safety

arXiv:2604.10788v1 Announce Type: cross Abstract: Tool-Integrated Reasoning (TIR) has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools durin

arXiv:2604.11195v1 Announce Type: cross Abstract: Existing object detectors often struggle to generalize across domains while adapting to emerging novel categories. Adaptive open-set object detection

arXiv:2604.10158v1 Announce Type: new Abstract: While modern transformer neural networks achieve grandmaster-level performance in chess and other reasoning tasks, their internal computation process re

arXiv:2604.10123v1 Announce Type: new Abstract: Dysarthric speech severity assessment typically requires trained clinicians or supervised models built from labelled pathological speech, limiting scala

arXiv:2604.10351v1 Announce Type: new Abstract: Accurate actuation models are critical for bridging the gap between simulation and real robot behavior, yet obtaining high-fidelity actuator dynamics ty

arXiv:2604.11522v1 Announce Type: new Abstract: Reinforcement learning for open-ended text generation is constrained by the lack of verifiable rewards, necessitating reliance on judge models that requ

arXiv:2604.11668v1 Announce Type: new Abstract: The growing availability of co-located geospatial data spanning aerial imagery, street-level views, elevation models, text, and geographic coordinates o

arXiv:2604.11611v1 Announce Type: new Abstract: To overcome the sparse reward challenge in reinforcement learning (RL) for agents based on large language models (LLMs), we propose Mutual Information S

arXiv:2512.21648v2 Announce Type: replace-cross Abstract: Monte Carlo Tree Search (MCTS) has profoundly influenced reinforcement learning (RL) by integrating planning and learning in tasks requiring l

arXiv:2604.11250v1 Announce Type: new Abstract: Face recognition embeddings encode identity, but they also encode other factors such as gender and ethnicity. Depending on how these factors are used by

arXiv:2604.10341v1 Announce Type: new Abstract: extbf{VeriTrans} is a reliability-first ML system that compiles natural-language requirements into solver-ready logic with validator-gated reliability.

arXiv:2604.05418v2 Announce Type: replace-cross Abstract: Scaling multimodal large language models (MLLMs) to long videos is constrained by limited context windows. While retrieval-augmented generatio

arXiv:2604.11138v1 Announce Type: cross Abstract: In-hand object reorientation requires precise estimation of the object pose to handle complex task dynamics. While RGB sensing offers rich semantic cu

arXiv:2604.10500v1 Announce Type: new Abstract: Multimodal latent reasoning has emerged as a promising paradigm that replaces explicit Chain-of-Thought (CoT) decoding with implicit feature propagation

arXiv:2604.11671v1 Announce Type: cross Abstract: Accurate material recognition is a fundamental capability for intelligent perception systems to interact safely and effectively with the physical worl

arXiv:2604.10245v1 Announce Type: new Abstract: Registration between preoperative CT and intraoperative laparoscopic video plays a crucial role in augmented reality (AR) guidance for minimally invasiv

arXiv:2604.10809v1 Announce Type: new Abstract: Recent advancements in learning from human demonstration have shown promising results in addressing the scalability and high cost of data collection req

arXiv:2604.10022v1 Announce Type: new Abstract: Weird generalization is a phenomenon in which models fine-tuned on data from a narrow domain (e.g. insecure code) develop surprising traits that manifes

arXiv:2507.08339v4 Announce Type: replace Abstract: Recently, large language models (LLMs) and reasoning large language models (RLLMs) have gained considerable attention from many researchers. RLLMs e

arXiv:2510.26202v2 Announce Type: replace-cross Abstract: Human feedback can alter language models in unpredictable and undesirable ways, as practitioners lack a clear understanding of what feedback d

arXiv:2604.10062v1 Announce Type: new Abstract: We study reward poisoning attacks in reinforcement learning (RL), where an adversary manipulates rewards within constrained budgets to force the target

arXiv:2604.02458v2 Announce Type: replace-cross Abstract: Behavioral simulation is increasingly used to anticipate responses to interventions. Large language models (LLMs) enable researchers to specif

arXiv:2604.10996v1 Announce Type: cross Abstract: Can large language models (LLMs) generate continuous numerical features that improve reinforcement learning (RL) trading agents? We build a modular pi

