Profiles2022-2026
Peng Li
Institute for AI Industry Research (AIR), Tsinghua University, Beijing
30Papers
0Last author
24Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers30
- MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment GroundingAuthor 8 of 12ACL 2026 · 10 citations
- Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement LearningAuthor 6 of 10ACL 2026 · 8 citations
- Pessimistic Verification for Open-Ended Math QuestionsAuthor 4 of 5ICML 2026 · 2 citations
- Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific PriorsAuthor 9 of 10ACL Findings 2026
- DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba PictogramsAuthor 9 of 10EMNLP Findings 2025 · 2 citations
- Adversarial Robust Memory-Based Continual LearnerAuthor 6 of 7ICCV 2025 · 1 citation
- Perspective Transition of Large Language Models for Solving Subjective TasksAuthor 7 of 8ACL Findings 2025 · 1 citation
- AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient OptimizationAuthor 6 of 12CVPR 2025
- MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language ModelsAuthor 10 of 11EMNLP 2025
- Budget-Constrained Tool Learning with PlanningAuthor 2 of 6ACL Findings 2024 · 5 citations
- CODIS: Benchmarking Context-dependent Visual Comprehension for Multimodal Large Language ModelsAuthor 11 of 14ACL 2024 · 3 citations
- FuseGen: PLM Fusion for Data-generation based Zero-shot LearningAuthor 3 of 6EMNLP 2024 · 3 citations
- Model Composition for Multimodal Large Language ModelsAuthor 6 of 11ACL 2024 · 2 citations
- PANDA: Preference Adaptation for Enhancing Domain-Specific Abilities of LLMsAuthor 5 of 9ACL Findings 2024
- Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language ModelsAuthor 5 of 7ACL 2024
- Self-Knowledge Guided Retrieval Augmentation for Large Language ModelsAuthor 2 of 4EMNLP Findings 2023 · 62 citations
- Knowledge Transfer in Incremental Learning for Multilingual Neural Machine TranslationAuthor 2 of 5ACL 2023 · 17 citations
- Learning to Relate to Previous Turns in Conversational SearchAuthor 5 of 7KDD 2023 · 16 citations
- Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule AccumulationAuthor 2 of 3EMNLP 2023 · 7 citations
- Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive OptimizationAuthor 3 of 5ICLR 2023 · 6 citations
- Continual Knowledge Distillation for Neural Machine TranslationAuthor 2 of 4ACL 2023 · 5 citations
- Hard Sample Aware Prompt-TuningAuthor 4 of 5ACL 2023 · 4 citations
- Learn and Consolidate: Continual Adaptation for Zero-Shot and Multilingual Neural Machine TranslationAuthor 2 of 5EMNLP 2023 · 4 citations
- Improving Adversarial Robustness of Deep Equilibrium Models with Explicit Regulations Along the Neural DynamicsAuthor 2 of 4ICML 2023 · 3 citations
- Weakly Supervised Vision-and-Language Pre-training with Relative RepresentationsAuthor 2 of 4ACL 2023 · 3 citations
- Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language ModelsAuthor 3 of 4ACL 2023 · 1 citation
- Revisiting Source Context in Nearest Neighbor Machine TranslationAuthor 2 of 3EMNLP 2023
- A Template-based Method for Constrained Neural Machine TranslationAuthor 2 of 6EMNLP 2022 · 14 citations
- End-to-End Unsupervised Vision-and-Language Pre-training with Referring Expression MatchingAuthor 2 of 4EMNLP 2022 · 7 citations
- CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text GenerationAuthor 4 of 7ACL 2022
