The paper introduces Synthesis Data Reversion (SDR), a method that infers the data laundering transformation used in LLM training and synthesizes queries to restore the detection signals lost when pro…

This paper proposes four guidelines and two novel data ordering methods (STR and SAW) to systematically optimize data organization, significantly enhancing the stability and performance of LLM trainin…

This paper analyzes the poor performance of Meta-learning for Training-data Selection (MTS) and proposes that increasing the batch size and incorporating informative features can significantly improve…

The paper introduces a novel, non-deep neural network architecture that achieves the performance of LLMs by finding the global optimum of the loss function in a single, closed-form iteration, eliminat…

The paper introduces Sparse Memory-Efficient Training (SMET), a method that stabilizes and optimizes Dynamic Sparse Training (DST) for large language models, enabling stable and memory-efficient spars…

The paper demonstrates that using synthetic hand images containing accessories, generated via inpainting, significantly improves the robustness of hand detectors for safety-critical applications by cl…

The paper proposes Self-Trained Verification (STV), a novel method that trains verifiers to catch self-generated errors by leveraging reference solutions, significantly boosting performance in both te…

This paper synthesizes over 150 scattered studies and reports to provide the first comprehensive primer on post-training reasoning data, organizing the field around data objects, utility, construction…

The paper introduces SORA, an adaptive adversarial training method that dynamically adjusts perturbation sizes to prevent Catastrophic Overfitting, achieving state-of-the-art robustness and clean accu…

This paper investigates the impact of batch sampling strategies using text and audio embeddings on text-to-music generation under low-data conditions.

This paper demonstrates that in-domain pretraining of BERT significantly improves the detection of DNS exfiltration, particularly in maintaining a low false positive rate.

This paper introduces novel, faceted classification schemes to comprehensively categorize the diverse landscape of authenticator-centric authentication techniques and authenticators.

This paper proposes Joint Speech-Text Interleaved Pretraining (JSTIP) for speech recognition, which constructs interleaved speech-text sequences and achieves consistent entity accuracy improvement.

This paper introduces a 'Sleep' paradigm for machine learning models to continually learn and transfer knowledge.

This paper proposes using offline reinforcement learning (RL) as an efficient alternative to online RL for post-training code-generating LLMs, demonstrating its effectiveness, especially for smaller m…

The paper proposes RTFree-F5, a method to make flow-matching TTS models like F5-TTS independent of reference transcripts, improving performance and naturalness for dysarthric speakers.

The paper introduces LinguIUTics, a system that significantly improves the classification of rare psychological defense mechanisms in conversational text by fine-tuning Qwen3-8B using specialized imba…

This paper introduces Arachne, a framework for efficient Text-to-Video model training at scale, reducing iteration time by up to 65% over leading frameworks.

This paper analyzes tool-calling in LLM agents, demonstrating that evaluation results are highly sensitive to implementation details and proposing new techniques to significantly improve the efficienc…