Beomjun Bark

PBJbutter's activity

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

upvoted 2 papers 2 days ago

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment

Paper • 2608.05102 • Published 4 days ago • 63

LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models

Paper • 2608.03457 • Published 5 days ago • 31

upvoted a paper 4 days ago

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Paper • 2608.01964 • Published 6 days ago • 161

upvoted 2 papers 6 days ago

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

Paper • 2607.28617 • Published 10 days ago • 37

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published 14 days ago • 102

upvoted 2 papers 10 days ago

CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition

Paper • 2607.25294 • Published 12 days ago • 49

CAST: Game Solvers as Turn-Level Teachers for LLM Agents

Paper • 2607.25308 • Published 12 days ago • 41

upvoted a paper 11 days ago

A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

Paper • 2607.24223 • Published 13 days ago • 94

upvoted a paper 13 days ago

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

Paper • 2607.22529 • Published 16 days ago • 48

upvoted a paper 18 days ago

DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

Paper • 2607.07820 • Published Jul 8 • 92

upvoted 2 papers 19 days ago

Environment-free Synthetic Data Generation for API-Calling Agents

Paper • 2607.16900 • Published 22 days ago • 20

SWE-Pruner Pro: The Coder LLM Already Knows What to Prune

Paper • 2607.18213 • Published 20 days ago • 79

upvoted 2 papers 20 days ago

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published 24 days ago • 106

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Paper • 2607.14935 • Published 24 days ago • 172

upvoted 3 papers 24 days ago

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Paper • 2607.11886 • Published 27 days ago • 85

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Paper • 2607.12463 • Published 26 days ago • 108

Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation

Paper • 2607.05382 • Published Jul 9 • 87

upvoted 2 papers 26 days ago

Scalable Visual Pretraining for Language Intelligence

Paper • 2607.09657 • Published about 1 month ago • 58

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Paper • 2607.08964 • Published Jul 9 • 77

upvoted a paper 27 days ago

Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing

Paper • 2607.07953 • Published Jul 8 • 16