Ax Yuhan Liu, Pei Fu, Hang Li, Yukun Qi, Chao Jiang, Jingwen Fu, Zhen Liu, Bin Qin, Zhenbo Luo, Jian Luan, Jingmin Xin 24d ago

ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval

ELVA improves multimodal retrieval using ranking-driven contrastive learning with MLLMs to address grain-level information blindness in universal retrieval.

Ax Yufei Li, Zaiwei Zhang, Mingfu Liang, Kavosh Asadi, Jay Xu, Jimmy Kim, Chongyang Bai, Jieyi Zhang, Hongye Xie, Prachi Agrawal, Dian Yu, Tianyi Chen, Jean-Pascal Billaud, Garret Buell, Yongkang Zhu, Sachin Patil, Brooke Bian, Zhou Fang, Kevin Huang, Shiva Sudanagunta, Yuzhen Huang, Emma Lu, Chris O'Brien, Yang Song, Lihong Li, Jacob Tao, Zhicheng Zhu, Chao Li, Gaoxiang Liu, Neil Wu, Zhongyin Hu, Li Han, Loki Chen, Ming Lei, Greg Rehm, Siyuan Song, Tianwei Zhang, Li Li, Ketan Singh, Yavuz Yetim, Ilyas Atishev, Satendra Gera, Ashkan Sadeghi, Rachel Yan, Nikko Mizutani, Shuaiwen Wang, Song Yang, Zhijing Li, Jiang Liu, Mengying Sun, Fei Tian, Xiaohan Wei, Chonglin Sun, Shuo Gu, Parish Aggarwal, Senthil Manickavelu, Kaushik Rangadurai, Zhi Hua, Frank Shyu, Ruchit Sharma, Liyuan Li, Shike Mei, Wenlin Chen, Santanu Kolay, Ben Schulte, Deepak Chandra, Yang Song, Sandeep Pandey, Xi Liu, Hamed Firooz, Luke Simon 24d ago

GR2 Technical Report

Technical report on GR2, an LLM-based re-ranking system for industrial recommendation pipelines addressing deployment gaps.

Ax Yuanda Xu, Zhengze Zhou, Hejian Sang, Xiaomin Li, Jiaxin Zhang, Xinchen Du, Sen Na, Zhipeng Wang, Alborz Geramifard 24d ago

TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning

Credit assignment method for agentic reinforcement learning that differentiates between exploration and regressive actions in multi-step agent trajectories.

Ax Chengzhi Hu, Xuewen Liu, Jing Zhang, Mengjuan Chen, Zhikai Li, Qingyi Gu 24d ago

Post-Training Pruning for Diffusion Transformers

Develops post-training pruning methods for diffusion transformers to reduce computational overhead in image generation models.

Ax Zhuoxuan Zhang (Yang), Kangqi Ni (Yang), Yuhang Chen (Yang), Mingfu Liang (Yang), Xiaohan Wei (Yang), Yunchen Pu (Yang), Fei Tian (Yang), Chonglin Sun (Yang), Frank Shyu (Yang), Adam (Yang), Song, Sandeep Pandey, Luke Simon, Tianlong Chen, Xi Liu 24d ago

Diffusion-GR2: Diffusion Generative Reasoning Re-ranker

Block-diffusion decoder for faster generative reasoning re-rankers in recommendation systems, parallelizing token generation to reduce inference latency.

Ax Dang Quang Thien Tran, Quang V. Dang, Vinamra Tyagi, Sai Soorya Rao Veeravalli, Trang Nguyen, Ryan A. Rossi, Franck Dernoncourt, Nedim Lipka, Koustava Goswami, Samyadeep Basu 24d ago

MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering

Training-free attribution method for multimodal QA systems that maps model outputs to evidence using attention mechanisms for improved transparency in AI assistants.

Ax Tianyi Zhang, Mousumi Das, Abrar Anwar, Jesse Thomason, David Traum 24d ago

DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents

Q-learning framework for dynamically selecting dialogue policies in high-stakes persuasion scenarios with LLMs, addressing personalized strategy selection for resident evacuation.

Ax Yunhe Li, Hao Shi, Wenhao Liu, Mengzhe Ruan, Hanxu Hou, Zhongxiang Dai, Shuang Qiu, Linqi Song 24d ago

DemoPSD: Disagreement-Modulated Policy Self-Distillation

DemoPSD: disagreement-modulated policy self-distillation for LLMs reducing overfitting from privileged information while improving reasoning.

Ax Francesco D'Angelo, Oguz Kaan Yuksel, Swathi Shree Narashiman, Nicolas Flammarion 24d ago

Induction Heads Interpolate N-Grams

Study of induction heads in transformers, identifying attention circuits that implement soft context-matching estimators for in-context learning via smoothing mechanisms.