arXiv
Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?
Computer-use agents (CUAs) increasingly act through desktop GUIs to complete long-horizon tasks. Current benchmarks p...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
$π\mathbf{R}^2$: Reactive Real-time Flow Policies
Generalist manipulation policies increasingly take the form of action-chunking flow policies built on large pretraine...
arXiv
Pass the Baton: Trajectory-Relayed On-Policy Distillation
On-policy distillation (OPD) grounds token-level supervision in the student's own trajectory, yet suffers from prefix...
HuggingFace
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often c...
HuggingFace
Shieldstral
We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms mod...
HuggingFace
Wonder: Video World Model Done Better
We present Wonder, a general-purpose video world model for real-time, camera-controllable world exploration. Given an...
HuggingFace
OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs
Emerging Omni-modal Large Language Models (OmniLLMs) enable unified understanding of text, audio, and video, but thei...
HuggingFace
Visual prompt engineering for video models
In the age of foundation models, a model is only as good as its prompt. For this reason, prompt engineering has becom...
HuggingFace
Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory
Long-term memory systems store what a user says in an external store and retrieve it when a related query arrives. Th...
HuggingFace
PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models
We introduce PerceptionBench, a benchmark specifically designed to evaluate the atomic visual perception capabilities...
HuggingFace
HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone
Learning deployable manipulation policies is bottlenecked by the scarcity of data that is both high-fidelity and scal...
HuggingFace
A New Role for Relevance: Guiding Corpus Interaction in Agentic Search
Relevance is a query-dependent estimate of whether a document or excerpt contains useful evidence. Existing retrieval...