32 citations · 94 across the 27 of their papers we have counts for
30 papers
Reducing Catastrophic Risk from AI with Systematic Monitoring and Evaluation of Rogue AI Progression
T. Bauer, W. P. Kegelmeyer, E. Begoli +15
This article presents a structured framework of behavioral indicators that may signal progression toward potentially catastrophic threats from artificial intelligence systems. We a…
Watermarking for Proprietary Dataset Protection
John Kirchenbauer, Brian R. Bartoldson, Bhavya Kailkhura +1
A growing body of literature suggests that training data membership inference problems are fundamentally hard tasks in modern language modeling settings. We argue that output water…
End-to-End Context Compression at Scale
Ang Li, Sean McLeish, Haozhe Chen +12
Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degra…
LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
Sumeet Ramesh Motwani, Daniel Nichols, Charles London +17
As language models are increasingly deployed for complex autonomous tasks, their ability to reason accurately over longer horizons becomes critical. An essential component of this…
Multi-Token Prediction via Self-Distillation
John Kirchenbauer, Abhimanyu Hans, Brian Bartoldson +3
Existing techniques for accelerating language model inference, such as speculative decoding, require training auxiliary speculator models and building and deploying complex inferen…
A Comedy of Estimators: On KL Regularization in RL Training of LLMs
Vedant Shah, Johan Obando-Ceron, Vineet Jain +10
The reasoning performance of large language models (LLMs) can be substantially improved by training them with reinforcement learning (RL). The RL objective for LLM training involve…
Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
Sean McLeish, Ang Li, John Kirchenbauer +7
Recent advances in depth-recurrent language models show that recurrence can decouple train-time compute and parameter count from test-time compute. In this work, we study how to co…
Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness
Tavish McDonald, Bo Lei, Stanislav Fort +2
Test-time reasoning has raised benchmark performances and even shown promise in addressing the historically intractable problem of making models robust to adversarially out-of-dist…
Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models
Siddarth Venkatraman, Vineet Jain, Sarthak Mittal +9
Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference to make a prediction. Inference-time co…
Modeling Code: Is Text All You Need?
Daniel Nichols, Konstantinos Parasyris, Harshitha Menon +4
Code LLMs have become extremely popular recently for modeling source code across a variety of tasks, such as generation, translation, and summarization. However, transformer-based…
The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
Nikhil Kandpal, Brian Lester, Colin Raffel +24
Large language models (LLMs) are typically trained on enormous quantities of unlicensed text, a practice that has led to scrutiny due to possible intellectual property infringement…
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Haizhong Zheng, Yang Zhou, Brian R. Bartoldson +4
Reinforcement learning, such as PPO and GRPO, has powered recent breakthroughs in LLM reasoning. Scaling rollout to sample more prompts enables models to selectively use higher-qua…
AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security
Zikui Cai, Shayan Shabihi, Bang An +5
We introduce AegisLLM, a cooperative multi-agent defense against adversarial attacks and information leakage. In AegisLLM, a structured workflow of autonomous agents - orchestrator…
STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
Zijun Wang, Haoqin Tu, Yuhan Wang +6
This paper introduces STAR-1, a high-quality, just-1k-scale safety dataset specifically designed for large reasoning models (LRMs) like DeepSeek-R1. Built on three core principles…
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
Brian Bartoldson, Siddarth Venkatraman, James Diffenderfer +7
Reinforcement learning (RL) is a critical component of large language model (LLM) post-training. However, on-policy algorithms used for post-training are not naturally robust to a…
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Jonas Geiping, Sean McLeish, Neel Jain +6
We study a novel language model architecture that is capable of scaling test-time computation by implicitly reasoning in latent space. Our model works by iterating a recurrent bloc…
Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness
Zeyu Wang, Cihang Xie, Brian Bartoldson +1
This paper investigates the robustness of vision-language models against adversarial visual perturbations and introduces a novel ``double visual defense" to enhance this robustness…
Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion
Jacob K Christopher, Brian R Bartoldson, Tal Ben-Nun +3
Speculative decoding has emerged as a widely adopted method to accelerate large language model inference without sacrificing the quality of the model outputs. While this technique…
ELFS: Label-Free Coreset Selection with Proxy Training Dynamics
Haizhong Zheng, Elisa Tsai, Yifu Lu +4
High-quality human-annotated data is crucial for modern deep learning pipelines, yet the human annotation process is both costly and time-consuming. Given a constrained human label…
Transformers Can Do Arithmetic with the Right Embeddings
Sean McLeish, Arpit Bansal, Alex Stein +8
The poor performance of transformers on arithmetic tasks seems to stem in large part from their inability to keep track of the exact position of each digit inside of a large span o…
Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
Brian R. Bartoldson, James Diffenderfer, Konstantinos Parasyris +1
This paper revisits the simple, long-studied, yet still unsolved problem of making image classifiers robust to imperceptible perturbations. Taking CIFAR10 as an example, SOTA clean…
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
Junyuan Hong, Jinhao Duan, Chenhui Zhang +12
Compressing high-capability Large Language Models (LLMs) has emerged as a favored strategy for resource-efficient inferences. While state-of-the-art (SoTA) compression methods boas…
NEFTune: Noisy Embeddings Improve Instruction Finetuning
Neel Jain, Ping-yeh Chiang, Yuxin Wen +10
We show that language model finetuning can be improved, sometimes dramatically, with a simple augmentation. NEFTune adds noise to the embedding vectors during training. Standard fi…
Scientific Computing Algorithms to Learn Enhanced Scalable Surrogates for Mesh Physics
Brian R. Bartoldson, Yeping Hu, Amar Saini +6
Data-driven modeling approaches can produce fast surrogates to study large-scale physics problems. Among them, graph neural networks (GNNs) that operate on mesh-based data are desi…