Chen Liu
26 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Archon, a unified, fully pretrained multimodal model that addresses the challenge of generating holistic digital humans by integrating seven modalities (including text, audio, motion, and visual content) into a single autoregressive framework.
The paper introduces Graph-Distance Contribution Reward (GDCR) and Step Advantage Policy Optimization (SAPO) to provide fine-grained, step-level credit assignment for agentic search by modeling world knowledge as a latent graph.
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 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.
The paper introduces and analyzes cross-session stored prompt injection, demonstrating that persistent system state transforms prompt injection from a temporary model-level threat into a long-lived, system-level vulnerability in agentic systems.
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.
Proposes a scalable LLM-based RTL optimization framework for long-context RTL designs.
This paper studies the computational complexity of the width parameter in Montanaro's polynomial representation of quantum circuits.
PAPERCLAW is a multi-agent system that autonomously curates a domain, generates ideas, and writes venue-compliant papers using large language models and a stoppable hypothesis map.
This paper introduces Active Task Driving Memory (ATMem), an actively maintained execution state for mobile GUI agents, and STR-GRPO, an online reinforcement learning method that uses ATMem selectively.
The paper introduces WorldDirector, a framework for creating controllable video worlds with persistent dynamic object memory and exact visual identities.
This paper proposes a dynamic image cropping framework and compound shrinking strategy to reduce computational overhead of CNNs on edge AI, achieving higher accuracy and lower computational cost.
The paper introduces LingBot-World 2.0, an advanced version of a language model with unbounded interaction horizon, rapid response time, diverse interactive elements, and agentic harness integration.
This paper addresses the obstacles of using Crossbar-based In-Memory Processing (IMP) accelerators for deep neural networks (DNNs) by reusing bit-shift units for multiplication, applying pruning methods, and adapting to non-ideality.
Introduces AlphaOracle, a human-workflow-inspired framework for deciphering undeciphered oracle bone script characters using a large digitized corpus, reducing analysis time and agreeing with expert interpretations.
The paper proposes TRAVEL, a framework for automated C-to-Rust translation using Monte Carlo Tree Search and reinforcement learning, improving accuracy and success rate.
This paper introduces GameLogicBench, a benchmark for evaluating the ability of coding agents to implement gameplay rules in game development.
The authors construct r-dimensional cubical sheaf complexes with positive constant rate, linear distance, and constant soundness for CSS codes.
This paper presents Isaac-Net, a GPU-batched 5G New Radio module that simulates thousands of environments in lockstep with Isaac Lab physics.
This paper introduces MemT-1.0, a new architecture of memory foundation models that internalize memory as part of model computation.