GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
Paper • 2604.17091 • Published • 25
boyan.yu
seamoonlight
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 5 days ago
StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models upvoted a paper 5 days ago
SPEED-Bench: A Unified and Diverse Benchmark for Speculative DecodingOrganizations
None yet
upvoted 4
papers 5 days ago
StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models
Paper • 2608.26067 • Published • 19
SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
Paper • 2604.09557 • Published • 14
HuggingFace's Transformers: State-of-the-art Natural Language Processing
Paper • 1910.03771 • Published • 28
upvoted 9
papers 18 days ago
VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models
Paper • 2606.16140 • Published • 126
MiniMax Sparse Attention
Paper • 2606.13392 • Published • 166
JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence
Paper • 2606.14777 • Published • 217
Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget
Paper • 2607.13125 • Published • 141
Kimi K3: Open Frontier Intelligence
Paper • 2607.24653 • Published • 514
MOSS-VL Technical Report
Paper • 2608.15045 • Published • 51
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
Paper • 2607.23802 • Published • 106
Self-Supervised Visual On-Policy Distillation
Paper • 2608.14144 • Published • 170
On-Policy Self-Distillation without Any Supervision
Paper • 2608.06296 • Published • 218
upvoted a paper 10 months ago
benchmark test
6
#1 opened 10 months ago
by seamoonlight
liked a
dataset 12 months ago