Hugging Face · Daily Papers
Daily machine learning papers highlighted by Hugging Face.
Read through RSSHubAppears in:IA
Latest from Hugging Face · Daily Papers
- Muir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter Readoutil y a 3 j
- Terminal-style Mathematical Modeling Bench: The First Agentic and Verifiable Benchmark for Mathematical Modelingil y a 3 j
- SAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specializationil y a 3 j
- Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentationil y a 3 j
- Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokensil y a 4 j
- VFlash: Fast, Accurate Visual Planning via Flash Primitive Decodingil y a 4 j
- SLA: Scaling Spatial-Language-Action Model via Continual Pre-trainingil y a 4 j
- WeLM-Image: A Unified Image Generation Model towards Visual Intelligenceil y a 4 j
- Towards Foundation Decision Models: Drexil y a 4 j
- EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failureil y a 4 j
- SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimizationil y a 4 j
- Information Games: Strategic Crowding and Firm Repositioning in Language-Model Spaceil y a 4 j
- NPCBench: A Clinical Apprenticeship Benchmark for Multimodal Care-Pathway Reasoning in Nasopharyngeal Carcinomail y a 4 j
- On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transferil y a 4 j
- Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generationil y a 4 j
- TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editingil y a 5 j
- Open-HumanScale: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Modelsil y a 5 j
- Future Representation Distillation for Imagination-free World Action Modelsil y a 5 j
- Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Modelsil y a 5 j
- Tools Need Not Speak in Text: Latent Context Compression for Agentsil y a 5 j
- From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligenceil y a 5 j
- Harness-S: Learning from Sibling Harnesses for Generalizable Agent Trainingil y a 6 j
- VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agentsil y a 6 j
- StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Modelsil y a 6 j
- HeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulationil y a 6 j
- EvoMemState: Evolving Memory State for Personal Agentsil y a 7 j
- Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agentsil y a 8 j
- Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRandil y a 9 j
- Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognitionil y a 9 j
- SynthFaces: Balanced Large Scale Human Datasetil y a 11 j