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

Awesome-GraphRAG submitted a paper 12 days ago

Org-Agent: Beyond Personal Assistants Towards Organizational Agents

Stephen-SMJ submitted a paper 12 days ago

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

yanggangu submitted a paper 13 days ago

SMAT: Simple and Efficient Merge-Aware Training

View all activity

Papers

Org-Agent: Beyond Personal Assistants Towards Organizational Agents

SMAT: Simple and Efficient Merge-Aware Training

View all Papers

Awesome-GraphRAG

submitted a paper to Daily Papers 12 days ago

Org-Agent: Beyond Personal Assistants Towards Organizational Agents

Paper • 2609.34392 • Published 14 days ago • 7

submitted a paper to Daily Papers 12 days ago

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

Paper • 2609.32488 • Published 16 days ago • 27

submitted a paper to Daily Papers 13 days ago

SMAT: Simple and Efficient Merge-Aware Training

Paper • 2609.33437 • Published 15 days ago • 5

submitted a paper to Daily Papers 13 days ago

Routing Drift Alone Does Not Diagnose Failure in Merged MoE LLMs

Paper • 2609.32821 • Published 16 days ago • 5

authored a paper 29 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 about 1 month ago

RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting

Paper • 2609.07414 • Published Sep 7 • 11

submitted a paper to Daily Papers 2 months ago

Persistent Recursive Worlds Enable Autonomous Software Evolution

Paper • 2608.10450 • Published Aug 12 • 8

sslu

authored 3 papers 3 months ago

Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training

Paper • 2605.09608 • Published May 10 • 52

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

Paper • 2605.26844 • Published May 26 • 24

Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model Merging

Paper • 2605.29489 • Published May 28 • 4

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

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

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

submitted a paper to Daily Papers 6 months ago

On Semiotic-Grounded Interpretive Evaluation of Generative Art

Paper • 2604.08641 • Published Apr 9 • 4

submitted a paper to Daily Papers 7 months ago

Multiscale Switch for Semi-Supervised and Contrastive Learning in Medical Ultrasound Image Segmentation

Paper • 2603.18655 • Published Mar 19 • 2

submitted a paper to Daily Papers 7 months ago

CL4SE: A Context Learning Benchmark For Software Engineering Tasks

Paper • 2602.23047 • Published Feb 26 • 2