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 --- diversity, deliberative reasoning, and rigorous filtering --- STAR-1 aims to address the critical needs for safety alignment in LRMs. Specifically, we begin by integrating existing open-source safety datasets from diverse sources. Then, we curate safety policies to generate policy-grounded deliberative reasoning samples. Lastly, we apply a GPT-4o-based safety scoring system to select training examples aligned with best practices. Experimental results show that fine-tuning LRMs with STAR-1 leads to an average 40% improvement in safety performance across four benchmarks, while only incurring a marginal decrease (e.g., an average of 1.1%) in reasoning ability measured across five reasoning tasks. Extensive ablation studies further validate the importance of our design principles in constructing STAR-1 and analyze its efficacy across both LRMs and traditional LLMs.

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 labeling budget, selecting an informative and representative data subset for labeling can significantly reduce human annotation effort. Well-performing state-of-the-art (SOTA) coreset selection methods require ground truth labels over the whole dataset, failing to reduce the human labeling burden. Meanwhile, SOTA label-free coreset selection methods deliver inferior performance due to poor geometry-based difficulty scores. In this paper, we introduce ELFS (Effective Label-Free Coreset Selection), a novel label-free coreset selection method. ELFS significantly improves label-free coreset selection by addressing two challenges: 1) ELFS utilizes deep clustering to estimate training dynamics-based data difficulty scores without ground truth labels; 2) Pseudo-labels introduce a distribution shift in the data difficulty scores, and we propose a simple but effective double-end pruning method to mitigate bias on calculated scores. We evaluate ELFS on four vision benchmarks and show that, given the same vision encoder, ELFS consistently outperforms SOTA label-free baselines. For instance, when using SwAV as the encoder, ELFS outperforms D2 by up to 10.2% in accuracy on ImageNet-1K. We make our code publicly available on GitHub.

Jacob K Christopher, Brian R. Bartoldson, Tal Ben-Nun, Michael Cardei, Bhavya Kailkhura, Ferdinando Fioretto. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

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 diversified content of experience replay buffers, which asynchronous off-policy actors can efficiently populate in parallel to training. We propose efficiently learning on such off-policy data via Trajectory Balance with Asynchrony (TBA), an approach to asynchronous RL for LLMs that leverages the principled off-policy TB objective. On math, preference-tuning, and automated red-teaming tasks, we post-train models ranging from Pythia 410M to Qwen 2.5 7B, finding TBA offers speed and performance boosts over strong baselines like Online DPO and Dr. GRPO. Beyond TBA's performance benefits (high accuracy even as asynchrony grows) and speedups ($4\times$ or more), we show its reward- and recency-prioritizing sampling enable further gains as data generation is scaled. Our code is available at https://github.com/bbartoldson/TBA.

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 block, thereby unrolling to arbitrary depth at test-time. This stands in contrast to mainstream reasoning models that scale up compute by producing more tokens. Unlike approaches based on chain-of-thought, our approach does not require any specialized training data, can work with small context windows, and can capture types of reasoning that are not easily represented in words. We train a proof-of-concept model from scratch with 3.5 billion parameters and 800 billion tokens. We show that this model can effortlessly use varying levels of compute, significantly improving with additional compute especially on reasoning tasks, such as math and coding. Further, this architecture naturally reduces compute costs via zero-shot per-token adaptive compute, KV-cache sharing and speculative decoding.

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 and ethical concerns. Training LLMs on openly licensed text presents a first step towards addressing these issues, but prior data collection efforts have yielded datasets too small or low-quality to produce performant LLMs. To address this gap, we collect, curate, and release the Common Pile v0.1, an eight terabyte collection of openly licensed text designed for LLM pretraining. The Common Pile comprises content from 30 sources that span diverse domains including research papers, code, books, encyclopedias, educational materials, audio transcripts, and more. Crucially, we validate our efforts by training two 7 billion parameter LLMs on text from the Common Pile: Comma v0.1-1T and Comma v0.1-2T, trained on 1 and 2 trillion tokens respectively. Both models attain competitive performance to LLMs trained on unlicensed text with similar computational budgets, such as Llama 1 and 2 7B. In addition to releasing the Common Pile v0.1 itself, we also release the code used in its creation as well as the training mixture and checkpoints for the Comma v0.1 models.

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-quality data for training, which can stabilize RL training and improve model performance, but at the cost of significant computational overhead. In this paper, we first show that a substantial portion of this overhead can be avoided by skipping uninformative prompts before rollout. Our analysis of reward dynamics reveals a strong temporal consistency in prompt value: prompts that are uninformative in one epoch of training are likely to remain uninformative in near future epochs. Based on these insights, we propose GRESO (GRPO with Efficient Selective Rollout), an online, lightweight pre-rollout filtering algorithm that predicts and skips uninformative prompts using reward training dynamics. By evaluating GRESO on a broad range of math reasoning benchmarks and models, like Qwen2.5-Math-1.5B, DeepSeek-R1-Distill-Qwen-1.5B, Qwen2.5-Math-7B, Qwen2.5-14B, and Qwen2.5-32B, we show that GRESO achieves up to 2.4x wall-clock time speedup in rollout and up to 2.0x speedup in total training time without accuracy degradation. We make our code publicly available at https://github.com/Infini-AI-Lab/GRESO/.

