Paper-Conference | Jiangtong Lihttps://www.jiangtongli.me/publication_types/paper-conference/Paper-ConferenceHugo Blox Builder (https://hugoblox.com)en-usFri, 01 May 2026 00:00:00 +0000https://www.jiangtongli.me/media/icon_hu68170e94a17a2a43d6dcb45cf0e8e589_3079_512x512_fill_lanczos_center_3.pngPaper-Conferencehttps://www.jiangtongli.me/publication_types/paper-conference/Breaking Dual Bottlenecks: Evolving Unified Multimodal Models into Self-Adaptive Interleaved Visual Reasonershttps://www.jiangtongli.me/publication/icml2026-breakingdualbottlenecks/Fri, 01 May 2026 00:00:00 +0000https://www.jiangtongli.me/publication/icml2026-breakingdualbottlenecks/Can LLMs Really Judge? A Progressive Argumentation-Mining Framework for Distinguishing Understanding from Aggregationhttps://www.jiangtongli.me/publication/acl2026-canllmsjudge/Fri, 01 May 2026 00:00:00 +0000https://www.jiangtongli.me/publication/acl2026-canllmsjudge/Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggershttps://www.jiangtongli.me/publication/ijcai2026-cpgba/Fri, 01 May 2026 00:00:00 +0000https://www.jiangtongli.me/publication/ijcai2026-cpgba/Bridging Visual Dynamics and Reasoning Evaluation: Multimodal Large Language Models for Short Drama Quality Assessmenthttps://www.jiangtongli.me/publication/www2026-dramaqa/Mon, 13 Apr 2026 00:00:00 +0000https://www.jiangtongli.me/publication/www2026-dramaqa/DynaMind: Reconstructing Dynamic Visual Scenes from EEG by Aligning Temporal Dynamics and Multimodal Semantics to Guided Diffusionhttps://www.jiangtongli.me/publication/cvpr2026-dynamind/Sun, 01 Mar 2026 00:00:00 +0000https://www.jiangtongli.me/publication/cvpr2026-dynamind/Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Poolhttps://www.jiangtongli.me/publication/neurips2025-attackbyyourself/Mon, 01 Dec 2025 00:00:00 +0000https://www.jiangtongli.me/publication/neurips2025-attackbyyourself/Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answeringhttps://www.jiangtongli.me/publication/icml2025-divideconquer/Tue, 01 Jul 2025 00:00:00 +0000https://www.jiangtongli.me/publication/icml2025-divideconquer/InspireDebate: Multi-Dimensional Subjective-Objective Evaluation-Guided Reasoning and Optimization for Debatinghttps://www.jiangtongli.me/publication/acl2025-inspiredebate/Tue, 01 Jul 2025 00:00:00 +0000https://www.jiangtongli.me/publication/acl2025-inspiredebate/Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learninghttps://www.jiangtongli.me/publication/icml2024-multipatch/Sun, 21 Jul 2024 00:00:00 +0000https://www.jiangtongli.me/publication/icml2024-multipatch/Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answeringhttps://www.jiangtongli.me/publication/va3-vidqa/Sun, 03 Mar 2024 14:01:16 +0800https://www.jiangtongli.me/publication/va3-vidqa/Knowledge Proxy Intervention for Deconfounded Video Question Answeringhttps://www.jiangtongli.me/publication/deconfounded-vidqa/Sun, 01 Oct 2023 00:00:00 +0000https://www.jiangtongli.me/publication/deconfounded-vidqa/From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answeringhttps://www.jiangtongli.me/publication/causal-vidqa/Tue, 21 Jun 2022 00:00:00 +0000https://www.jiangtongli.me/publication/causal-vidqa/Action-Aware Embedding Enhancement for Image-Text Retrievalhttps://www.jiangtongli.me/publication/motion-itr/Thu, 10 Feb 2022 14:01:16 +0800https://www.jiangtongli.me/publication/motion-itr/Video Semantic Segmentation via Sparse Temporal Transformer,https://www.jiangtongli.me/publication/trans-vss/Tue, 19 Oct 2021 16:31:57 +0800https://www.jiangtongli.me/publication/trans-vss/Modeling Multi-turn Conversation with Deep Utterance Aggregationhttps://www.jiangtongli.me/publication/dua/Sun, 26 Aug 2018 14:01:16 +0800https://www.jiangtongli.me/publication/dua/