Junchi Yan

Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization

Native Adaptive Solution Expansion for Diffusion-based Combinatorial Optimization

MMPD: Diverse Time Series Forecasting via Multi-Mode Patch Diffusion Loss

DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Driving

Achieving low-bit Muon through subspace preservation and grid quantization

SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning

MaskCO: Masked Generation Drives Effective Representation Learning and Exploiting for Combinatorial Optimization

When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms

Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention

GeoBench: Rethinking Multimodal Geometric Problem-Solving via Hierarchical Evaluation

Interleave-VLA: Enhancing Robot Manipulation with Image-Text Interleaved Instructions

One-Step Diffusion Solver for Non-binary Integer Linear Programming

MLOT: Generalizing the Bipartite Structure to a Multi-Layered Framework for Optimal Transport

KO: Kinetics-inspired Neural Optimizer with PDE Simulation Approaches

Group Verification-based Policy Optimization for Interactive Coding Agents

TrajTok: What makes for a good trajectory tokenizer in behavior generation?

Invariant Predict-and-Combinatorial Optimization under Distribution Shifts

Design Linear Constrained Neural Layers with Implicit Convex Optimization

LoWR: LoRA Weight Rescaling for Effective Rank Utilization beyond Reduction

FineRMOE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach

ConRep4CO: Contrastive Representation Learning of Combinatorial Optimization Instances across Types

Structure-Aware Antibody Humanization via a Novel Black-box Optimization Algorithm

Dual-Branch Center-Surrounding Contrast: Rethinking Contrastive Learning for 3D Point Clouds

Revisiting Standard-Definition Map Based Motion Prediction in the Era of End-to-End Autonomous Driving

Exploring the Boundary of Diffusion-based Methods for Solving Constrained Optimization

Unintended Harmful Knowledge Elicitation Issue in Large Reasoning Models and a RL Solution

Yet Another Scaling Axis with Some Free Lunch: Enlarging Token-indexed Parameters

Understanding the Task and Data Misconceptions in Online Map Based Motion Prediction for Autonomous Driving and a Boundary-Free Baseline

IO-Adam: Rethinking Memory-Efficient Adaptive Optimizers from Gradient Computation

Neural-Guided Enumerative SAT Framework for Cryptographic Key Recovery

Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space

Towards a Collaborative Memory for Agentic Workflow: Breaking the Prefix Barrier with Segment-Level KV Cache Sharing

Many Can Beat One: MoE-Linear Attention for Full MLP Image Generation

Edit-then-Consolidate for Reliable Knowledge Editing

Let's Explore Step by Step: Generating Provable Formal Statements with Deductive Exploration

How Does Local Landscape Geometry Evolve in Language Model Pre-Training?

Progressive Vision-Language Alignment via LLM-based Embedder

ReGen4AD: Retrieval Based Online Video Generation for Reactive Autonomous Driving Simulation

FlashPlanner: Accelerating Diffusion-based Planner for Autonomous Driving via Globally Consistent Velocity Field and Redundancy Reduction

PointARSim: Point-cloud–enhanced Generative Auto-Regressive Simulation for Closed-loop End-to-end Autonomous Driving Evaluation

One Direction to Rule Them All: Toward Generalizable Solving Strategies Across Combinatorial Optimization Problems

M$^2$GenCO: Multi-task Meta Learning for Generative Combinatorial Optimization

ParetoRouter: VLSI Global Routing with Multi-Objective Optimization

KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches

PRICIN: Principle-Centered Inorganic Retrosynthesis

Finding the Broad Gini in the Bottle: Optimizing Equity, Efficiency, and Resilience in Grid Restoration

Rethinking ab initio Neural Wave Function: GNNs at Electron Level

CORectifier: Hierarchical Trajectory Rectifications Boost Reinforcement Learning for Combinatorial Optimization

Primary-Dual Diffusion Solver for Quadratic Programming Problems

$S^3$-Bench: A Comprehensive Study of Multimodal LLMs for Scientific Discovery with Benchmarking

Train on Pins and Test on Obstacles for Rectilinear Steiner Minimum Tree

Generation as Search Operator for Test-Time Scaling of Diffusion-based Combinatorial Optimization