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 finetuning of LLaMA-2-7B using Alpaca achieves $29.79$\% on AlpacaEval, which rises to $64.69$\% using noisy embeddings. NEFTune also improves over strong baselines on modern instruction datasets. Models trained with Evol-Instruct see a $10$\% improvement, with ShareGPT an $8$\% improvement, and with OpenPlatypus an $8$\% improvement. Even powerful models further refined with RLHF such as LLaMA-2-Chat benefit from additional training with NEFTune. Particularly, we see these improvements on the conversational abilities of the instruction model and not on traditional tasks like those on the OpenLLM Leaderboard, where performance is the same.

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 accuracy is about $100$%, but SOTA robustness to $\ell_{\infty}$-norm bounded perturbations barely exceeds $70$%. To understand this gap, we analyze how model size, dataset size, and synthetic data quality affect robustness by developing the first scaling laws for adversarial training. Our scaling laws reveal inefficiencies in prior art and provide actionable feedback to advance the field. For instance, we discovered that SOTA methods diverge notably from compute-optimal setups, using excess compute for their level of robustness. Leveraging a compute-efficient setup, we surpass the prior SOTA with $20$% ($70$%) fewer training (inference) FLOPs. We trained various compute-efficient models, with our best achieving $74$% AutoAttack accuracy ($+3$% gain). However, our scaling laws also predict robustness slowly grows then plateaus at $90$%: dwarfing our new SOTA by scaling is impractical, and perfect robustness is impossible. To better understand this predicted limit, we carry out a small-scale human evaluation on the AutoAttack data that fools our top-performing model. Concerningly, we estimate that human performance also plateaus near $90$%, which we show to be attributable to $\ell_{\infty}$-constrained attacks’ generation of invalid images not consistent with their original labels. Having characterized limiting roadblocks, we outline promising paths for future research.

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 boast impressive advancements in preserving benign task performance, the potential risks of compression in terms of safety and trustworthiness have been largely neglected. This study conducts the first, thorough evaluation of **three (3) leading LLMs** using **five (5) SoTA compression techniques** across **eight (8) trustworthiness dimensions**. Our experiments highlight the intricate interplay between compression and trustworthiness, revealing some interesting patterns. We find that quantization is currently a more effective approach than pruning in achieving efficiency and trustworthiness simultaneously. For instance, a 4-bit quantized model retains the trustworthiness of its original counterpart, but model pruning significantly degrades trustworthiness, even at 50% sparsity. Moreover, employing quantization within a moderate bit range could unexpectedly improve certain trustworthiness dimensions such as ethics and fairness. Conversely, extreme quantization to very low bit levels (3 bits) tends to reduce trustworthiness significantly. This increased risk cannot be uncovered by looking at benign performance alone, in turn, mandating comprehensive trustworthiness evaluation in practice. These findings culminate in practical recommendations for simultaneously achieving high utility, efficiency, and trustworthiness in LLMs. Code and models are available at https://decoding-comp-trust.github.io.

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 of digits. We mend this problem by adding an embedding to each digit that encodes its position relative to the start of the number. In addition to the boost these embeddings provide on their own, we show that this fix enables architectural modifications such as input injection and recurrent layers to improve performance even further. With positions resolved, we can study the logical extrapolation ability of transformers. Can they solve arithmetic problems that are larger and more complex than those in their training data? We find that training on only 20 digit numbers with a single GPU for one day, we can reach state-of-the-art performance, achieving up to 99% accuracy on 100 digit addition problems. Finally, we show that these gains in numeracy also unlock improvements on other multi-step reasoning tasks including sorting and multiplication.

Although deep learning has made great progress in recent years, the exploding economic and environmental costs of training neural networks are becoming unsustainable. To address this problem, there has been a great deal of research on *algorithmically-efficient deep learning*, which seeks to reduce training costs not at the hardware or implementation level, but through changes in the semantics of the training program. In this paper, we present a structured and comprehensive overview of the research in this field. First, we formalize the *algorithmic speedup* problem, then we use fundamental building blocks of algorithmically efficient training to develop a taxonomy. Our taxonomy highlights commonalities of seemingly disparate methods and reveals current research gaps. Next, we present evaluation best practices to enable comprehensive, fair, and reliable comparisons of speedup techniques. To further aid research and applications, we discuss common bottlenecks in the training pipeline (illustrated via experiments) and offer taxonomic mitigation strategies for them. Finally, we highlight some unsolved research challenges and present promising future directions.