Why why why is it so hard to understand that stupid systems can still be dangerous? @Graffitinights1 For the zillionth time, dumb systems that are empowered can dangerous. like this monstrosity, as an

arXiv:2604.11351v1 Announce Type: new Abstract: Imitation learning is a powerful paradigm for training robotic policies, yet its performance is limited by compounding errors: minor policy inaccuracies

arXiv:2604.10968v1 Announce Type: new Abstract: Most conversational agents (CAs) are designed to satisfy user needs through user-driven interactions. However, many real-world settings, such as academi

arXiv:2604.10898v1 Announce Type: new Abstract: Large language models (LLMs) have shown great performance on complex reasoning tasks but often require generating long intermediate thoughts before reac

arXiv:2604.08874v1 Announce Type: cross Abstract: This study proposes a temporal modeling framework with a counterfactual policy-simulation layer for student dropout in higher education, using LMS eng

At the University of California, Riverside (UCR), scientific breakthroughs depend on quickly moving from a hypothesis to a finished study. Yet for many researchers, the path to federal grants is often

arXiv:2604.08561v1 Announce Type: new Abstract: We investigate how successful bias mitigation reshapes the embedding space of encoder-only and decoder-only foundation models, offering an internal audi

A Restore Britain Government would back British drivers. How? Raise the speed limit on motorways to 80mph. Remove all 20mph zones, other than those outside schools or areas with vulnerable individuals

arXiv:2604.08588v1 Announce Type: cross Abstract: Effective automation hinges on deciding when to act and when to escalate. We model this as a decision under uncertainty: an LLM forms a prediction, es

ACTUAL BREAKING NEWS that sounds like an @TheOnion Headline: Florida man/Adjudicated rapist/convicted felon/one-time close personal friend with Jeffrey Epstein who has six corporate bankruptcies in hi

arXiv:2604.09462v1 Announce Type: new Abstract: Assistive teleoperation enhances efficiency via shared control, yet inter-operator variability, stemming from diverse habits and expertise, induces high

arXiv:2604.09035v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) with autoregressive world models suffers from compounding errors, whereas diffusion world models mitigate this

arXiv:2510.20512v2 Announce Type: replace Abstract: Recent progress in accelerating text-to-image diffusion models enables high-fidelity synthesis within a single denoising step. However, customizing

arXiv:2502.08691v2 Announce Type: replace-cross Abstract: Understanding human behavior and society is a central focus in social sciences, with the rise of generative social science marking a significa

A study has found that AI chatbots incorrectly diagnose patients in more than 80% of early medical cases, raising significant concerns about the reliability of AI tools in clinical settings. The resea

Alienated Europe Alienated the religious right Alienated Rogan, Carlson and many more Declared a war that even he can’t justify Messed up the Middle East Drove up the price of oil Drove up inflation U

arXiv:2602.13939v3 Announce Type: replace-cross Abstract: Business environments characterized by intermittent demand, high variability, and multi-step planning horizons require forecasting policies th

Veronica Irwin / Transformer: Anthropic says its $20M donation to Public First Action can't be “used to influence federal elections” and is to educate the public on AI policy — The company's money isn

arXiv:2604.09288v1 Announce Type: new Abstract: Trusted multi-view classification typically relies on a view-wise evidential fusion process: each view independently produces class evidence and uncerta

arXiv:2604.08756v1 Announce Type: new Abstract: The situated view of cognition holds that intelligent behavior depends not only on internal memory, but on an agent's active use of environmental resour

As AI agents accelerate coding, what is the future of software engineering? Some trends are clear, such as the Product Management Bottleneck, referring to the idea that we are more constrained by deci

arXiv:2604.08355v2 Announce Type: replace Abstract: Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered.

arXiv:2604.08999v1 Announce Type: cross Abstract: Table serialization remains a critical bottleneck for Large Language Models (LLMs) in complex table question answering, hindered by challenges such as