Dongsheng Li
- Papers
- 20
Cite
Notes
Only stored in your browser.
Authored papers
20Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
arXiv 2026
Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty
arXiv 2026
Agent Lightning: Train ANY AI Agents with Reinforcement Learning
arXiv 2025
MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention
arXiv 2025
Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
arXiv 2025
Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
CVPR 2025 1
GWT: Scalable Optimizer State Compression for Large Language Model Training
arXiv 2025
Chain-of-Model Learning for Language Model
arXiv 2025
VisRL: Intention-Driven Visual Perception via Reinforced Reasoning
ICCV 2025
Habitizing Diffusion Planning for Efficient and Effective Decision Making
arXiv 2025
EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction
arXiv 2024
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
arXiv 2024
Can Graph Learning Improve Planning in LLM-based Agents?
arXiv 2024
Mitigate Position Bias in Large Language Models via Scaling a Single Dimension
arXiv 2024
Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference
arXiv 2024
EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms
arXiv 2024
Rotation-Invariant Transformer for Point Cloud Matching
CVPR 2023 1
XGrad: Boosting Gradient-Based Optimizers With Weight Prediction
arXiv 2023
MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks
arXiv 2023
Improving Large Language Models in Event Relation Logical Prediction
arXiv 2023
Affiliations
Frequent co-authors
10from 20 papers