LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios
Paper • 2509.09926 • Published • 14
Reading list
-
-
What Breaks Knowledge Graph based RAG? Empirical Insights into Reasoning under Incomplete Knowledge
Paper • 2508.08344 • Published -
MemMamba: Rethinking Memory Patterns in State Space Model
Paper • 2510.03279 • Published • 74 -
When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs
Paper • 2510.07499 • Published • 49 -
TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar
Paper • 2510.14972 • Published • 35 -
ReCode: Unify Plan and Action for Universal Granularity Control
Paper • 2510.23564 • Published • 123 -
Code Aesthetics with Agentic Reward Feedback
Paper • 2510.23272 • Published • 9 -
BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
Paper • 2510.18927 • Published • 85 -
ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use
Paper • 2510.27363 • Published • 23 -
Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset
Paper • 2403.09029 • Published • 57 -
Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers
Paper • 2512.17351 • Published • 28 -
Memory in the Age of AI Agents
Paper • 2512.13564 • Published • 157 -
FineVision: Open Data Is All You Need
Paper • 2510.17269 • Published • 79