huggingface-papers-2026-05-30
AI · · 1 min read
Reflective Prompt Tuning through Language Model Function-Calling
Published: 2026-05-19 | Upvotes: 0
Why Far Looks Up: Probing Spatial Representation in Vision-Language Models
Published: 2026-05-27 | Upvotes: 0
CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM
Published: 2026-05-23 | Upvotes: 0
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation
Published: 2026-05-25 | Upvotes: 0
Convex Low-resource Accent-Robust Language Detection in Speech Recognition
Published: 2026-05-21 | Upvotes: 0
DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation
Published: 2026-05-27 | Upvotes: 0
Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection
Published: 2026-05-27 | Upvotes: 0
Reducing Political Manipulation with Consistency Training
Published: 2026-05-27 | Upvotes: 0
Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation
Published: 2026-05-23 | Upvotes: 0
REPOT: Recoverable Program-of-Thought via Checkpoint Repair
Published: 2026-05-27 | Upvotes: 0
Xetrieval: Mechanistically Explaining Dense Retrieval
Published: 2026-05-27 | Upvotes: 0
CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval
Published: 2026-05-27 | Upvotes: 0
EarlyTom: Early Token Compression Completes Fast Video Understanding
Published: 2026-05-27 | Upvotes: 0
Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
Published: 2026-05-20 | Upvotes: 0
PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers
Published: 2026-05-26 | Upvotes: 0
Towards Consistent Video Geometry Estimation
Published: 2026-05-27 | Upvotes: 0
Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
Published: 2026-05-25 | Upvotes: 0
When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
Published: 2026-05-27 | Upvotes: 0
Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence
Published: 2026-05-27 | Upvotes: 0
Thinking Before Constraining: A Unified Decoding Framework for Large Language Models
Published: 2026-05-27 | Upvotes: 0