Repurposing AlphaFold3-like Protein Folding Models for Antibody Sequence and Structure Co-design

Rethinking and Improving Autoformalization: Towards a Faithful Metric and a Dependency Retrieval-based Approach

Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training

DSBRouter: End-to-end Global Routing via Diffusion Schr\"{o}dinger Bridge

Pedestrian Motion Reconstruction: A Large-scale Benchmark via Mixed Reality Rendering with Multiple Perspectives and Modalities

GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training

StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization

NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective

Fractional Langevin Dynamics for Combinatorial Optimization via Polynomial-Time Escape

HShare: Fast LLM Decoding by Hierarchical Key-Value Sharing

DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving

Learning Initial Basis Selection for Linear Programming via Duality-Inspired Tripartite Graph Representation and Comprehensive Supervision

The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training

QuaDiM: A Conditional Diffusion Model For Quantum State Property Estimation

PhysPDE: Rethinking PDE Discovery and a Physical Hypothesis Selection Benchmark

Beyond Circuit Connections: A Non-Message Passing Graph Transformer Approach for Quantum Error Mitigation

VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models

Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)

CORE: Collaborative Optimization with Reinforcement Learning and Evolutionary Algorithm for Floorplanning

SINGER: Stochastic Network Graph Evolving Operator for High Dimensional PDEs

On Designing General and Expressive Quantum Graph Neural Networks with Applications to MILP Instance Representation

BTBS-LNS: Binarized-Tightening, Branch and Search on Learning LNS Policies for MIP

On the Role of Label Noise in the Feature Learning Process

UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP

Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search

Rethinking Classifier Re-Training in Long-Tailed Recognition: Label Over-Smooth Can Balance

DocGenome: A Large Benchmark for Multi-Modal Language Models in Real-World Academic Document Understanding

Position-Query-Based Autoencoders for View Decoupled Cross Point Cloud Reconstruction and a Self-Supervised Learning Framework

Learning Structured Universe Graph with Outlier OOD Detection for Partial Matching

COExpander: Adaptive Solution Expansion for Combinatorial Optimization

QuanONet: Quantum Neural Operator with Application to Differential Equation

QEM-Bench: Benchmarking Learning-based Quantum Error Mitigation and QEMFormer as a Multi-ranged Context Learning Baseline

Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning

SelKD: Selective Knowledge Distillation via Optimal Transport Perspective

Regularizing Energy among Training Samples for Out-of-Distribution Generalization

COT: Consistent Optimal Transport with Applications to Visual Matching and Travelling Salesman Problems

Optimal Flow Transport and its Entropic Regularization: a GPU-friendly Matrix Iterative Algorithm for Flow Balance Satisfaction

CR2PQ: Continuous Relative Rotary Positional Query for Dense Visual Representation Learning

Bootstrapping Hierarchical Autoregressive Formal Reasoner with Chain-of-Proxy-Autoformalization

Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models

Your Consistency Model is Secretly a More Powerful Supervised Learning Paradigm for Learning Tasks with Complex Labels

Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous Driving

BiQAP: Neural Bi-level Optimization-based Framework for Solving Quadratic Assignment Problems

HEAP: Hyper Extended A-PDHG Operator for Constrained High-dim PDEs

The Role of Label Noise in the Feature Learning Process

Derail Yourself: Multi-turn LLM Jailbreak Attack through self-discovered clues

ESDMotion: End-to-end Motion Prediction Only with SD Maps

DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient Self-Driving

Rethinking Fairness Representation in Multi-Task Learning: a Performance-Informed Variance Reduction Approach

Learning General Representations Across Graph Combinatorial Optimization Problems

Toward Learning Generalized Cross-Problem Solving Strategies for Combinatorial Optimization

Inv-PnCO: Invariant Predict-and-Combinatorial Optimization under Distribution Shifts

MLOT: Extending the Bipartite Structure towards Multi-Layered Structure for Optimal Transport

Towards LLM4Floorplan: Agents Can Do What Engineers Do in Chip Design

TerDiT: Ternary Diffusion Models with Transformers

Towards General Certified Robustness of Combinatorial Optimization Solvers

ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving

From Graph Embedding to LKH: Bridging Learning and Heuristics for a Streamlined General TSP Solver

Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives