Qiang Xu

Video-As-Prompt: Unified Semantic Control for Video Generation

EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning

From Samples to Scenarios: A New Paradigm for Probabilistic Forecasting

Reasoning Scaffolding: Distilling the Flow of Thought from LLMs

Mathesis: Towards Formal Theorem Proving from Natural Languages

Fidel-TS: A High-Fidelity Benchmark for Multimodal Time Series Forecasting

Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier

Beyond Tokens: Enhancing RTL Quality Estimation via Structural Graph Learning

Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy

RL-Guard: Rescuing LLM Agents from Pitfalls

TRACE: Learning to Compute on Graphs

UniRTL: Unifying Code and Graph for Robust RTL Representation Learning

Alignment Unlocks Complementarity: A Framework for Multiview Circuit Representation Learning

Influence-Aware Forecasting: Breaking the Self-Stimulation Barrier in Time Series

FailureAtlas: Mapping the Failure Landscape of T2I Models via Active Exploration

Concept-SAE: Active Causal Probing of Visual Model Behavior

DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model

Functional Matching of Logic Subgraphs: Beyond Structural Isomorphism

Dependency Matters: Enhancing LLM Reasoning with Explicit Knowledge Grounding

DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale

HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging

Test Time Augmentations are Worth One Million Images for Out-of-Distribution Detection

DeepLayout: Learning Neural Representations of Circuit Placement Layout

Beyond Trend and Periodicity: Guide Time Series Forecasting with Textual Cues

MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes

DynamicRTL: RTL Representation Learning for Dynamic Circuit Behavior

GenBen:A Genarative Benchmark for LLM-Aided Design

DeepCircuitX: Repository-Level RTL Dataset for Code Understanding, Generation, and Multimodal Analysis