ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment

Haosen Sun^*, Hongjue Zhao^*, Jiangtao Kong, Xiaochang Li, Qineng Wang, Liwei Jiang, Qi Zhu, Tarek F. Abdelzaher, Yejin Choi, Manling Li^†, Huajie Shao^†

ICLR 2026

Project Page Paper Code

• A unified ODE-based framework for multi-step and adaptive activation steering guided by barrier functions.
• Consistent gains on TruthfulQA (+5.7%), RealToxicityPrompts (+2.4%), UltraFeedback (+2.5%).

ProgressLM: Towards Progress Reasoning in Vision-Language Models

Jianshu Zhang^*, Chengxuan Qian^*, Haosen Sun, Haoran Lu, Dingcheng Wang, Letian Xue, Han Liu

Oral @ ACL 2026
ICLR 2026 Workshop on World Models

Project Page Paper Code

• PROGRESS-BENCH: a benchmark for long-horizon progress reasoning in VLMs, with controlled modality, viewpoint, and answerability.
• Reveals that vanilla VLMs struggle to estimate task progress from a single observation; ProgressLM-3B (SFT + RL) addresses this via episodic retrieval and mental simulation.

T*: Re-thinking Temporal Search for Long-Form Video Understanding

Jinhui Ye^*, Zihan Wang^*, Haosen Sun, Keshigeyan Chandrasegaran, Zane Durante, Cristobal Eyzaguirre, Yonatan Bisk, Juan Carlos Niebles, Ehsan Adeli, Fei-Fei Li, Jiajun Wu, Manling Li

CVPR 2025
Oral @ ICCV 2025 Workshop on LongVid-Foundations
Featured by Stanford AI Blog

Project Page Paper Code

• We introduce LongVideoHaystack (LV-Haystack), a 480-hour dataset for keyframe search in long videos, with 15,092 human-annotated instances (SOTA: 2.1% Temporal F₁).
• Our framework T* reframed temporal search as spatial search with adaptive zooming, boosting GPT-4o from 50.5% to 53.1% and LLaVA-OV from 56.5% to 62.4% on LongVideoBench XL.

Auto-DAS: Automated Proxy Discovery for Training-free Distillation-aware Architecture Search

Haosen Sun, Lujun Li^†, Peijie Dong, Zimian Wei, Shitong Shao

ECCV 2024

Paper Code

• We present Auto-DAS, an automatic proxy discovery framework using an Evolutionary Algorithm (EA) for training-free Distillation-aware Architecture Search (DAS).
• Auto-DAS generalizes well to various architectures and search spaces (e.g. ResNet, ViT, NAS-Bench-101, and NAS-Bench-201), achieving state-of-the-art results in both ranking correlation and final searched accuracy.

Auto-GAS: Automated Proxy Discovery for Training-free Generative Architecture Search

Lujun Li, Haosen Sun, Shiwen Li, Peijie Dong, Wenhan Luo, Wei Xue, Qifeng Liu^†, Yike Guo^†

ECCV 2024

Paper Code

• We introduce Auto-GAS, the first training-free Generation Architecture Search (GAS) framework enabled by an auto-discovered proxy, which achieves competitive scores with 110× faster search than GAN Compression.

Inpaint4DNeRF: Promptable Spatio-Temporal NeRF Inpainting with Generative Diffusion Models

Han Jiang^*, Haosen Sun^*, Ruoxuan Li^*, Yu-Wing Tai, Chi-Keung Tang

arXiv Preprint 2023

Project Page Paper Code

• Inpaint4DNeRF can generate prompt-based objects guided by the seed images and their 3D proxies while preserving multiview consistency. Our generative baseline framework is general and can be readily extended to 4D dynamic NeRFs.

ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment

Haosen Sun^*, Hongjue Zhao^*, Jiangtao Kong, Xiaochang Li, Qineng Wang, Liwei Jiang, Qi Zhu, Tarek F. Abdelzaher, Yejin Choi, Manling Li^†, Huajie Shao^†

ICLR 2026

Project Page Paper Code

• A unified ODE-based framework for multi-step and adaptive activation steering guided by barrier functions.
• Consistent gains on TruthfulQA (+5.7%), RealToxicityPrompts (+2.4%), UltraFeedback (+2.5%).

