University of Waterloo

university

Verified

https://uwaterloo.ca/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

yuntian-deng submitted a paper 11 days ago

Compile by Training: Turning Natural-Language Specifications into Local Neural Functions

yuntian-deng submitted a paper 13 days ago

Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs

yuntian-deng submitted a paper about 2 months ago

Interactive Training 2: Auditable Control Plane for Live Model Training

View all activity

Papers

Compile by Training: Turning Natural-Language Specifications into Local Neural Functions

Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs

View all Papers

submitted a paper to Daily Papers 11 days ago

Compile by Training: Turning Natural-Language Specifications into Local Neural Functions

Paper • 2609.04199 • Published 12 days ago • 383

submitted a paper to Daily Papers 13 days ago

Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs

Paper • 2609.00621 • Published 14 days ago • 9

submitted a paper to Daily Papers about 2 months ago

Interactive Training 2: Auditable Control Plane for Live Model Training

Paper • 2607.18314 • Published Jul 17 • 21

authored 2 papers 2 months ago

SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding

Paper • 2603.16124 • Published Mar 17 • 3

Towards Retrieving Interaction Spaces for Agentic Search

Paper • 2606.06880 • Published Jun 5 • 5

authored 2 papers 2 months ago

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Paper • 2606.15007 • Published Jun 12 • 20

Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion

Paper • 2606.14885 • Published Jun 12 • 13

submitted a paper to Daily Papers 2 months ago

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

Paper • 2607.02512 • Published Jul 2 • 310

authored a paper 3 months ago

Measuring Epistemic Resilience of LLMs Under Misleading Medical Context

Paper • 2606.12291 • Published Jun 10 • 60

authored a paper 3 months ago

Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution

Paper • 2606.06492 • Published Jun 4 • 96

submitted a paper to Daily Papers 3 months ago

Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution

Paper • 2606.06492 • Published Jun 4 • 96

authored 3 papers 3 months ago

RewardHarness: Self-Evolving Agentic Post-Training

Paper • 2605.08703 • Published May 9 • 11

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published Jun 1 • 143

AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?

Paper • 2606.05080 • Published Jun 3 • 32

submitted a paper to Daily Papers 4 months ago

Diversed Model Discovery via Structured Table Discovery

Paper • 2605.22766 • Published May 21 • 7

authored 4 papers 4 months ago

Watch Before You Answer: Learning from Visually Grounded Post-Training

Paper • 2604.05117 • Published Apr 6 • 36

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 264

Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Paper • 2604.12374 • Published Apr 14 • 39

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published May 3 • 127

submitted a paper to Daily Papers 5 months ago

FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios

Paper • 2604.07413 • Published Apr 8 • 99