arXiv
SceneBind: Binding What and Where Across Vision, Audio and Language
We present SceneBind, an omni-modal representation of realistic scenes with joint semantic and 3D spatial understandi...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Pretraining Data Can Be Poisoned through Computational Propaganda
Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate. Prior wo...
arXiv
SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions
Editing the figures in a research paper is a routine and time-consuming part of everyday research practice: authors r...
arXiv
RoboTTT: Context Scaling for Robot Policies
Recent robot foundation models operate with single-step or short-history visuomotor context. We introduce Test-Time-T...
HuggingFace
RoboTTT: Context Scaling for Robot Policies
Recent robot foundation models operate with single-step or short-history visuomotor context. We introduce Test-Time-T...
HuggingFace
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn inte...
HuggingFace
Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel
We report a way to make a frozen small language model both more capable and dramatically cheaper at once, without cha...
HuggingFace
MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them ...
HuggingFace
BadWAM: When World-Action Models Dream Right but Act Wrong
World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting action...
HuggingFace
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seekin...
HuggingFace
WanSong v1.0 Technical Report
Music generation foundation models have recently attracted significant industry attention. However, achieving efficie...
HuggingFace
Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes
Human cognition does not separate understanding and generation. A teacher at a whiteboard speaks and draws together, ...