SciLT: Long-Tailed Classification in Scientific Image Domains
Paper • 2604.03687 • Published • 3
specimba
specimba
AI & ML interests
None yet
Recent Activity
upvoted a paper about 10 hours ago
SciLT: Long-Tailed Classification in Scientific Image Domains upvoted a paper about 10 hours ago
Can LLMs Learn to Reason Robustly under Noisy Supervision? upvoted a paper about 10 hours ago
CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal ModelsOrganizations
upvoted 19
papers about 10 hours ago
Can LLMs Learn to Reason Robustly under Noisy Supervision?
Paper • 2604.03993 • Published • 9
CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models
Paper • 2604.04780 • Published • 5
Less Detail, Better Answers: Degradation-Driven Prompting for VQA
Paper • 2604.04838 • Published • 7
Memory Intelligence Agent
Paper • 2604.04503 • Published • 7
PLUME: Latent Reasoning Based Universal Multimodal Embedding
Paper • 2604.02073 • Published • 8
Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
Paper • 2604.04759 • Published • 11
Self-Execution Simulation Improves Coding Models
Paper • 2604.03253 • Published • 22
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Paper • 2604.04804 • Published • 19
FileGram: Grounding Agent Personalization in File-System Behavioral Traces
Paper • 2604.04901 • Published • 24
Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
Paper • 2604.02288 • Published • 23
ClawArena: Benchmarking AI Agents in Evolving Information Environments
Paper • 2604.04202 • Published • 25
Adam's Law: Textual Frequency Law on Large Language Models
Paper • 2604.02176 • Published • 45
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
Paper • 2604.04707 • Published • 146
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Paper • 2604.04771 • Published • 89
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Paper • 2604.04921 • Published • 62
AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks
Paper • 2604.01487 • Published • 6
Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression
Paper • 2604.01609 • Published • 6
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Paper • 2604.02721 • Published • 61
upvoted a paper 1 day ago