Papers

Papers by year released in reversed chronological order.

2025

2025

  1. arXiv
    DynaGuard: A Dynamic Guardrail Model With User-Defined Policies
    Monte Hoover, Vatsal Baherwani, Neel Jain, Khalid Saifullah, Joseph Vincent, Chirag Jain, Melissa Kazemi Rad, C Bayan Bruss, and 2 more authors
    arXiv preprint arXiv:2509.02563,
    PDF
  2. NeurIPS
    Scaling up test-time compute with latent reasoning: A recurrent depth approach
    Jonas Geiping, Sean McLeish, Neel Jain, John Kirchenbauer, Siddharth Singh, Brian R Bartoldson, Bhavya Kailkhura, Abhinav Bhatele, and 1 more author
    Neural Information Processing Systems (Spotlight), 2025
    PDF
  3. COLM
    Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
    Neel Jain, Aditya Shrivastava, Chenyang Zhu, Daben Liu, Alfy Samuel, Ashwinee Panda, Anoop Kumar, Micah Goldblum, and 1 more author
    Second Conference on Language Modeling, 2025
  4. ICLR
    LiveBench: A Challenging, Contamination-Free LLM Benchmark
    Colin White, Samuel Dooley, Manley Roberts, Arka Pal, Ben Feuer, Siddhartha Jain, Ravid Shwartz-Ziv, Neel Jain, and 3 more authors
    International Conference on Learning Representations (Spotlight), 2025
    PDF Blog

2024

2024

  1. SC24
    Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers
    Siddharth Singh, Prajwal Singhania, Aditya Ranjan, John Kirchenbauer, Jonas Geiping, Yuxin Wen, Neel Jain, Abhimanyu Hans, and 4 more authors
    SC24: International Conference for High Performance Computing, Networking, Storage and Analysis (Gordon Bell Finalist), 2024
    PDF
  2. arXiv
    GenQA: Generating Millions of Instructions from a Handful of Prompts
    Jiuhai Chen, Rifaa Qadri, Yuxin Wen, Neel Jain, John Kirchenbauer, Tianyi Zhou, and Tom Goldstein
    arXiv preprint arXiv:2406.10323,
    PDF Data
  3. NeurIPS
    Be like a Goldfish, Don’t Memorize! Mitigating Memorization in Generative LLMs
    Abhimanyu Hans, Yuxin Wen, Neel Jain, John Kirchenbauer, Hamid Kazemi, Prajwal Singhania, Siddharth Singh, Gowthami Somepalli, and 3 more authors
    Neural Information Processing Systems, 2024
    PDF Code
  4. NeurIPS
    Transformers Can Do Arithmetic with the Right Embeddings
    Sean McLeish, Arpit Bansal, Alex Stein, Neel Jain, John Kirchenbauer, Brian R Bartoldson, Bhavya Kailkhura, Abhinav Bhatele, and 3 more authors
    Neural Information Processing Systems, 2024
    PDF Code
  5. arXiv
    Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs
    Ryan Synk, Monte Hoover, John Kirchenbauer, Neel Jain, Alex Stein, Manli Shu, Josue Melendez Sanchez, Ramani Duraiswami, and 1 more author
    arXiv preprint arXiv:2502.06766,
    PDF

2023

2023

  1. ICLR
    NEFTune: Noisy Embeddings Improve Instruction Finetuning
    Neel Jain, Ping-yeh Chiang, Yuxin Wen, John Kirchenbauer, Hong-Min Chu, Gowthami Somepalli, Brian Bartoldson, Bhavya Kailkhura, and 5 more authors
    International Conference on Learning Representations, 2024
    PDF Code
  2. arXiv
    Baseline Defenses for Adversarial Attacks Against Aligned Language Models
    Neel Jain, Avi Schwarzschild, Yuxin Wen, Gowthami Somepalli, John Kirchenbauer, Ping-yeh Chiang, Micah Goldblum, Aniruddha Saha, and 2 more authors
    arXiv preprint arXiv:2309.00614, 2023
    PDF Code
  3. COLM
    Bring Your Own Data! Self-Supervised Evaluation for Large Language Models
    Neel Jain, Khalid Saifullah, Yuxin Wen, John Kirchenbauer, Manli Shu, Aniruddha Saha, Micah Goldblum, Jonas Geiping, and 1 more author
    Conference on Language Modeling, 2024
    PDF Code
  4. NeurIPS
    Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
    Yuxin Wen, Neel Jain, John Kirchenbauer, Micah Goldblum, Jonas Geiping, and Tom Goldstein
    Neural Information Processing Systems, 2023
    PDF Code Demo

2022

2022

  1. How to Do a Vocab Swap? A Study of Embedding Replacement for Pre-trained Transformers
    Neel Jain, John Kirchenbauer, Jonas Geiping, and Tom Goldstein
    Preprint, 2022
    PDF

2020

2020

  1. Springer
    Multi-color forcing in graphs
    Chassidy Bozeman, Pamela E Harris, Neel Jain, Ben Young, and Teresa Yu
    Graphs and Combinatorics, 2020
    PDF