Liqiang Nie

TTOM: Test-Time Optimization and Memorization for Compositional Video Generation

Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation

Boost Post-Training Quantization via Null Space Optimization for Large Language Models

PCDVQ: Enhancing Vector Quantization for Large Language Models via Polar Coordinate Decoupling

SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting

Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse Attention

CSO: Refining Robotic Policies via Skill Distribution Alignment and Skill-Grained Optimization

Do All Individual Layers Help? An Empirical Study of Task-Interfering Layers in Vision-Language Models

Beyond Quantity: Distribution-Aware Labeling for Visual Grounding

CoT-RC: Chain-of-Thought Reflection and Correction for Image Generation without Extra Training

TANGO: Tokenized Analysis-by-synthesis for 3D Nuclei Segmentation Correction

Spatial Understanding from Videos: Structured Prompts Meet Simulation Data

SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION

Unified Transferability Metrics for Time Series Foundation Models

Embodied Crowd Counting

STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization

Fair Deepfake Detectors Can Generalize

Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression

CogVLA: Cognition-Aligned Vision-Language-Action Models via Instruction-Driven Routing & Sparsification

Enhancing GUI Agent with Uncertainty-Aware Self-Trained Evaluator

Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization

UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation

Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters

TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models

The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense

Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning

Meta Guidance: Incorporating Inductive Biases into Deep Time Series Imputers

Breakthrough Sensor-Limited Single View: Towards Implicit Temporal Dynamics for Time Series Domain Adaptation

R$^2$ec: Towards Large Recommender Models with Reasoning

Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin

3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds

On the Power of Federated Learning for Online Sparse Linear Regression with Decentralized Data

Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing

Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding