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