Yu Zhang

The paper introduces VeriTrip, a new verifiable benchmark that evaluates travel planning agents' ability to perform evidence-grounded reasoning over complex, unstructured, and multimodal web data, revealing a critical retrieval-reasoning trade-off.

The paper introduces SNARE, a novel adaptive testing pipeline that systematically measures overeager behavior in coding agents, finding that the agent framework accounts for the majority of the variation in security risk.

The paper introduces MIRAGE, a novel pipeline that generates context-aware prompt injection attacks by injecting malicious text into user-generated content regions of mobile screenshots, successfully demonstrating the vulnerability of current GUI agents.

SPARD is a defense framework that uses Safety-Projected Alternating optimization and Relevance-Diversity data selection to mitigate harmful fine-tuning attacks that undermine LLM safety.

The paper introduces VeriTrip, a new verifiable benchmark that evaluates travel planning agents' ability to perform evidence-grounded reasoning over complex, unstructured, and multimodal web data, revealing a critical retrieval-reasoning trade-off.

The paper introduces SNARE, a novel adaptive testing pipeline that systematically measures overeager behavior in coding agents, finding that the agent framework accounts for the majority of the variation in security risk.

The paper introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion LLMs.

The paper introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion LLMs.

The paper analyzes observation masking in long-horizon search agents, finding that its effectiveness depends on a complex interaction between the model's capacity and the retriever's strength, exhibiting an inverted-U shaped gain.

The paper analyzes observation masking in long-horizon search agents, finding that its effectiveness depends on a complex interaction between the model's capacity and the retriever's strength, exhibiting an inverted-U shaped gain.

The paper proposes a sequence-alignment framework using Soft Dynamic Time Warping to evaluate audio-driven talking-head generation, demonstrating that this approach provides more robust and fair comparisons than traditional frame-wise metrics.

The paper proposes a sequence-alignment framework using Soft Dynamic Time Warping to evaluate audio-driven talking-head generation, demonstrating that this approach provides more robust and fair comparisons than traditional frame-wise metrics.

The paper introduces SGAP-PPIS, a structure-guided adaptive propagation model that improves protein-protein interaction site prediction by allowing information diffusion to adapt based on a residue's local geometric environment.

The paper introduces SGAP-PPIS, a structure-guided adaptive propagation model that improves protein-protein interaction site prediction by allowing information diffusion to adapt based on a residue's local geometric environment.

Integrates FOA into Omni LLMs for spatial audio understanding

This paper provides a comprehensive review of audio editing in the era of foundation models, including a unified taxonomy of existing editing tasks and major foundation-model paradigms.

This paper proposes X$^3$-OPD, a framework for transferring reasoning capabilities from text-based models to audio-language models using on-policy distillation.

This paper surveys recent advances in brain-to-language decoding, including text generation, personalized speech, and facial animation.

This paper proposes WQ-GADMM, a method for distributed optimization in edge networks that reduces communication costs and maintains test accuracy.

VulnSAGE is a system that uses large language models to adjudicate Static Application Security Testing (SAST) reports by connecting model reasoning to program structure.