arXiv
Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs
Aligned language models routinely misreport under non-evidential incentive pressure: they agree with a confident user...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Win by Silence: Deletion Non-Monotonicity, Autonomous Exploitation, and Typed-State Gating in LLM Plan Evaluation
Plan evaluators can reward a strategic plan for becoming less explicit. This paper studies that failure in a staged e...
arXiv
Dynamic Resource Allocation for Ensemble Determinization MCTS
Simulation-based algorithms are especially suited for high-uncertainty environments such as adversarial board games w...
arXiv
Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time. We ask whether a ...
arXiv
PalmClaw: A Native On-Device Agent Framework for Mobile Phones
Large Language Model (LLM) agents have moved beyond generating responses to executing multi-step tasks by calling too...
arXiv
TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale
Training robust autonomous driving agents requires a simulator that is fast enough for reinforcement learning at scal...
arXiv
Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they ra...
HuggingFace
Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution
LLM-based coding agents have significantly advanced automated software issue resolution, yet they remain highly prone...
HuggingFace
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
In this paper, we propose SpectraReward, a training-free reward function that turns pretrained MLLMs into off-the-she...
HuggingFace
Latent-Identity Tuning in Text-to-Image Personalization Models
Generating and editing a person's face demands high precision, as even minor modifications can significantly alter a ...
HuggingFace
EgoSteer: A Full-Stack System Towards Steerable Dexterous Manipulation from Egocentric Videos
Steerability is a defining capability of generalist robot policies, yet remains largely absent in dexterous-hand syst...
HuggingFace
Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model
Recent foundation image and video generation models offer strong generalization and controllability, but their direct...