Profiles2020-2026
Yaliang Li
Alibaba Group
69Papers
10Last author
115Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers69
- On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic WeightingAuthor 6 of 8ICLR 2026 · 100 citations
- Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model AgentsAuthor 6 of 7ACL 2026 · 40 citations
- BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement FinetuningAuthor 5 of 7ICLR 2026 · 15 citations
- Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its FriendsAuthor 7 of 8ICLR 2026 · 13 citations
- On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language ModelsAuthor 6 of 7ICML 2026 · 7 citations
- Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action MemoryAuthor 4 of 6ACL 2026 · 5 citations
- Grounded in Reality: Learning and Deploying Proactive LLM from Offline LogsAuthor 7 of 8ICML 2026 · 2 citations
- Accurate Table Question Answering with Accessible LLMsAuthor 4 of 7ICDE 2026 · 1 citation
- AttriCtrl: A Generalizable Framework for Controlling Semantic Attribute Intensity in Diffusion ModelsAuthor 6 of 7ICLR 2026
- HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized BenchmarksAuthor 5 of 6CVPR 2026
- IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement LearningAuthor 5 of 6ICML 2026
- Private Direct Preference Optimization for LLM AlignmentAuthor 5 of 6CCS 2026
- Retrieval Heads are DynamicAuthor 6 of 9ACL 2026
- Provable Scaling Laws for the Test-Time Compute of Large Language ModelsAuthor 3 of 5NeurIPS 2025 · 16 citations
- Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined DataAuthor 5 of 6NeurIPS 2025 · 14 citations
- Responsible Diffusion Models via Constraining Text Embeddings within Safe RegionsAuthor 2 of 4WWW 2025 · 11 citations
- Less is More: High-value Data Selection for Visual Instruction TuningAuthor 5 of 6ACM MM 2025 · 3 citations
- ViFT: Towards Visual Instruction-Free Fine-tuning for Large Vision-Language ModelsAuthor 5 of 6EMNLP Findings 2025 · 1 citation
- A Bargaining-Based Approach for Feature Trading in Vertical Federated LearningAuthor 4 of 6ICDE 2025
- Agent-Oriented Planning in Multi-Agent SystemsAuthor 6 of 6ICLR 2025
- Enhancing Multimodal Retrieval via Complementary Information Extraction and AlignmentAuthor 3 of 4ACL 2025
- Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion ModelsAuthor 7 of 7ICLR 2025
- Img-Diff: Contrastive Data Synthesis for Multimodal Large Language ModelsAuthor 5 of 6CVPR 2025
- Text-to-SQL Empowered by Large Language Models: A Benchmark EvaluationAuthor 3 of 7VLDB 2024 · 609 citations
- Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client ResourcesAuthor 5 of 5NeurIPS 2024 · 178 citations
- Improving LoRA in Privacy-preserving Federated LearningAuthor 3 of 4ICLR 2024 · 173 citations
- EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D ParallelismAuthor 3 of 5ICML 2024 · 73 citations
- Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 KilobytesAuthor 5 of 6ICML 2024 · 73 citations
- FedBiOT: LLM Local Fine-tuning in Federated Learning without Full ModelAuthor 3 of 5KDD 2024 · 52 citations
- On the Convergence of Zeroth-Order Federated Tuning for Large Language ModelsAuthor 4 of 5KDD 2024 · 17 citations
Showing the 30 most recent indexed papers.
