J C

dark-pen's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 9 hours ago

SAGE: Scalable Agentic 3D Scene Generation for Embodied AI

Paper • 2602.10116 • Published Feb 10 • 13

upvoted a collection about 10 hours ago

💧 LFM2.5

Collection

Collection of post-trained and base LFM2.5 models. • 23 items • Updated about 11 hours ago • 112

upvoted a paper about 11 hours ago

Make Geometry Matter for Spatial Reasoning

Paper • 2603.26639 • Published 4 days ago • 19

upvoted 2 papers about 13 hours ago

Semi-Supervised Reward Modeling via Iterative Self-Training

Paper • 2409.06903 • Published Sep 10, 2024 • 1

WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks

Paper • 2601.02439 • Published Jan 5 • 18

upvoted a collection about 13 hours ago

MergeBench

Collection

A Benchmark for Merging Domain-Specialized LLMs • 2 items • Updated Oct 21, 2025 • 1

upvoted a paper about 13 hours ago

MergeBench: A Benchmark for Merging Domain-Specialized LLMs

Paper • 2505.10833 • Published May 16, 2025 • 2

upvoted a collection about 13 hours ago

merging

Collection

24 items • Updated Nov 23, 2025 • 3

upvoted a paper about 14 hours ago

O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL

Paper • 2601.03743 • Published Jan 7 • 3

upvoted 4 papers about 15 hours ago

Draft-Conditioned Constrained Decoding for Structured Generation in LLMs

Paper • 2603.03305 • Published Feb 8 • 1

RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation

Paper • 2603.25804 • Published 5 days ago • 21

UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

Paper • 2602.02437 • Published Feb 2 • 80

DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Paper • 2602.12205 • Published Feb 12 • 81

upvoted a collection about 15 hours ago

PRIMO R1

Collection

Official release of PRIMO R1, a 7B video MLLM for robotic process reasoning featuring RL-optimized models, SFT/RL datasets, and cross-domain benchmark • 3 items • Updated 14 days ago • 4

upvoted 2 papers about 15 hours ago

From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation

Paper • 2603.15600 • Published 15 days ago • 7

GenMask: Adapting DiT for Segmentation via Direct Mask

Paper • 2603.23906 • Published 7 days ago • 6

upvoted 4 papers about 17 hours ago

Clipping-Free Policy Optimization for Large Language Models

Paper • 2601.22801 • Published Jan 30 • 3

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks

Paper • 2602.05547 • Published Feb 5 • 14

Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers

Paper • 2602.18292 • Published Feb 20 • 11

The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus

Paper • 2603.20105 • Published 11 days ago • 36