Zhang

This paper presents GRAIL, a digital generation pipeline that synthesizes human-object interactions for humanoid robots.

This paper proposes a new framework called STRIDE for training data attribution in Large Language Models.

The paper demonstrates that audio-language models often ignore conflicting audio evidence in favor of text, and proposes a training-free decoding rule, GACL, that significantly improves faithfulness by correcting this arbitration bias.

This paper proposes a preconditioning layer for stable weight conditioning in LLM training.

This paper proposes NF-CoT, a latent reasoning framework that preserves the advantages of chain-of-thought in large language models.

TempoVLA is a novel Vision-Language-Action model that enables controllable execution speed for robot manipulation by explicitly conditioning the policy on the desired speed.

This paper introduces Repeated Policy Regret (RP-Regret), a novel game-theoretic metric for analyzing regret in repeated games with adaptive opponents, and proposes algorithms to minimize it.

MLEvolve is a novel self-evolving multi-agent framework that enables LLM agents to discover and optimize machine learning algorithms for complex, long-horizon tasks.

The paper proposes Cross-Layer Sparse Attention (CLSA) to significantly improve the efficiency and accuracy of long-context LLMs by jointly optimizing KV-cache sharing and the routing index across decoder layers.

The paper introduces PAR3D, a unified part-aware 3D-MLLM framework, to enhance 3D scene understanding by enabling models to reason about and ground both whole objects and their fine-grained parts.

This paper introduces MedReCo and MedReCo-VLM, a framework that enables entity-aware cross-image reasoning for medical imaging, allowing AI to compare current scans with prior studies and analogous cases based on structured clinical reports.

The paper proposes OneReason, a framework that enhances the reasoning capability of generative recommendation models by focusing on improving item perception and structuring user behavior into coherent latent interests.

This paper introduces Ghostwriter, an attack framework demonstrating that LLMs are highly vulnerable to adopting misleading viewpoints when provided with fabricated, yet credible-looking, evidence.

The paper introduces RedEdit, an agentic red-teaming framework that demonstrates that malicious images can be easily edited to bypass safety classifiers while retaining their harmful semantics.

The paper introduces a novel Clean-Referenced Feature-Vocoder Attack, a black-box adversarial attack that perturbs high-level SSL feature representations instead of raw audio waveforms, achieving superior transferability and robustness against modern ASR defenses.

This paper introduces CORE-Bench, a comprehensive benchmark for code retrieval in agentic coding.

This paper proposes CompRank, a token-efficient reranking framework for large language models that reduces redundant computation and achieves strong reranking performance.

This paper presents a comprehensive survey on reconfigurable antennas for next-generation mobile networks, focusing on their potential and applications.

This paper introduces Agents-K1, an end-to-end knowledge orchestration pipeline that converts raw documents into agent-native scientific knowledge graphs.

This paper presents EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery.