Yu Wang

This paper introduces Chronos, a physics-informed framework for non-Markovian long-horizon manipulation, which elevates observation history to the latent state of the policy dynamics and achieves higher success rates and fewer parameters than Markovian VLA baselines in both simulated and real-world experiments.

This paper presents Festina, a profiling-guided, power-aware control plane for minimizing energy consumption in serverless large language model (LLM) serving.

The paper introduces WorldDirector, a framework for creating controllable video worlds with persistent dynamic object memory and exact visual identities.

The paper introduces MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal Language Models with an executable mechanism for mental visualization using SVG graphics.

This paper introduces ArchEval, a benchmark and platform for evaluating LLM agents on computer architecture design and optimization.

This paper introduces LingBot-Video, a video pretraining paradigm for embodied intelligence using a DiT-based approach, Mixture-of-Experts framework, and extensive robot-oriented data.

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.

Proposed MCF-Net framework fuses myocardial motion cues with foundation model representations for reliable segment-level MI localization in echocardiography.

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.

This paper proposes FinSAgent, an evidence-grounded multi-agent framework for financial question answering over SEC filings, which improves retrieval coverage and answer correctness through corpus-side conditioning.

This paper proposes a test-time scaling approach for Vision-Language Models in Unmanned Aerial Vehicle navigation, enabling self-correction and generation of more accurate and reliable flight plans.

The paper introduces DeCNIP, a method for identifying and neutralizing backdoors in large language models using representational analysis and neuron isolation pruning.

The paper proposes CARA, an interpretable framework for collision anticipation in autonomous driving using domain-grounded risk concepts, aligning them with video frames, and organizing them into evolving concept trajectories.

This paper introduces IR275K, a curated benchmark for multi-frame super-resolution in infrared remote sensing, and evaluates CGMamba, a lightweight state-space model, achieving state-of-the-art performance.

This paper rigorously proves that a Reinforcement Learning Hyper-heuristic (RLHH) optimizes the LeadingOnes benchmark function with optimal expected runtime using two random local search operators, outperforming the Generalised Random Gradient HH.

This paper proposes a method for learning a world model of piano sound using Joint Embedding Predictive Architectures (JEPA), treating music as an action-conditioned system.

Libra is a load balancing approach for long-context LLM training that groups packed sequences into fixed-size pools and reduces attention workload variance, improving end-to-end throughput and straggler-attention speedup.

The paper presents CHASE, an application-driven framework that explores physically feasible Cross-layer Heterogeneous System architectures for executing workloads with diverse requirements.

This paper organizes embodied data sources for multimodal foundation models into a pyramid, focusing on real-robot, UMI-style, egocentric and exocentric, simulation, and general vision-language data.

The paper introduces CoRenew, an open-source platform for simulating negotiations among stakeholders in multifamily residential redevelopment using LLM-based agents, with validations against survey responses and real-life negotiation data.