Jiang Bian

Causal Time Series Generation via Diffusion Models

PixelCraft: A Multi-Agent system for High-Fidelity Visual Reasoning on Structured Images

villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

Rethinking Reward Models for Multi-Domain Test-Time Scaling

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs

Continuous Time Series Generation with Irregular Observations

Co-Evolving Latent Action World Models

In-Context Compositional Q-Learning for Offline Reinforcement Learning

Can Vision–Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset Perspective.

From End-to-End to Step-by-Step: learning Composable Navigation Primitives for Vision-Language Navigation

Data-Efficient Training by Evolved Sampling

Reinforcement Learning with Inverse Rewards for World Model Post-training

CAD-Tokenizer: Towards Text-Based CAD Prototyping via Modality-Specific Tokenization

Playing with Transformer at 30+ FPS via Next-Frame Diffusion

Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

Fast Autoregressive Video Generation with Diagonal Decoding

Routing Channel-Patch Dependencies in Time Series Forecasting with Graph Spectral Decomposition

Sample-efficient LLM Optimization with Reset Replay

OATS: Online Data Augmentation for Time Series Foundation Models

Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains

Battery-Sim-Agent: Leveraging LLM-Agent for Inverse Battery Parameter Estimation

Less Is More: Generating Time Series with LLaMA-Style Autoregression in Simple Factorized Latent Spaces

LatentBit: Discrete Visual Tokenization with Preserved Continuous Structure

R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science

MIRA: Medical Time Series Foundation Model for Real-World Health Data

CADMorph: Geometry‑Driven Parametric CAD Editing via a Plan–Generate–Verify Loop

Functional Complexity-adaptive Temporal Tensor Decomposition

Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators

MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model

From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning

Unveiling Markov heads in Pretrained Language Models for Offline Reinforcement Learning

NaDRO: Leveraging Dual-Reward Strategies for LLMs Training on Noisy Data

Dyn-O: Building Structured World Models with Object-Centric Representations

BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling

What Do Latent Action Models Actually Learn?

Generating Full-field Evolution of Physical Dynamics from Irregular Sparse Observations

Policy Filtration for RLHF to Mitigate Noise in Reward Models

DPO Meets PPO: Reinforced Token Optimization for RLHF

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence

Data-Efficient Training by Evolved Sampling

Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models

Efficient Discovery of Pareto Front for Multi-Objective Reinforcement Learning

CAD-Editor: Text-based CAD Editing through Adapting Large Language Models with Synthetic Data

RD2Bench: Toward Data-Centric Automatic R&D

BRIDGE: Bootstrapping Text to Guide Time-Series Generation via Multi-Agent Iterative Optimisation and Diffusion Modelling

From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning

FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models

TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting

CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing

UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing

Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning

Policy Filtration in RLHF to Fine-Tune LLM for Code Generation

IGOR: Image-GOal Representations are the Atomic Building Blocks for Next-Level Generalization in Embodied AI

ANALOGXPERT: AUTOMATING ANALOG TOPOLOGY SYNTHESIS BY INCORPORATING CIRCUIT DESIGN EXPERTISE INTO LARGE LANGUAGE MODELS

GETMusic: Generating Music Tracks with a Unified Representation and Diffusion Framework

HeurAgenix: A Multi-Agent LLM-Based Paradigm for Adaptive Heuristic Evolution and Selection in Combinatorial Optimization

Semantic-Aware Diffusion Model for Sequential Recommendation