Cohere Labs ML-Agents Community

c4ai-ml-agents's activity

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

1024m 

updated a Space 10 days ago

Running

c4ai-ml-agents

🤖

Cohere Labs ML-Agents group

1024m 

published a Space 10 days ago

Running

c4ai-ml-agents

🤖

Cohere Labs ML-Agents group

ignoreandfly 

authored 2 papers about 2 months ago

The Spatial Blindspot of Vision-Language Models

Paper • 2601.09954 • Published Jan 15

Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks

Paper • 2605.01417 • Published May 2 • 1

raghavprabhakar 

authored 2 papers 2 months ago

MahaTTS: A Unified Framework for Multilingual Text-to-Speech Synthesis

Paper • 2508.14049 • Published Aug 5, 2025

Population Dynamics in ARIEL Robotics Systems Featuring Embodied Evolution via Spatial Mating Mechanisms

Paper • 2604.26822 • Published Apr 29

patrickamadeus 

authored 5 papers 3 months ago

Seeing Culture: A Benchmark for Visual Reasoning and Grounding

Paper • 2509.16517 • Published Sep 20, 2025 • 3

Vision Language Models are Confused Tourists

Paper • 2511.17004 • Published Nov 21, 2025 • 1

Can Large Language Models Understand, Reason About, and Generate Code-Switched Text?

Paper • 2601.07153 • Published Jan 12

M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG

Paper • 2512.05959 • Published Dec 5, 2025

LinguDistill: Recovering Linguistic Ability in Vision- Language Models via Selective Cross-Modal Distillation

Paper • 2604.00829 • Published Apr 1 • 8

patrickamadeus 

submitted a paper to Daily Papers 3 months ago

LinguDistill: Recovering Linguistic Ability in Vision- Language Models via Selective Cross-Modal Distillation

Paper • 2604.00829 • Published Apr 1 • 8

syedmohaiminulhoque 

authored a paper 4 months ago

Gradient Masters at BLP-2025 Task 1: Advancing Low-Resource NLP for Bengali using Ensemble-Based Adversarial Training for Hate Speech Detection

Paper • 2511.18324 • Published Nov 23, 2025

Abrar2652 

authored 2 papers 5 months ago

AdeptHEQ-FL: Adaptive Homomorphic Encryption for Federated Learning of Hybrid Classical-Quantum Models with Dynamic Layer Sparing

Paper • 2507.07316 • Published Jul 9, 2025

ChronoSpike: An Adaptive Spiking Graph Neural Network for Dynamic Graphs

Paper • 2602.01124 • Published Feb 1 • 1

Akhil-Theerthala 

submitted a paper to Daily Papers 6 months ago

FinForge: Semi-Synthetic Financial Benchmark Generation

Paper • 2601.06747 • Published Jan 11 • 2

Akhil-Theerthala 

authored a paper 6 months ago

FinForge: Semi-Synthetic Financial Benchmark Generation

Paper • 2601.06747 • Published Jan 11 • 2

Akhil-Theerthala 

posted an update 6 months ago

view post

Post

504

Is it better to show a model too many images once (Diversity), or extract as much information from a small set of images?

I have always wanted to do an ablation study on this and recently I got the chance to do exactly that. Why? In applied domains like robotics, manufacturing, or banking, we rarely have the luxury of internet-scale diverse image datasets. We are often "Data Poor" in terms of diversity but "Data Rich" in depth.

The takeaway? Density is efficient for facts but dangerous for reasoning (logical collapse) if you don't have larger scale data.

More details:
https://huggingface.co/blog/Akhil-Theerthala/diversity-density-for-vision-language-models

See translation

• 
• 1 reply

·

👍

3

3

+

Reply

smsnobin77 

authored 2 papers 7 months ago

FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health

Paper • 2509.14275 • Published Sep 16, 2025

FedMentalCare: Towards Privacy-Preserving Fine-Tuned LLMs to Analyze Mental Health Status Using Federated Learning Framework

Paper • 2503.05786 • Published Feb 27, 2025