bimanual robots. Imitation learning methods have been broadly used to solve these
arXiv:2605.11959v1 Announce Type: cross Abstract: Multimodal video summarization requires visual features that align semantically with language generation. Traditional approaches rely on CNN features
New paper in Nature. The more a government controls its domestic media, the more it dominates AI training data, the more pro-regime outputs we get from AI. By scraping the open web, LLMs are unwitting
arXiv:2605.11102v1 Announce Type: new Abstract: Neural warm starts can sharply reduce the number of Newton-Raphson iterations required to solve the AC power flow problem, but existing supervised appro
Gary Marcus argues that current large language models (LLMs) do not constitute artificial general intelligence (AGI), though they will cause some job displacement. He suggests that true AGI, if achiev
no remorse, just further evasion. so slick; so dangerous. 🚨 SEVEN OPENAI INSIDERS HAVE ACCUSED SAM ALTMAN OF LYING Today on cross, Musk's lawyer walked Altman through all of them: >Ilya Sutskever (co-
arXiv:2603.18702v3 Announce Type: replace Abstract: We study off-policy learning (OPL) in contextual bandits, which plays a key role in a wide range of real-world applications such as recommendation s
arXiv:2505.17506v2 Announce Type: replace-cross Abstract: We study offline constrained reinforcement learning with general function approximation in discounted constrained Markov decision processes. P
arXiv:2605.11479v1 Announce Type: new Abstract: Policy evaluation is a fundamental component of the development and deployment pipeline for robotic policies. In modern manipulation systems, this probl
arXiv:2605.12400v1 Announce Type: new Abstract: We study {on-policy self-distillation} (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions alon
arXiv:2605.12480v1 Announce Type: new Abstract: Recent advances in joint audio-video generation have been remarkable, yet real-world applications demand strong per-modality fidelity, cross-modal align
arXiv:2605.12206v1 Announce Type: new Abstract: In reinforcement learning (RL), agents acting in partially observable Markov decision processes (POMDPs) must rely on memory, typically encoded in a rec
arXiv:2605.05630v2 Announce Type: replace Abstract: Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objec
OpenAI Global Affairs: OpenAI endorses the Kids Online Safety Act and Illinois SB 315, an AI safety bill to create requirements around transparency, incident reporting, and more — Welcome (back) to Th
arXiv:2605.12235v1 Announce Type: cross Abstract: We study optimal policy learning under combined budget and minimum coverage constraints. We show that the problem admits a knapsack-type structure and
arXiv:2605.11977v1 Announce Type: new Abstract: We present a unified framework for 3D geometric abstraction using a single continuous 4D wire, parameterized as a B-spline with spatial coordinates and
arXiv:2605.12446v1 Announce Type: cross Abstract: Large language models (LLMs) often produce answers with high certainty even when they are incorrect, making reliable confidence estimation essential f
Our evaluations show that frontier AI's cyber capabilities are advancing quickly. The length of cyber tasks frontier models can complete has been doubling every few months, and this rate has become fa
arXiv:2605.11525v1 Announce Type: new Abstract: Missing values are routinely treated as defects to be eliminated through deletion or imputation prior to machine learning. In many applied domains, howe
arXiv:2605.11178v1 Announce Type: new Abstract: Neural Sheaf Diffusion (NSD) generalizes diffusion-based Graph Neural Networks by replacing scalar graph Laplacians with sheaf Laplacians whose learned
arXiv:2605.11730v1 Announce Type: new Abstract: Automated red-teaming for LLMs often discovers narrow attack slices, missing diverse real-world threats, and yielding insufficient data for safety fine-
arXiv:2512.05683v2 Announce Type: replace Abstract: Optical aberrations significantly degrade image quality in microscopy, particularly when imaging deeper into samples. These aberrations arise from d
arXiv:2605.11520v1 Announce Type: new Abstract: Unsupervised point cloud segmentation is critical for embodied artificial intelligence and autonomous driving, as it mitigates the prohibitive cost of d
arXiv:2512.11883v3 Announce Type: replace-cross Abstract: Over-aligning image generation models to a generalized aesthetic preference conflicts with user intent, particularly when 'anti-aesthetic' out
arXiv:2605.11511v1 Announce Type: cross Abstract: The validity of statistical inference depends critically on how data are collected. When data gathered through active data collection (ADC) are reused
arXiv:2605.11453v1 Announce Type: cross Abstract: Practitioners deploying multi-agent large language model (LLM) systems must currently choose between communication topologies such as chain, star, mes
arXiv:2605.12382v1 Announce Type: new Abstract: Large language models (LLMs) exhibit systematic preferences for well-known entities, a phenomenon often attributed to popularity bias. However, the exte
arXiv:2605.11535v1 Announce Type: new Abstract: Existing work on linear constrained Markov decision processes (CMDPs) has primarily focused on stochastic settings, where the losses and costs are eithe
arXiv:2605.11299v1 Announce Type: cross Abstract: Code generation is typically trained in the primal space of programs: a model produces a candidate solution and receives sparse execution feedback, of
arXiv:2605.12289v1 Announce Type: new Abstract: Leveraging the rich world knowledge of Large Language Models (LLMs) to enhance Reinforcement Learning (RL) agents offers a promising path toward general
arXiv:2509.06701v2 Announce Type: replace Abstract: We develop a theory of intelligent agency grounded in probabilistic modeling for neural models. Agents are represented as outcome distributions with
probably correct, from @polynoamial: “with today’s AI models, intelligence is a function of inference compute.” but what about tomorrow’s models? never forget that humans are remarkably intelligent (t
arXiv:2603.23677v2 Announce Type: replace Abstract: Deep learning models are increasingly deployed in safety-critical applications, where reliable out-of-distribution (OOD) detection is essential to e
arXiv:2605.12398v1 Announce Type: new Abstract: Estimating question difficulty is a critical component in evaluating and improving large language models (LLMs) for question answering (QA). Existing ap
arXiv:2605.11289v1 Announce Type: new Abstract: Average-reward reinforcement learning requires estimating the gain and the bias, which is defined only up to an additive constant. This makes direct dis
arXiv:2602.02280v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) face severe safety risks from jailbreak attacks, yet current safety testing largely relies on static datasets and
arXiv:2605.11697v1 Announce Type: new Abstract: This paper presents a kinematics-aware deep reinforcement learning framework based on Rainbow Deep Q-Networks (DQN) for cooperative peg-in-hole manipula