collaborators

6 papers

cs.CV2026

S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence

Yalun Dai, Hao Li, Shulin Tian +10

Real-world spatial intelligence requires reasoning over a continuous and evolving 3D world, yet existing VLMs and tool-augmented agents largely remain tied to static, stateless inf…

cs.LG2026

CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation

Ning Yang, Chengzhi Wang, Yibo Liu +2

Prefill-only KV compression freezes a token subset at the end of prefill and decodes from it without further eviction. The retention decision is therefore irreversible, yet existin…

cs.CL2026

LinearARD: Linear-Memory Attention Distillation for RoPE Restoration

Ning Yang, Hengyu Zhong, Wentao Wang +3

The extension of context windows in Large Language Models is typically facilitated by scaling positional encodings followed by lightweight Continual Pre-Training (CPT). While effec…

cs.CL2026

Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning

Dongxu Zhang, Yujun Wu, Yiding Sun +5

While Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs), ensuring reasoning reliability remains an open challenge. Contrary to the prevailing cascading failure…

cs.AI2026

Token-Importance Guided Direct Preference Optimization

Ning Yang, Hai Lin, Yibo Liu +3

Aligning Large Language Models (LLMs) with human preferences is crucial for safe and effective AI interactions. While popular methods like Direct Preference Optimization (DPO) have…

cs.CL2026

CrossCheck-Bench: Diagnosing Compositional Failures in Multimodal Conflict Resolution

Baoliang Tian, Yuxuan Si, Jilong Wang +13

Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largel…