Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptation
Paper
• 2603.01375 • Published
• 1 •
2
Librarian Bot (Bot)
librarian-bot
AI & ML interests
I am a friendly librarian bot working to help improve metadata on the 🤗 hub. Run by Hugging Face'ss Machine Learning Librarian (HF username: davanstrien)
Recent Activity
commented on
a paper
about 6 hours ago
Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptation commented on
a paper
about 6 hours ago
LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models commented on
a paper
about 6 hours ago
AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models Organizations
commented 20 papers about 6 hours ago
LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models
Paper
• 2603.01563 • Published
• 2 •
2
AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models
Paper
• 2603.01236 • Published
• 6 •
2
Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory
Paper
• 2603.04257 • Published
• 11 •
2
SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration
Paper
• 2603.03823 • Published
• 3 •
2
Specificity-aware reinforcement learning for fine-grained open-world classification
Paper
• 2603.03197 • Published
• 2 •
2
HDINO: A Concise and Efficient Open-Vocabulary Detector
Paper
• 2603.02924 • Published
•
2
EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding
Paper
• 2603.04254 • Published
• 1 •
2
Helios: Real Real-Time Long Video Generation Model
Paper
• 2603.04379 • Published
• 119 •
5
MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models
Paper
• 2603.02482 • Published
• 2 •
2
ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors
Paper
• 2603.04338 • Published
• 19 •
3
MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning
Paper
• 2603.03379 • Published
• 23 •
2
RIVER: A Real-Time Interaction Benchmark for Video LLMs
Paper
• 2603.03985 • Published
• 4 •
2
CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video
Paper
• 2603.04291 • Published
• 10 •
2
Phi-4-reasoning-vision-15B Technical Report
Paper
• 2603.03975 • Published
• 13 •
1
Heterogeneous Agent Collaborative Reinforcement Learning
Paper
• 2603.02604 • Published
• 134 •
5
InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions
Paper
• 2603.03646 • Published
• 5 •
2
Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
Paper
• 2603.03447 • Published
• 24 •
3
GroupEnsemble: Efficient Uncertainty Estimation for DETR-based Object Detection
Paper
• 2603.01847 • Published
• 1 •
2
BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning
Paper
• 2603.04124 • Published
• 1 •
2