The CO2 capture efficiency in solvent-based carbon capture systems (CCSs) critically depends on the gas-solvent interfacial area (IA), making maximization of IA a foundational challenge in CCS design. While the IA associated with a particular CCS design can be estimated via a computational fluid dynamics (CFD) simulation, using CFD to derive the IAs associated with numerous CCS designs is prohibitively costly. Fortunately, previous works such as Deep Fluids (DF) (Kim et al., 2019) show that large simulation speedups are achievable by replacing CFD simulators with neural network (NN) surrogates that faithfully mimic the CFD simulation process. This raises the possibility of a fast, accurate replacement for a CFD simulator and therefore efficient approximation of the IAs required by CCS design optimization. Thus, here, we build on the DF approach to develop surrogates that can successfully be applied to our complex carbon-capture CFD simulations. Our optimized DF-style surrogates produce large speedups (4000x) while obtaining IA relative errors as low as 4% on unseen CCS configurations that lie within the range of training configurations. This hints at the promise of NN surrogates for our CCS design optimization problem. Nonetheless, DF has inherent limitations with respect to CCS design (e.g., limited transferability of trained models to new CCS packings). We conclude with ideas to address these challenges.

Improving the accuracy of deep neural networks on out-of-distribution (OOD) data is critical to an acceptance of deep learning in real world applications. It has been observed that accuracies on in-distribution (ID) versus OOD data follow a linear trend and models that outperform this baseline are exceptionally rare (and referred to as ``effectively robust”). Recently, some promising approaches have been developed to improve OOD robustness: model pruning, data augmentation, and ensembling or zero-shot evaluating large pretrained models. However, there still is no clear understanding of the conditions on OOD data and model properties that are required to observe effective robustness. We approach this issue by conducting a comprehensive empirical study of diverse approaches that are known to impact OOD robustness on a broad range of natural and synthetic distribution shifts of CIFAR-10 and ImageNet. In particular, we view the "effective robustness puzzle" through a Fourier lens and ask how spectral properties of both models and OOD data correlate with OOD robustness. We find this Fourier lens offers some insight into why certain robust models, particularly those from the CLIP family, achieve OOD robustness. However, our analysis also makes clear that no known metric is consistently the best explanation of OOD robustness. Thus, to aid future research into the OOD puzzle, we address the gap in publicly-available models with effective robustness by introducing a set of pretrained CIFAR-10 models---$RobustNets$---with varying levels of OOD robustness.

Successful adoption of deep learning (DL) in the wild requires models to be: (1) compact, (2) accurate, and (3) robust to distributional shifts. Unfortunately, efforts towards simultaneously meeting these requirements have mostly been unsuccessful. This raises an important question: Is the inability to create Compact, Accurate, and Robust Deep neural networks (CARDs) fundamental? To answer this question, we perform a large-scale analysis of popular model compression techniques which uncovers several intriguing patterns. Notably, in contrast to traditional pruning approaches (e.g., fine tuning and gradual magnitude pruning), we find that ``lottery ticket-style'' approaches can surprisingly be used to produce CARDs, including binary-weight CARDs. Specifically, we are able to create extremely compact CARDs that, compared to their larger counterparts, have similar test accuracy and matching (or better) robustness---simply by pruning and (optionally) quantizing. Leveraging the compactness of CARDs, we develop a simple domain-adaptive test-time ensembling approach (CARD-Decks) that uses a gating module to dynamically select appropriate CARDs from the CARD-Deck based on their spectral-similarity with test samples. The proposed approach builds a "winning hand'' of CARDs that establishes a new state-of-the-art (on RobustBench) on CIFAR-10-C accuracies (i.e., 96.8% standard and 92.75% robust) and CIFAR-100-C accuracies (80.6% standard and 71.3% robust) with better memory usage than non-compressed baselines (pretrained CARDs and CARD-Decks available at https://github.com/RobustBench/robustbench). Finally, we provide theoretical support for our empirical findings.

Pruning neural network parameters is often viewed as a means to compress models, but pruning has also been motivated by the desire to prevent overfitting. This motivation is particularly relevant given the perhaps surprising observation that a wide variety of pruning approaches increase test accuracy despite sometimes massive reductions in parameter counts. To better understand this phenomenon, we analyze the behavior of pruning over the course of training, finding that pruning's benefit to generalization increases with pruning's instability (defined as the drop in test accuracy immediately following pruning). We demonstrate that this "generalization-stability tradeoff'' is present across a wide variety of pruning settings and propose a mechanism for its cause: pruning regularizes similarly to noise injection. Supporting this, we find less pruning stability leads to more model flatness and the benefits of pruning do not depend on permanent parameter removal. These results explain the compatibility of pruning-based generalization improvements and the high generalization recently observed in overparameterized networks.