2025
Zoomer: Adaptive Image Focus Optimization for Black-box MLLM.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, May, 2025
MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention.
,
,
,
,
,
,
,
,
,
,
CoRR, April, 2025
VisRL: Intention-Driven Visual Perception via Reinforced Reasoning.
CoRR, March, 2025
On Memory Construction and Retrieval for Personalized Conversational Agents.
,
,
,
,
,
,
,
,
,
,
CoRR, February, 2025
Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key.
CoRR, January, 2025
SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents.
,
,
,
,
,
,
,
,
,
,
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
SCBench: A KV Cache-Centric Analysis of Long-Context Methods.
,
,
,
,
,
,
,
,
,
,
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
2024
LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation.
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
Mitigate Position Bias in Large Language Models via Scaling a Single Dimension.
CoRR, 2024
A Large-scale Medical Visual Task Adaptation Benchmark.
CoRR, 2024
LLM-ABR: Designing Adaptive Bitrate Algorithms via Large Language Models.
CoRR, 2024
LLM-RadJudge: Achieving Radiologist-Level Evaluation for X-Ray Report Generation.
CoRR, 2024
LSPT: Long-term Spatial Prompt Tuning for Visual Representation Learning.
CoRR, 2024
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention.
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Addressing Signal Delay in Deep Reinforcement Learning.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
CNN Kernels Can Be the Best Shapelets.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Designing Network Algorithms via Large Language Models.
Proceedings of the 23rd ACM Workshop on Hot Topics in Networks, 2024
Unified Medical Image Pre-training in Language-Guided Common Semantic Space.
Proceedings of the Computer Vision - ECCV 2024, 2024
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression.
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Findings of the Association for Computational Linguistics, 2024
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024
2023
Toward Open-ended Embodied Tasks Solving.
CoRR, 2023
AdaMedGraph: Adaboosting Graph Neural Networks for Personalized Medicine.
CoRR, 2023
Is Risk-Sensitive Reinforcement Learning Properly Resolved?
CoRR, 2023
Protecting the Future: Neonatal Seizure Detection with Spatial-Temporal Modeling.
Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, 2023
CircuitNet: A Generic Neural Network to Realize Universal Circuit Motif Modeling.
Proceedings of the International Conference on Machine Learning, 2023
Data Continuity Matters: Improving Sequence Modeling with Lipschitz Regularizer.
Proceedings of the Eleventh International Conference on Learning Representations, 2023
Adaptive Policy Learning for Offline-to-Online Reinforcement Learning.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
2022
Accurate and Explainable Recommendation via Review Rationalization.
Proceedings of the WWW '22: The ACM Web Conference 2022, Virtual Event, Lyon, France, April 25, 2022
MINDSim: User Simulator for News Recommenders.
Proceedings of the WWW '22: The ACM Web Conference 2022, Virtual Event, Lyon, France, April 25, 2022
Bootstrapped Transformer for Offline Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble.
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022
Variational oracle guiding for reinforcement learning.
Proceedings of the Tenth International Conference on Learning Representations, 2022
2021
Path-BN: Towards effective batch normalization in the Path Space for ReLU networks.
Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021
2020
PMA-DRL: A parallel model-augmented framework for deep reinforcement learning algorithms.
Neurocomputing, 2020
I4R: Promoting Deep Reinforcement Learning by the Indicator for Expressive Representations.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020
2019
Improving Deep Learning by Regularized Scale-Free MSE of Representations.
Proceedings of the Neural Information Processing - 26th International Conference, 2019
2018
CoChat: Enabling Bot and Human Collaboration for Task Completion.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018