Changshui Zhang

Beyond Tokens: Dynamic Latent Reasoning via Semantic Residual Refinement AAAI 2026 Kronos: A Foundation Model for the Language of Financial Markets AAAI 2026 Learning without Isolation: Pathway Protection for Continual Learning ICML 2025 CALM: Consensus-Aware Localized Merging for Multi-Task Learning ICML 2025 Adaptive Localization of Knowledge Negation for Continual LLM Unlearning ICML 2025 Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models COLING 2025 Assimilation and Accommodation: Task-Adaptive Hierarchical Abstraction for Solving Web Tasks ACL 2025 Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization NIPS 2024 A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning NAACL 2024 Balancing Similarity and Complementarity for Federated Learning ICML 2024 CLAP: Collaborative Adaptation for Patchwork Learning ICLR 2024 CLOMO: Counterfactual Logical Modification with Large Language Models ACL 2024 Accurate Forgetting for Heterogeneous Federated Continual Learning ICLR 2024 Abstraction-of-Thought Makes Language Models Better Reasoners EMNLP 2024 Subjective Topic meets LLMs: Unleashing Comprehensive, Reflective and Creative Thinking through the Negation of Negation EMNLP 2024 Faithful Question Answering with Monte-Carlo Planning ACL 2023 Structured BFGS Method for Optimal Doubly Stochastic Matrix Approximation AAAI 2023 Synergy-of-Experts: Collaborate to Improve Adversarial Robustness NIPS 2022 ViTAS: Vision Transformer Architecture Search ECCV 2022 GreedyNASv2: Greedier Search With a Greedy Path Filter CVPR 2022 MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure EMNLP 2022 METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation NAACL 2022 Learning a Proposal Classifier for Multiple Object Tracking CVPR 2021 ReSSL: Relational Self-Supervised Learning with Weak Augmentation NIPS 2021 Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning NIPS 2021 Prioritized Architecture Sampling With Monto-Carlo Tree Search CVPR 2021 BCNet: Searching for Network Width With Bilaterally Coupled Network CVPR 2021 Exophoric Pronoun Resolution in Dialogues with Topic Regularization EMNLP 2021 Learning With Privileged Tasks ICCV 2021 Weakly Supervised Contrastive Learning ICCV 2021 Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples ICLR 2021 Locally Free Weight Sharing for Network Width Search ICLR 2021 K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets ICML 2021 Reborn Filters: Pruning Convolutional Neural Networks with Limited Data AAAI 2020 GreedyNAS: Towards Fast One-Shot NAS With Greedy Supernet CVPR 2020 Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space NIPS 2020 Few Sample Knowledge Distillation for Efficient Network Compression CVPR 2020 Boosting Semantic Human Matting With Coarse Annotations CVPR 2020 When Counterpoint Meets Chinese Folk Melodies NIPS 2020 RL-Duet: Online Music Accompaniment Generation Using Deep Reinforcement Learning AAAI 2020 Sparse Coding with Gated Learned ISTA ICLR 2020 Semismooth Newton Algorithm for Efficient Projections onto $\ell_1, ∞$-norm Ball ICML 2020 What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues IJCNLP 2019 Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks NIPS 2019 What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues EMNLP 2019 Deep Defense: Training DNNs with Improved Adversarial Robustness NIPS 2018 Sparse DNNs with Improved Adversarial Robustness NIPS 2018 Connectionist Temporal Classification with Maximum Entropy Regularization NIPS 2018 Learning Efficient Convolutional Networks Through Network Slimming ICCV 2017 Recurrent Convolutional Neural Networks for Continuous Sign Language Recognition by Staged Optimization CVPR 2017 Non-Asymptotic Analysis of Relational Learning with One Network AISTATS 2014 Exploiting the Limits of Structure Learning via Inherent Symmetry AISTATS 2014 Seeing the Arrow of Time CVPR 2014 Multi-Stage Multi-Task Feature Learning JMLR 2013 A General Iterative Shrinkage and Thresholding Algorithm for Non-convex Regularized Optimization Problems ICML 2013 High-dimensional Inference via Lipschitz Sparsity-Yielding Regularizers AISTATS 2013 Multi-Stage Multi-Task Feature Learning NIPS 2012 Learning Kernels with Radiuses of Minimum Enclosing Balls NIPS 2010