The Hong Kong Polytechnic University

university

Verified

https://www.polyu.edu.hk/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

zhuhu00 authored a paper about 18 hours ago

GEM-Occ: From Visual Geometry Evidence to Embodied Semantic Occupancy Memory

zhuhu00 authored a paper about 18 hours ago

EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making

zhuhu00 authored a paper about 18 hours ago

UniScene: Unified Occupancy-centric Driving Scene Generation

View all activity

Papers

Org-Agent: Beyond Personal Assistants Towards Organizational Agents

SMAT: Simple and Efficient Merge-Aware Training

View all Papers

authored 3 papers about 18 hours ago

GEM-Occ: From Visual Geometry Evidence to Embodied Semantic Occupancy Memory

Paper • 2607.05543 • Published 4 days ago • 1

EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making

Paper • 2609.38334 • Published 8 days ago • 80

UniScene: Unified Occupancy-centric Driving Scene Generation

Paper • 2412.05435 • Published Dec 6, 2024

Awesome-GraphRAG

submitted a paper to Daily Papers 8 days ago

Org-Agent: Beyond Personal Assistants Towards Organizational Agents

Paper • 2609.34392 • Published 11 days ago • 6

submitted a paper to Daily Papers 9 days ago

When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections

Paper • 2609.32488 • Published 13 days ago • 26

submitted a paper to Daily Papers 10 days ago

SMAT: Simple and Efficient Merge-Aware Training

Paper • 2609.33437 • Published 12 days ago • 5

submitted a paper to Daily Papers 10 days ago

Routing Drift Alone Does Not Diagnose Failure in Merged MoE LLMs

Paper • 2609.32821 • Published 13 days ago • 5

authored a paper 25 days ago

A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM

Paper • 2609.07821 • Published Sep 7 • 16

vLAR

submitted a paper to Daily Papers 30 days ago

RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting

Paper • 2609.07414 • Published Sep 7 • 11

submitted a paper to Daily Papers about 2 months ago

Persistent Recursive Worlds Enable Autonomous Software Evolution

Paper • 2608.10450 • Published Aug 12 • 8

authored a paper 3 months ago

Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training

Paper • 2607.01763 • Published Jul 2 • 8

submitted 2 papers to Daily Papers 4 months ago

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

Paper • 2606.18322 • Published Jun 16 • 16

BadWorld: Adversarial Attacks on World Models

Paper • 2606.16519 • Published Jun 15 • 17

authored a paper 4 months ago

Beyond APIs: Probing the Limits of MLLMs in Physical Tool Use

Paper • 2606.10803 • Published Jun 9 • 3

submitted a paper to Daily Papers 4 months ago

Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation

Paper • 2605.26844 • Published May 26 • 24

authored a paper 5 months ago

BrainAnytime: Anatomy-Aware Cross-Modal Pretraining for Brain Image Analysis with Arbitrary Modality Availability

Paper • 2605.13059 • Published May 13

submitted a paper to Daily Papers 5 months ago

E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring

Paper • 2605.16882 • Published May 16 • 2

submitted a paper to Daily Papers 5 months ago

FeatCal: Feature Calibration for Post-Merging Models

Paper • 2605.13030 • Published May 13 • 7

submitted a paper to Daily Papers 5 months ago

Model Merging Scaling Laws in Large Language Models

Paper • 2509.24244 • Published May 11 • 44

submitted a paper to Daily Papers 6 months ago

ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning

Paper • 2604.19254 • Published Apr 21 • 32