Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models
Paper • 2609.26637 • Published • 12 •
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
commentedon a paper about 4 hours ago
Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models updated a dataset about 4 hours ago
librarian-bots/paper-recommendations-v2 commentedon a paper about 4 hours ago
X-Planner: Event-Structured Task Planning for Embodied IntelligenceOrganizations
commented 10
papers about 4 hours ago
X-Planner: Event-Structured Task Planning for Embodied Intelligence
Paper • 2609.25187 • Published • 1 •
2
Calibration as a First-Class Criterion in LLM Evaluation
Paper • 2609.26489 • Published • 2 •
2
StudentBench: AI and human tutoring yield equivalent GRE learning gains
Paper • 2609.28470 • Published • 3 •
6
The Past Frames the Future: Memory for Autoregressive Video Generation
Paper • 2609.28466 • Published • 36 •
2
All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation
Paper • 2609.27901 • Published • 5 •
2
WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents
Paper • 2609.27490 • Published • 8 •
2
HappyWorld-Bench
Paper • 2609.24308 • Published • 39 •
3
PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing
Paper • 2609.23784 • Published • 10 •
2
RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling
Paper • 2609.22947 • Published • 21 •
2
commented 10
papers about 5 hours ago
GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression
Paper • 2609.25963 • Published • 11 •
2
PACT: From Credit Assignment to Critic Alignment
Paper • 2609.26355 • Published • 15 •
3
Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents
Paper • 2609.27334 • Published • 34 •
2
Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery
Paper • 2609.27980 • Published • 3 •
3
Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
Paper • 2609.27321 • Published • 8 •
1
Self-Organizing Agent Teams Learn to Reason Together
Paper • 2609.22682 • Published • 4 •
2
Knowledge Pull Requests for Continual Document Authoring
Paper • 2609.26634 • Published • 2 •
2
InternW0: A Foundational Physical World Model for Efficient Real-World Interactions
Paper • 2609.27656 • Published • 5 •
1
The Linear Representation Hypothesis Needs a Group Action
Paper • 2609.27158 • Published • 2 •
2
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
Paper • 2609.26780 • Published • 82 •
5