2 225 90

Raja Biswas

rbiswasfc

raja_biswas
rbiswasfc
raja-biswas
raja-biswas.bsky.social

AI & ML interests

NLP, Generative AI

Recent Activity

upvoted a paper 13 days ago

Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs

liked a Space about 1 month ago

HuggingFaceTB/smol-training-playbook

upvoted a paper about 1 month ago

DRBench: A Realistic Benchmark for Enterprise Deep Research

View all activity

Raja Biswas

AI & ML interests

Recent Activity

Organizations

rbiswasfc 's collections 4

SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents

Alibaba-NLP/Tongyi-DeepResearch-30B-A3B

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

Open Data Synthesis For Deep Research

Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models

Textbooks Are All You Need II: phi-1.5 technical report

DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows

Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models

Orca 2: Teaching Small Language Models How to Reason

ToolTalk: Evaluating Tool-Usage in a Conversational Setting

Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning

MultiLoRA: Democratizing LoRA for Better Multi-Task Learning

OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework

Scaling Laws for Downstream Task Performance of Large Language Models

Orca 2: Teaching Small Language Models How to Reason

Orca-Math: Unlocking the potential of SLMs in Grade School Math

SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents

Alibaba-NLP/Tongyi-DeepResearch-30B-A3B

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

Open Data Synthesis For Deep Research

Orca 2: Teaching Small Language Models How to Reason

ToolTalk: Evaluating Tool-Usage in a Conversational Setting

Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning

MultiLoRA: Democratizing LoRA for Better Multi-Task Learning

Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models

Textbooks Are All You Need II: phi-1.5 technical report

DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows

Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models

OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework

Scaling Laws for Downstream Task Performance of Large Language Models

Orca 2: Teaching Small Language Models How to Reason

Orca-Math: Unlocking the potential of SLMs in Grade School Math