B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
Paper • 2412.17256 • Published • 47
KaLM
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
zifeishan
authored 11
papers 3 days ago
On the Perception Bottleneck of VLMs for Chart Understanding
Paper • 2503.18435 • Published • 1
KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
Paper • 2506.20923 • Published • 10
LexSemBridge: Fine-Grained Dense Representation Enhancement through Token-Aware Embedding Augmentation
Paper • 2508.17858 • Published • 10
RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents
Paper • 2601.18130 • Published • 2
DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens
Paper • 2502.11493 • Published
SkillNet: Create, Evaluate, and Connect AI Skills
Paper • 2603.04448 • Published • 93
ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart Editing
Paper • 2601.21694 • Published • 1
GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows
Paper • 2604.15715 • Published • 3
Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language
Paper • 2604.19667 • Published • 20
Compression Represents Intelligence Linearly
Paper • 2404.09937 • Published • 28
zifeishan
authored a
paper about 1 month ago
YanshekWoo
authored a
paper about 1 month ago
YanshekWoo
authored 2
papers 6 months ago
YanshekWoo
authored 4
papers over 1 year ago
CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models
Paper • 2412.07393 • Published • 2
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
Paper • 2501.01028 • Published • 19
FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
Paper • 2410.10293 • Published
MSDF: A General Open-Domain Multi-Skill Dialog Framework
Paper • 2206.08626 • Published • 2
zifeishan
authored a
paper over 1 year ago