Patrice Bechard

patricebechard's activity

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

upvoted 2 papers 8 days ago

SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG

Paper • 2606.18381 • Published 14 days ago • 19

MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval

Paper • 2606.18508 • Published 15 days ago • 21

upvoted an article 21 days ago

view article

Article

Can Voice Agents Handle Bilingual Customers? Benchmarking Frontier ASR on Code-Switched Speech

• 

ServiceNow-AI

•

21 days ago

• 44

upvoted an article 26 days ago

view article

Article

EVA-Bench Data 2.0: 3 Domains, 121 Tools, 213 Scenarios

• 

ServiceNow-AI

•

26 days ago

• 41

upvoted 2 papers about 2 months ago

EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents

Paper • 2605.13841 • Published May 13 • 75

Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics

Paper • 2605.12178 • Published May 12 • 65

upvoted 4 papers 3 months ago

Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning

Paper • 2604.02007 • Published Apr 2 • 14

Therefore I am. I Think

Paper • 2604.01202 • Published Apr 2 • 33

Terminal Agents Suffice for Enterprise Automation

Paper • 2604.00073 • Published Mar 31 • 98

CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents

Paper • 2603.24440 • Published Mar 25 • 99

upvoted an article 3 months ago

view article

Article

A New Framework for Evaluating Voice Agents (EVA)

• 

ServiceNow-AI

•

Mar 24

• 95

upvoted a paper 4 months ago

EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings

Paper • 2603.13594 • Published Mar 13 • 149

upvoted a paper 5 months ago

Privileged Information Distillation for Language Models

Paper • 2602.04942 • Published Feb 4 • 28

upvoted 2 articles 7 months ago

view article

Article

Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models

• 

ServiceNow-AI

•

Nov 19, 2025

• 34

view article

Article

Apriel-1.6-15b-Thinker: Cost-efficient Frontier Multimodal Performance

• 

ServiceNow-AI

•

Dec 9, 2025

• 84

upvoted a collection 7 months ago

Apriel-H1

Collection

Introducing Apriel-H1 hybrids each blending Attention and Mamba State Space layers in varying proportions. • 7 items • Updated Mar 2 • 10

upvoted a paper 8 months ago

Grounding Computer Use Agents on Human Demonstrations

Paper • 2511.07332 • Published Nov 10, 2025 • 107

upvoted a collection 9 months ago

Apriel-1.5-15B-Thinker

Collection

3 items • Updated Oct 2, 2025 • 76

upvoted 2 papers 9 months ago

Apriel-1.5-15b-Thinker

Paper • 2510.01141 • Published Oct 1, 2025 • 125

Optimizing What Matters: AUC-Driven Learning for Robust Neural Retrieval

Paper • 2510.00137 • Published Sep 30, 2025 • 3