works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.AI2026

SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning

Mingyuan Wu, Jingcheng Yang, Shengyi Qian +11

The paper introduces SVR-R1, a reinforcement learning framework that lets a multimodal model generate an answer and then self‑verify it with a binary verdict, allowing a second‑cha…

cs.AI2026

Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning

Banghao Chi, Yining Xie, Mingyuan Wu +9

Spreadsheet systems (e.g., Microsoft Excel, Google Sheets) play a central role in modern data-centric workflows. As AI agents grow increasingly capable of automating complex tasks,…

cs.AI2026

TTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed Tokens

Jianpeng Cheng, Xian Wu, Jiangfan Zhang +10

Recent research has demonstrated that Universal Multimodal Embedding (UME) benefits significantly from Chain-of-Thought (CoT) reasoning. In this paradigm, a generative model produc…

cs.LG2026

Federated Nested Learning: Collaborative Training of Self-Referential Memories for Test-Time Adaptation

Hong Chen, Pengcheng Wu, Yuanguo Lin +4

We rethink Federated Learning (FL) from a nested learning perspective, framing the core challenge as how to collaboratively learn optimization rules, not just static models, to tac…

cs.AI2026

GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification

Iordanis Fostiropoulos, Muhammad Rafay Azhar, Abdalaziz Sawwan +8

We introduce GISTBench, a benchmark for evaluating Large Language Models' (LLMs) ability to understand users from their interaction histories in recommendation systems. Unlike trad…

cs.CL2025

RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization

Zhaoning Yu, Will Su, Leitian Tao +9

Reinforcement learning with human-annotated data has boosted chain-of-thought reasoning in large reasoning models, but these gains come at high costs in labeled data while falterin…