Zhi Wei Tan

zwtan-cs's activity

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

upvoted 4 papers about 18 hours ago

Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents

Paper • 2610.01892 • Published 10 days ago • 30

SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving

Paper • 2609.34117 • Published 13 days ago • 23

Learning Functional Subspaces for Neural Network Compression

Paper • 2609.40127 • Published 11 days ago • 20

Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment

Paper • 2609.38972 • Published 11 days ago • 27

upvoted 3 papers 1 day ago

HLA-WM: Hybrid Linear Attention for Long-Horizon Video World Models

Paper • 2610.05739 • Published 6 days ago • 21

Towards Looped Models Done Right, Part II: Rethinking at Fixed Points

Paper • 2610.06833 • Published 6 days ago • 32

ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context

Paper • 2609.36684 • Published 12 days ago • 20

upvoted 2 papers 4 days ago

Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs

Paper • 2609.32259 • Published 12 days ago • 98

On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics

Paper • 2609.35259 • Published 13 days ago • 201

upvoted 2 papers 5 days ago

WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms

Paper • 2609.38121 • Published 12 days ago • 26

OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software

Paper • 2609.39903 • Published 11 days ago • 64

upvoted 2 papers 6 days ago

RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation

Paper • 2609.29028 • Published 17 days ago • 16

Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR

Paper • 2609.37868 • Published 12 days ago • 65

upvoted 2 papers 8 days ago

WorldAttention: An Efficient Attention Architecture for Interactive Video World Models

Paper • 2609.34606 • Published 13 days ago • 50

LongCat-DeepResearch Technical Report

Paper • 2609.36071 • Published 13 days ago • 72

upvoted 2 papers 9 days ago

In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion

Paper • 2609.32540 • Published 15 days ago • 35

How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining

Paper • 2609.35457 • Published 13 days ago • 68

upvoted a paper 11 days ago

Coding Agents for Generalized Task and Motion Planning Problems

Paper • 2609.30233 • Published 17 days ago • 28

upvoted a paper 12 days ago

PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing

Paper • 2609.23784 • Published 21 days ago • 16

upvoted a paper 13 days ago

Blaming Across the Aisle: Political Contrasting and Blame Attribution in the Danish Parliament

Paper • 2609.26346 • Published 19 days ago • 11