arXiv
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigation
Aerial vision-language navigation (VLN) requires an embodied agent to integrate visual evidence over time, plan futur...
HuggingFace
Agent Safety Should Be a Runtime Contract
The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitu...
HuggingFace
StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization
Previsualization is an intermediate layer between ideas and production in film, games, architecture, and urban design...
HuggingFace
AVA-Encoder: Towards Agent-Native Video Representation Learning
Creative agents still lack an effective way to learn from high-quality human films, limiting their ability to produce...
HuggingFace
AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research
World modeling is an unsettled field: architectures, training objectives, and state representations interact in compl...
HuggingFace
MBA: Multimodal Benchmark and Agents for Real-World Business Ideation
Agentic systems powered by large language models (LLMs) have opened new opportunities for business ideation. Yet exis...
HuggingFace
From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection
Videos captured through glass often contain reflections that degrade visual quality and interfere with downstream vis...
HuggingFace
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's...
HuggingFace
NeuPAT: Neuron-aware Plasticity Allocation Tuning for Language-Preserving MLLMs
Multimodal expansion of large language models (LLMs) enables new perceptual capabilities but often compromises the la...
HuggingFace
The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images
The "thinking-with-images" paradigm equips multimodal LLMs with active visual operations such as crop-and-zoom. Howev...
HuggingFace
Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives
The rapid advancement of Large Language Models (LLMs) is revolutionizing AI for Games by enabling open-ended and flui...