Xiang Li

This paper identifies and characterizes 'guidance injection,' a stealthy attack vector that embeds adversarial operational narratives into autonomous coding agents' bootstrap guidance, demonstrating high success rates and evasion capabilities.

LoSATok proposes a low-dimensional semantic-acoustic tokenizer that efficiently compresses high-dimensional audio features into a compact latent space, significantly improving the performance and efficiency of audio generation models.

LoSATok proposes a low-dimensional semantic-acoustic tokenizer that efficiently compresses high-dimensional audio features into a compact latent space, significantly improving the performance and efficiency of audio generation models.

The paper introduces MASA, a model-aware skill alignment framework that adaptively rewrites general and task-specific skills for LLM agents, achieving superior performance across diverse backbones and environments.

The paper introduces MASA, a model-aware skill alignment framework that adaptively rewrites general and task-specific skills for LLM agents, achieving superior performance across diverse backbones and environments.

The paper introduces Diversity-inducing Initialization (DivIn), a novel method that improves image diversity by re-weighting the initial noise selection based on the guidance potential, thereby mitigating mode collapse.

The eMoT framework enhances multi-step reasoning in LLMs by treating reasoning as an evolving memory, stabilizing performance through symbolic computation and structured refinement.

The paper introduces CASTER, a new human-centric task for evaluating User-Generated Content (UGC) resonance, and proposes MEDEA, an architecture that uses a Social Chain-of-Thought mechanism to simulate community reactions for quality assessment.

The paper introduces Diversity-inducing Initialization (DivIn), a novel method that improves image diversity by re-weighting the initial noise selection based on the guidance potential, thereby mitigating mode collapse.

The eMoT framework enhances multi-step reasoning in LLMs by treating reasoning as an evolving memory, stabilizing performance through symbolic computation and structured refinement.

The paper introduces CASTER, a new human-centric task for evaluating User-Generated Content (UGC) resonance, and proposes MEDEA, an architecture that uses a Social Chain-of-Thought mechanism to simulate community reactions for quality assessment.

The paper proposes a method called self-guidance to improve the reconstruction fidelity of neural speech codecs based on Vector-Quantized VAEs.

This paper introduces Chronos, a physics-informed framework for non-Markovian long-horizon manipulation, which elevates observation history to the latent state of the policy dynamics and achieves higher success rates and fewer parameters than Markovian VLA baselines in both simulated and real-world experiments.

This paper proposes RL-MACRO, a cybernetic closed-loop intelligence framework for autonomous robotic craniotomy, which includes a CNN-LSTM observer for temperature reconstruction, an offline Implicit Q-Learning policy, and a novel dual-head Actor for coordinating cutting parameters.

This paper investigates the transfer of strategic capabilities in large language models by proposing a lightweight behavioural embedding for game analysis.