Hugging Face · Daily Papers
Daily machine learning papers highlighted by Hugging Face.
經 RSSHub 讀取所屬板塊:AI
Hugging Face · Daily Papers 最新
- Muir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter Readout3 天前
- Terminal-style Mathematical Modeling Bench: The First Agentic and Verifiable Benchmark for Mathematical Modeling3 天前
- SAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization3 天前
- Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation3 天前
- Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens4 天前
- VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding4 天前
- SLA: Scaling Spatial-Language-Action Model via Continual Pre-training4 天前
- WeLM-Image: A Unified Image Generation Model towards Visual Intelligence4 天前
- Towards Foundation Decision Models: Drex4 天前
- EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure4 天前
- SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization4 天前
- Information Games: Strategic Crowding and Firm Repositioning in Language-Model Space4 天前
- NPCBench: A Clinical Apprenticeship Benchmark for Multimodal Care-Pathway Reasoning in Nasopharyngeal Carcinoma4 天前
- On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer4 天前
- Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation4 天前
- TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing5 天前
- Open-HumanScale: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models5 天前
- Future Representation Distillation for Imagination-free World Action Models5 天前
- Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models5 天前
- Tools Need Not Speak in Text: Latent Context Compression for Agents5 天前
- From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence5 天前
- Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training6 天前
- VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents6 天前
- StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models6 天前
- HeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulation6 天前
- EvoMemState: Evolving Memory State for Personal Agents7 天前
- Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents8 天前
- Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand9 天前
- Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognition9 天前
- SynthFaces: Balanced Large Scale Human Dataset11 天前