Skip to content

Author

Ai-Dong Zhang

We have 7 of 32 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Nov 2026

Label-Free Localization and Test-Time Suppression of CLIP's Typographic Circuits

A mechanistic intervention that reweighs attention away from the patch tokens in the identified lexical heads at test-time is performed and a test-time adaptive attention head routing is proposed to further reduce the impact on performance at matched robustness, pushing beyond the Pareto frontier of current robustness-...

Bo-Han Liu, Wenqian Ye, Guang-Zhi Xiong et al. · 0 citations
Preprint Sep 2026

Monitorable Chart Reasoning Agents via Verifiable Process Rewards

Chart reasoning agents are increasingly used to extract actionable insights in critical domains, achieving state-of-the-art performance on multiple benchmarks. Yet, high benchmark accuracy alone is insufficient for deployment, where stakeholders must be able to audit and verify how a model reaches its answer. Existing...

Sanchit Sinha, Oana Frunza, Kashif Rasul et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Capturing In-Context Learning Dynamics with Task Operators

In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requires processing the full set of examples, resulting in inefficient deployments, and how ICL works mechanistically is not fully understood. Prior work compresses ICL into fi...

Guang-Zhi Xiong, Zheng-Hao He, Bo-Han Liu et al. · 0 citations

MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories

This work introduces MemLife, a multimodal memory system that constructs entity-grounded, first-person text episodes and retrieves them via a time-indexed agentic reader and proposes MemOpt, a reinforcement learning framework that optimizes the memory writer to produce faithful, informative, and retrievable memories.

Guang-Zhi Xiong, Xin-Yuan Zhang, Xiao Yang et al. · 0 citations

Reliable Parallel Decoding in Masked Diffusion Language Models

Masked diffusion language models (MDLMs) can generate text efficiently by predicting multiple masked tokens in parallel, but predictions from the same forward pass are not necessarily reliable when committed together. We study when parallel commitment is reliable. Our diagnostics show that confidence alone does not det...

Zheng-Hao He, Bo-Han Liu, Guang-Zhi Xiong et al. · 0 citations

Rethinking Reasoning Paths as Phase-Structured Trajectories

This work proposes to view reasoning paths as phase-structured trajectories within fixed questions as PAIR, short for Phase-Aligned Intra-question Reasoning, and improves within-question trajectory ranking and Best-of-N trajectory selection across models and benchmarks.

Zheng-Hao He, Guang-Zhi Xiong, Sanchit Sinha et al. · 0 citations
#artificial intelligence Preprint Jan 2026

Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models

It is suggested that CoT prompting activates specific latent features to trigger reasoning, and that targeted intervention on these features offers an alternative pathway to elicit efficient reasoning behavior without explicit CoT prompting.

Zhenghao He, Guangzhi Xiong, Bohan Liu et al. · 6 citations · ⚡1

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.