conftrace_

Xiangyu Liu

23 papers · 2021–2026 · 9 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+11 more ↓ 🌍 Conference Polyglot (9) 🌈 Renaissance Researcher (6) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird
🧭 Keyword Pioneer 🌈 Renaissance Researcher (6) 🌍 Conference Polyglot (9) 🧬 Topic Evolution 🏆 Grand Slam 🏆 Keyword Champion (2) 🗃️ Keyword Collector (120) Prolific Year (6) 💎 Century Club (21) 🔥 Unstoppable (5) The Questioner (2)

Conferences

AAAI (5) ICLR (5) EMNLP (4) ACL (3) NIPS (2) CVPR (1) ICML (1) INTERSPEECH (1) NAACL (1)

Papers

ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders AAAI 2026 Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models AAAI 2026 Is Poisoning a Real Threat to DPO? Maybe More So Than You Think AAAI 2025 Do LLM Agents Have Regret? A Case Study in Online Learning and Games ICLR 2025 Controllable Protein Sequence Generation with LLM Preference Optimization AAAI 2025 Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering ACL 2025 Lunar Twins: We Choose to Go to the Moon with Large Language Models ACL 2025 MVBoost: Boost 3D Reconstruction with Multi-View Refinement CVPR 2025 Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition EMNLP 2025 Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations ICLR 2024 Provable Partially Observable Reinforcement Learning with Privileged Information NIPS 2024 Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies ICLR 2024 Knowledge Graph Error Detection with Contrastive Confidence Adaption AAAI 2024 Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL ICLR 2024 Multi-Aspect Controllable Text Generation with Disentangled Counterfactual Augmentation ACL 2024 Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing ICML 2023 Bayes-MIL: A New Probabilistic Perspective on Attention-based Multiple Instance Learning for Whole Slide Images ICLR 2023 Revisit Systematic Generalization via Meaningful Learning EMNLP 2022 RoChBert: Towards Robust BERT Fine-tuning for Chinese EMNLP 2022 SemAttack: Natural Textual Attacks via Different Semantic Spaces NAACL 2022 Counterfactual Adversarial Learning with Representation Interpolation EMNLP 2021 Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games NIPS 2021 Incorporating External POS Tagger for Punctuation Restoration INTERSPEECH 2021