Ax Baichuan Mo, Hanyong Xu, Ruoyun Ma, Jung-Hoon Cho, Dingyi Zhuang, Xiaotong Guo, Jinhua Zhao 3/12/2026

Large Language Models for Travel Behavior Prediction

Application of LLMs to travel behavior prediction through natural language reasoning, comparing frameworks for transportation demand modeling.

Ax Prince Kumar, Rudra Murthy, Riyaz Bhat, Danish Contractor 3/12/2026

Training with Pseudo-Code for Instruction Following

Improves instruction following in LLMs by training with pseudo-code instead of natural language, particularly for compositional tasks.

Ax Calvin Luo, Zilai Zeng, Mingxi Jia, Yilun Du, Chen Sun 3/12/2026

Self-Improving Loops for Visual Robotic Planning

Self-improving visual robotic planning agents using video generative models, addressing generalization to unseen tasks through self-supervised learning loops.

Ax Zhuolin Xu, Chenglin Li, Qiushi Li, Shin Hwei Tan 3/12/2026

What Makes Code Generation Ethically Sourced?

Survey of ethical issues in code generation models, covering licensing, privacy, fairness, and environmental impact of AI-assisted software development.

Ax Kiril Bangachev, Guy Bresler, Iliyas Noman, Yury Polyanskiy 3/12/2026

Global Minimizers of Sigmoid Contrastive Loss

Theoretical analysis of sigmoid contrastive loss in SigLIP models explains temperature and bias synchronization for representation alignment in pretraining.

Ax Jack Hong, Chenxiao Zhao, ChengLin Zhu, Weiheng Lu, Guohai Xu, Xing Yu 3/12/2026

DeepEyesV2: Toward Agentic Multimodal Model

DeepEyesV2 agentic multimodal model integrates text, images, code execution, and web search through reinforcement learning for structured reasoning and tool invocation.

Ax Naman Agarwal, Siddhartha R. Dalal, Vishal Misra 3/12/2026

Geometric Scaling of Bayesian Inference in LLMs

Investigation of geometric scaling properties in Bayesian inference across production-grade language models including Llama, Mistral, and Pythia families.

Ax Roy Xie, Deepak Gopinath, David Qiu, Dong Lin, Haitian Sun, Saloni Potdar, Bhuwan Dhingra 3/12/2026

Over-Searching in Search-Augmented Large Language Models

Analysis of over-searching problem in retrieval-augmented LLMs, where models invoke search unnecessarily, causing inefficiency and hallucinations from irrelevant context.

Ax Chuanrui Hu, Tong Li, Xingze Gao, Hongda Chen, Yi Bai, Dannong Xu, Tianwei Lin, Xiaohong Li, Yunyun Han, Jian Pei, Yafeng Deng 3/12/2026

Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues

Benchmark for evaluating long-term conversational memory in multi-party LLM applications with realistic interaction patterns across groups and channels.