Related papers: The Stability-Efficiency Dilemma: Investigating Se…

The training of large language models (LLMs) is expensive. In this paper, we study data-efficient approaches for pre-training LLMs, i.e., techniques that aim to optimize the Pareto frontier of model quality and training resource/data…

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes available. A much more efficient solution is to continually pre-train these models, saving significant…

Large Language Models (LLMs) excel at long-context understanding but exhibit significant limitations in long-form generation. Existing studies primarily focus on single-generation quality, generally overlooking the volatility of the output.…

An appropriate choice of batch sizes in large-scale model training is crucial, yet it involves an intrinsic yet inevitable dilemma: large-batch training improves training efficiency in terms of memory utilization, while generalization…

This paper examines the phenomenon of probabilistic robustness overestimation in TRADES, a prominent adversarial training method. Our study reveals that TRADES sometimes yields disproportionately high PGD validation accuracy compared to the…

Large language models (LLMs) have achieved widespread success on a variety of in-context few-shot tasks, but this success is typically evaluated via correctness rather than consistency. We argue that self-consistency is an important…

Recent research enhances language model reasoning by scaling test-time compute via longer chain-of-thought traces. This often improves accuracy but also introduces redundancy and high computational cost, especially for small language models…

Fine-tuning large language models is a popular choice among users trying to adapt them for specific applications. However, fine-tuning these models is a demanding task because the user has to examine several factors, such as resource…

Building deep reinforcement learning (RL) agents that find a good policy with few samples has proven notoriously challenging. To achieve sample efficiency, recent work has explored updating neural networks with large numbers of gradient…

Reinforcement learning (RL) experiments have notoriously high variance, and minor details can have disproportionately large effects on measured outcomes. This is problematic for creating reproducible research and also serves as an obstacle…

Continual learning aims to incrementally acquire new concepts in data streams while resisting forgetting previous knowledge. With the rise of powerful pre-trained models (PTMs), there is a growing interest in training incremental learning…

Large Language Models (LLMs) currently respond to every prompt. However, they can produce incorrect answers when they lack knowledge or capability -- a problem known as hallucination. We instead propose post-training an LLM to generate…

Scale of data and scale of computation infrastructures together enable the current deep learning renaissance. However, training large-scale deep architectures demands both algorithmic improvement and careful system configuration. In this…

Continual Instruction Tuning (CIT) is adopted to continually instruct Large Models to follow human intent data by data. It is observed that existing gradient update would heavily destroy the performance on previous datasets during CIT…

Despite the recent success of large language models (LLMs) in reasoning such as DeepSeek, we for the first time identify a key dilemma in reasoning robustness and generalization: significant performance degradation on novel or incomplete…

Standard attention-based transformers are known to exhibit instability under learning rate overspecification during training, particularly at high learning rates. While various methods have been proposed to improve resilience to such…

Test-time scaling improves the reasoning capabilities of large language models (LLMs) by allocating extra compute to generate longer Chains-of-Thoughts (CoTs). This enables models to tackle more complex problem by breaking them down into…

Deep learning-based RF fingerprinting offers great potential for improving the security robustness of various emerging wireless networks. Although much progress has been done in enhancing fingerprinting methods, the impact of device…

Long sequences are critical for applications like RAG, long document summarization, multi-modality, etc., and modern LLMs, like Llama 4 Scout, support max sequence length of up to 10 million tokens. However, outside of enterprise labs, long…

Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge. Despite substantial progress in benchmarking CL methods, comparative evaluations typically keep the fine-tuning regime…