Bingzheng Wei

Bingzheng's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 3 hours ago

Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation

Paper • 2602.16990 • Published 9 days ago • 11

upvoted 4 papers about 4 hours ago

DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference

Paper • 2602.21548 • Published 3 days ago • 24

veScale-FSDP: Flexible and High-Performance FSDP at Scale

Paper • 2602.22437 • Published 3 days ago • 5

Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization

Paper • 2602.22675 • Published 2 days ago • 17

MediX-R1: Open Ended Medical Reinforcement Learning

Paper • 2602.23363 • Published 1 day ago • 16

upvoted a paper about 10 hours ago

MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios

Paper • 2602.22638 • Published 2 days ago • 94

upvoted 9 papers 1 day ago

From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models

Paper • 2602.22859 • Published 2 days ago • 143

Discovering Multiagent Learning Algorithms with Large Language Models

Paper • 2602.16928 • Published 10 days ago • 16

Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization

Paper • 2602.23008 • Published 2 days ago • 27

Imagination Helps Visual Reasoning, But Not Yet in Latent Space

Paper • 2602.22766 • Published 2 days ago • 34

OmniGAIA: Towards Native Omni-Modal AI Agents

Paper • 2602.22897 • Published 2 days ago • 47

The Trinity of Consistency as a Defining Principle for General World Models

Paper • 2602.23152 • Published 2 days ago • 182

SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model

Paper • 2602.21818 • Published 3 days ago • 46

MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models

Paper • 2602.17602 • Published 9 days ago • 52

HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation

Paper • 2602.18283 • Published 8 days ago • 53

upvoted 5 papers 2 days ago

QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models

Paper • 2602.20309 • Published 5 days ago • 15

LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces

Paper • 2602.14337 • Published 13 days ago • 12

DREAM: Deep Research Evaluation with Agentic Metrics

Paper • 2602.18940 • Published 7 days ago • 14

Multi-Vector Index Compression in Any Modality

Paper • 2602.21202 • Published 4 days ago • 20

World Guidance: World Modeling in Condition Space for Action Generation

Paper • 2602.22010 • Published 3 days ago • 8