Hao Chen

The paper introduces the Data-centric Reasoning Compiler (DCRC), a novel data-driven framework that enhances financial QA systems by compiling user queries and retrieved documents into verifiable, executable programs to prevent numerical hallucinations.

The paper introduces BilliardPhys-Bench, a new benchmark that demonstrates that current multimodal LLMs struggle with complex physical reasoning and predicting object dynamics in simulated environments.

COMPASS introduces a Cognitive MCTS-Guided Process Alignment framework to ensure robust safety for LLM search agents by identifying and supervising risky intermediate steps in multi-step reasoning.

The paper introduces Latent Reward Steering (LRS), an adaptive inference-time framework that implicitly improves the reasoning ability of LLMs by guiding the model's internal latent states based on a reward signal derived from final answer correctness.

This paper addresses the challenge of achieving optimal fairness and accuracy simultaneously in multi-class classification by proposing novel in-processing and post-processing algorithms that converge to the optimal Pareto frontier.

The paper proposes an Entropy Dynamics framework to analyze the stability and failure modes of centralized orchestration in Multi-Agent Systems, identifying a 'Reasoning Trap' where complex reasoning models fail due to context overload.

The paper introduces HomeFlow, a verifiable data flywheel that procedurally generates high-quality, multi-turn training data for smart home agents, achieving state-of-the-art performance on smart home tasks.

The paper proposes using Vision-Language Models (VLMs) as 'teachers' to guide Video Generation Models (VGMs) during test-time optimization, significantly improving video reasoning capabilities.

The paper proposes FLAME, a novel framework that detects AI-generated image forgeries by identifying intrinsic energy anomalies caused by the diffusion process, achieving state-of-the-art localization.

SeClaw is a new framework that synthesizes security tasks from structured risk specifications to evaluate autonomous LLM agents' behavior in stateful environments, focusing on the process of unsafe actions rather than just the final outcome.

The paper introduces OpenWebRL, an open framework that enables training visual web agents using online multi-turn Reinforcement Learning directly on live websites, achieving state-of-the-art performance on challenging web benchmarks.

The paper introduces SMH-Bench, a comprehensive benchmark built on a simulator to rigorously test LLM agents' ability to perform complex, environment-grounded reasoning and actions in realistic smart-home scenarios.

SeClaw is a new framework that uses specification-driven task synthesis to create comprehensive and controllable security benchmarks for evaluating the unsafe behaviors of autonomous LLM agents.

This paper studies how to scale robust robot policies by expanding physical domains in a recoverable way.

This paper investigates the use of spectral filtering for continuous subgraph matching over dynamic graphs and presents three key findings.

LISA is a novel LLM-based invariant testing framework for software functional bugs, achieving higher bug-detection rates and competitive code coverage than fuzzing and prior LLM-based test generation approaches.

OpenForgeRL is an open-source framework for training harness-based AI agents end-to-end in various environments using a lightweight proxy and Kubernetes orchestrator.

The authors propose a new solution for the content cold-start problem in industry-scale search and recommender systems, reducing bias, improving model prediction, and validating long-term impact.

Loom is a system for analyzing spatial transcriptomics data through detailed pseudo-temporal exploration, cross-sample comparisons, and investigation of spatiotemporal biological mechanisms.

The paper proposes SharpRec, a framework for LLM-based Cross-Domain Sequential Recommendation to address the bottlenecks of cross-domain knowledge conflict and performance saturation in multi-domain fusion.