12 papers
LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory
Kun-Yang Yu, Yingzhe Li, Hongyu Xu +8
Vision-Language Navigation (VLN) requires an embodied agent to follow natural-language instructions in unseen environments. Recent progress has been largely driven by Multimodal La…
Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models
Zhaoyi Li, Deyang Kong, Yuan Wei +13
On-policy distillation (OPD) transfers teacher capabilities by supervising trajectories sampled from the student's own policy, yet its generalization behavior remains poorly unders…
Self-Evolving Neuro-Symbolic Skills for Tool-Augmented Spatial Reasoning
Shi-Yu Tian, Zhuo-Xia Wang, Xuan-Yi Zhu +6
Large vision-language models have achieved strong performance in multimodal reasoning, but they remain unreliable on fine-grained spatial tasks that demand both precise spatial per…
On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective
Zhi Zhou, Ming Yang, Shi-Yu Tian +3
Test-time adaptation (TTA) aims to adapt models to maintain reliable performance on non-stationary test streams without requiring labeled data. Despite its empirical success, the l…
Towards Effective Experiential Learning: Dual Guidance for Utilization and Internalization
Fei Bai, Zhipeng Chen, Chuan Hao +6
Recently, reinforcement learning~(RL) has become an important approach for improving the capabilities of large language models~(LLMs). In particular, reinforcement learning from ve…
Thinking with Tables: Enhancing Multi-Modal Tabular Understanding via Neuro-Symbolic Reasoning
Kun-Yang Yu, Zhi Zhou, Shi-Yu Tian +6
Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities across modalities such as images and text. However, tabular data, despite being a criti…
SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Models
Pengfei Cao, Mingxuan Yang, Yubo Chen +4
Understanding why real-world events occur is important for both natural language processing and practical decision-making, yet direct-cause inference remains underexplored in evide…
NeSy-Route: A Neuro-Symbolic Benchmark for Constrained Route Planning in Remote Sensing
Ming Yang, Zhi Zhou, Shi-Yu Tian +3
Remote sensing underpins crucial applications such as disaster relief and ecological field surveys, where systems must understand complex scenes and constraints and make reliable d…
TabularMath: Understanding Math Reasoning over Tables with Large Language Models
Shi-Yu Tian, Zhi Zhou, Wei Dong +5
Mathematical reasoning has long been a key benchmark for evaluating large language models. Although substantial progress has been made on math word problems, the need for reasoning…
BMIP: Bi-directional Modality Interaction Prompt Learning for VLM
Song-Lin Lv, Yu-Yang Chen, Zhi Zhou +2
Vision-language models (VLMs) have exhibited remarkable generalization capabilities, and prompt learning for VLMs has attracted great attention for the ability to adapt pre-trained…
VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning
Shi-Yu Tian, Zhi Zhou, Kun-Yang Yu +4
Large language models (LLMs) have demonstrated impressive performance on reasoning tasks, including mathematical reasoning. However, the current evaluation mostly focuses on carefu…
DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection
Zhi Zhou, Ming Yang, Jiang-Xin Shi +2
Vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot capabilities for various downstream tasks. Their performance can be further enhanced through few…