Profiles2020-2026
Zhaopeng Tu
Tencent
56Papers
23Last author
61Unique co-authors
1First author
1Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers56
- DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing ReasoningAuthor 13 of 15ICLR 2026 · 271 citations
- RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon AgentsAuthor 1 of 1ICLR 2026 · 59 citations
- BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMsAuthor 13 of 14ACL 2026
- Identifying the Achilles' Heel: An Iterative Method for Uncovering Factual Errors in Large Language ModelsAuthor 9 of 10ACL Findings 2026
- Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language ModelsAuthor 12 of 13ACL Findings 2026
- Social Welfare Function Leaderboard: On the Emergence of LLM Agents as the Welfare DictatorAuthor 14 of 17ACL Findings 2026
- Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal TrainingAuthor 8 of 8ACL 2025 · 65 citations
- Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable RewardsAuthor 7 of 9NeurIPS 2025 · 46 citations
- The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning ModelsAuthor 11 of 13NeurIPS 2025 · 33 citations
- Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMsAuthor 7 of 7ACL 2025 · 20 citations
- Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional TrainingAuthor 13 of 15NeurIPS 2025 · 19 citations
- Thoughts Are All Over the Place: On the Underthinking of Long Reasoning ModelsAuthor 12 of 14NeurIPS 2025 · 13 citations
- SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward LearningAuthor 5 of 6NeurIPS 2025 · 10 citations
- Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration PitfallsAuthor 7 of 9ACL 2025 · 9 citations
- Chain-of-Jailbreak Attack for Image Generation Models via Step by Step EditingAuthor 8 of 8ACL Findings 2025 · 1 citation
- Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMsAuthor 8 of 8ACL 2025
- Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning CapabilityAuthor 10 of 10ICML 2025
- Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning ModelsAuthor 12 of 14ICML 2025
- Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form GenerationAuthor 7 of 7EMNLP 2025
- RaSA: Rank-Sharing Low-Rank AdaptationAuthor 2 of 10ICLR 2025
- Unleashing LLM Reasoning Capability via Scalable Question Synthesis from ScratchAuthor 5 of 7ACL 2025
- GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via CipherAuthor 7 of 7ICLR 2024 · 441 citations
- Encouraging Divergent Thinking in Large Language Models through Multi-Agent DebateAuthor 9 of 9EMNLP 2024 · 177 citations
- On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMsAuthor 8 of 9ICLR 2024 · 85 citations
- Apathetic or Empathetic? Evaluating LLMs' Emotional Alignments with HumansAuthor 7 of 9NeurIPS 2024 · 63 citations
- GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware GenerationAuthor 10 of 11ACM MM 2024 · 22 citations
- All Languages Matter: On the Multilingual Safety of LLMsAuthor 2 of 7ACL Findings 2024 · 21 citations
- Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language ModelsAuthor 6 of 8ACL 2024 · 17 citations
- Addressing Entity Translation Problem via Translation Difficulty and Context DiversityAuthor 6 of 6ACL Findings 2024
- Document-Level Machine Translation with Large Language ModelsAuthor 7 of 8EMNLP 2023 · 129 citations
Showing the 30 most recent indexed papers.
