hf-daily-papers-2026-05-29
AI · · 1 min read
HuggingFace Daily Papers - 2026-05-29
Found 15 daily papers
1. Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
- Upvotes: 0
2. When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
- Upvotes: 0
3. Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence
- Upvotes: 0
4. Thinking Before Constraining: A Unified Decoding Framework for Large Language Models
- Upvotes: 0
5. PhyGenHOI: Physically-Aware 4D Generation of Dynamic Human-Object Interactions
- Upvotes: 0
6. UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering
- Upvotes: 0
7. ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage
- Upvotes: 0
8. RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains
- Upvotes: 0
9. Discovering Cooperative Pipelines: Autoresearch for Sequential Social Dilemmas
- Upvotes: 0
10. Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering
- Upvotes: 0
11. Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation
- Upvotes: 0
12. ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood
- Upvotes: 0
13. Colored Noise Diffusion Sampling
- Upvotes: 0
14. Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
- Upvotes: 0
15. Is Position Bias in Dense Retrievers Built In-or Learned from Data?
- Upvotes: 0