Ao Wang

This paper introduces the concept of Budget-Aware Agents (BAGEN), showing that current LLM agents often fail to manage resources proactively, and proposes that incorporating early stop and interval estimation significantly improves efficiency.

This paper proposes a Signal Cost Proxy framework, drawing from signaling theory, to systematically evaluate the contextual appropriateness of empathy in AI interactions.

The paper introduces AMix-2, a novel protein-text foundation model that unifies protein understanding and sequence design by embedding both modalities in a shared token space, achieving state-of-the-art performance on comprehensive benchmarks.

The paper introduces PIGMENT, a physics-informed foundation model that enables reliable quantitative mapping of brain microstructure from extremely sparse or challenging diffusion MRI scans.

The paper introduces SURE, a unified framework designed to standardize and improve the comparability and reproducibility of evaluations for advanced speech understanding models.

PatchWorld introduces a gradient-free framework to create executable Python world models from offline trajectories, achieving high planning scores by inducing symbolic belief-state programs.

The paper introduces I-WebGenBench, a framework and benchmark that converts static scientific papers into executable, interactive web systems, allowing users to dynamically explore the paper's mechanisms.

The paper identifies and demonstrates a novel vulnerability, cross-app context poisoning, in the shared context architecture of ChatGPT Apps, allowing malicious apps to manipulate the LLM's behavior across different, benign co-resident apps.

This survey reviews how Large and Multi-modal Language Models (LLMs/MM-LLMs) are being applied to integrate diverse data sources for enhanced decision support in transportation systems management and operations.

SafeSteer proposes a localized on-policy distillation method that restricts safety alignment to specific safety tokens, thereby achieving strong safety performance with minimal degradation to general capabilities and significantly reducing data requirements.

The paper introduces MCP-Persona, a novel benchmark designed to evaluate LLM agents' performance on real-world, personalized applications using the Model Context Protocol (MCP), revealing that current state-of-the-art agents struggle with such personalized tool use.

The paper proposes GIM-World, a geometry-aware implicit memory framework that significantly improves long-horizon video world models by explicitly encoding 3D scene geometry into a compact memory state.

The paper argues that observed gains in multimodal agents using tools may be due to learning tool-calling patterns rather than genuine capability expansion, finding that tool access provides little consistent aggregate improvement.

SafeMCP is a server-side defense plugin that uses look-ahead reasoning to proactively filter and constrain tool acquisition for LLM agents, thereby mitigating catastrophic risks associated with expanding action spaces.

The paper introduces Deep Spurious Regression (DSR) to address spurious correlations in continuous prediction tasks, proposing a method that exploits attribute similarity in both feature and label spaces for robust generalization.

GJDNet proposes a joint disentanglement framework to enhance the robustness of Graph Neural Networks against adversarial attacks by simultaneously stabilizing node representations and decision boundaries across diverse graph connectivity types.

ResMerge proposes a residual-based spectral merging framework that improves the combination of multiple reinforcement learning (RL) expert models by stabilizing the aggregation process using a residual backbone.

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

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 addresses the challenging problem of multi-objective submodular maximization under a cardinality constraint while ensuring differential privacy, proposing novel algorithms with approximation guarantees.