ProgressLM: Towards Progress Reasoning in Vision-Language Models

Jianshu Zhang^*, Chengxuan Qian^*, Haosen Sun, Haoran Lu, Dingcheng Wang, Letian Xue, Han Liu

Oral @ ACL 2026
ICLR 2026 Workshop on World Models

Project Page Paper Code

• PROGRESS-BENCH: a benchmark for long-horizon progress reasoning in VLMs, with controlled modality, viewpoint, and answerability.
• Reveals that vanilla VLMs struggle to estimate task progress from a single observation; ProgressLM-3B (SFT + RL) addresses this via episodic retrieval and mental simulation.

Flow-Based Knowledge Transfer for Efficient Large Model Distillation

Xinye Yang^*, Junhao Wang^*, Haosen Sun^‡, Xuesheng Zhang, Zebang Liu, Gaochao Xu, Yiwei Chen^†

AAAI 2026

Paper

• FlowDistill leverages invertible normalizing flows to achieve lossless teacher-to-student knowledge transfer.
• It outperforms diffusion-based distillation (+2.1%) while cutting inference 3.5×, advancing SOTA across tasks.

T*: Re-thinking Temporal Search for Long-Form Video Understanding

Jinhui Ye^*, Zihan Wang^*, Haosen Sun, Keshigeyan Chandrasegaran, Zane Durante, Cristobal Eyzaguirre, Yonatan Bisk, Juan Carlos Niebles, Ehsan Adeli, Fei-Fei Li, Jiajun Wu, Manling Li

CVPR 2025
Oral @ ICCV 2025 Workshop on LongVid-Foundations
Featured by Stanford AI Blog

Project Page Paper Code

• We introduce LongVideoHaystack (LV-Haystack), a 480-hour dataset for keyframe search in long videos, with 15,092 human-annotated instances (SOTA: 2.1% Temporal F₁).
• Our framework T* reframed temporal search as spatial search with adaptive zooming, boosting GPT-4o from 50.5% to 53.1% and LLaVA-OV from 56.5% to 62.4% on LongVideoBench XL.

Auto-DAS: Automated Proxy Discovery for Training-free Distillation-aware Architecture Search

Haosen Sun, Lujun Li^†, Peijie Dong, Zimian Wei, Shitong Shao

ECCV 2024

Paper Code

• We present Auto-DAS, an automatic proxy discovery framework using an Evolutionary Algorithm (EA) for training-free Distillation-aware Architecture Search (DAS).
• Auto-DAS generalizes well to various architectures and search spaces (e.g. ResNet, ViT, NAS-Bench-101, and NAS-Bench-201), achieving state-of-the-art results in both ranking correlation and final searched accuracy.

Auto-GAS: Automated Proxy Discovery for Training-free Generative Architecture Search

Lujun Li, Haosen Sun, Shiwen Li, Peijie Dong, Wenhan Luo, Wei Xue, Qifeng Liu^†, Yike Guo^†

ECCV 2024

Paper Code

• We introduce Auto-GAS, the first training-free Generation Architecture Search (GAS) framework enabled by an auto-discovered proxy, which achieves competitive scores with 110× faster search than GAN Compression.

Inpaint4DNeRF: Promptable Spatio-Temporal NeRF Inpainting with Generative Diffusion Models

Han Jiang^*, Haosen Sun^*, Ruoxuan Li^*, Yu-Wing Tai, Chi-Keung Tang

arXiv Preprint 2023

Project Page Paper Code

• Inpaint4DNeRF can generate prompt-based objects guided by the seed images and their 3D proxies while preserving multiview consistency. Our generative baseline framework is general and can be readily extended to 4D dynamic NeRFs.

Registering Neural Radiance Fields as 3D Density Images

Han Jiang^*, Ruoxuan Li^*, Haosen Sun, Yu-Wing Tai, Chi-Keung Tang

arXiv Preprint 2023

Paper

• We propose a method to align and merge pre-trained NeRF models of partially overlapping 3D scenes using a generalized registration pipeline, incorporating key point detection, point set registration, and universal pre-trained descriptor networks with a contrastive learning strategy.