Biziel
Grzegorz
AI & ML interests
None yet
Recent Activity
updated a collection about 11 hours ago
Agentic upvoted a paper about 12 hours ago
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable upvoted a paper about 14 hours ago
SWE-Pruner Pro: The Coder LLM Already Knows What to PruneOrganizations
Agentic
-
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
Paper • 2605.05242 • Published • 127 -
MIGRATION-BENCH: Repository-Level Code Migration Benchmark from Java 8
Paper • 2505.09569 • Published • 7 -
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
Paper • 2607.13285 • Published • 213
VLMs
-
LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
Paper • 2501.08282 • Published -
Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play
Paper • 2509.25541 • Published • 142 -
Kwai Keye-VL-2.0 Technical Report
Paper • 2606.10651 • Published • 194 -
Thinking with Visual Grounding
Paper • 2606.16122 • Published • 11
Benchmarking
safety
Agentic
-
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
Paper • 2605.05242 • Published • 127 -
MIGRATION-BENCH: Repository-Level Code Migration Benchmark from Java 8
Paper • 2505.09569 • Published • 7 -
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
Paper • 2607.13285 • Published • 213
World modeling
VLMs
-
LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
Paper • 2501.08282 • Published -
Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play
Paper • 2509.25541 • Published • 142 -
Kwai Keye-VL-2.0 Technical Report
Paper • 2606.10651 • Published • 194 -
Thinking with Visual Grounding
Paper • 2606.16122 • Published • 11
Engineering with LLMs
Benchmarking