activity
20242026
collaborators

8 papers

cs.CR2026

TeleGapper: On the (un)reliability of Privacy Policies in Telegram Mini apps

Luca Ferrari, Mariano Ceccato, Luca Verderame

Telegram Mini Apps are Web applications embedded within the Telegram client, forming an ecosystem of third-party services within one of the world's most widely used messaging platf…

cs.CV2026

APE: Agentic Prompt Enhancer for Image Generation and Editing

Zijian Huang, Jay Zhangjie Wu, Zian Wang +5

Natural language has become a powerful interface for image generation and editing, yet text-guided visual systems remain highly sensitive to prompt formulation. Semantically simila…

cs.LG2026

VSPO: Vector-Steered Policy Optimization for Behavioral Control

Xuechen Zhang, Zijian Huang, Kai Yang +3

Modern language models often need to optimize a primary accuracy objective while also accommodating secondary behavioral preferences, such as verbosity, agreeableness, or the level…

cs.CR2025

Evil Vizier: Vulnerabilities of LLM-Integrated XR Systems

Yicheng Zhang, Zijian Huang, Sophie Chen +3

Extended reality (XR) applications increasingly integrate Large Language Models (LLMs) to enhance user experience, scene understanding, and even generate executable XR content, and…

cs.LG2025

BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning

Xuechen Zhang, Zijian Huang, Yingcong Li +3

Small language models (SLMs) struggle to learn complex reasoning behaviors, especially when high-quality traces are scarce or difficult to learn from. The standard training approac…

cs.LG2025

Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement

Xuechen Zhang, Zijian Huang, Chenshun Ni +3

Recent research enhances language model reasoning by scaling test-time compute via longer chain-of-thought traces. This often improves accuracy but also introduces redundancy and h…