ข่าว
Train Your Large Model on Multiple GPUs with Tensor Parallelism
This article is divided into five parts; they are: • An Example of Tensor Parallelism...
Train Your Large Model on Multiple GPUs with Fully Sharded Data Parallelism
This article is divided into five parts; they are: • Introduction to Fully Sharded Data...
Train a Model Faster with torch.compile and Gradient Accumulation
This article is divided into two parts; they are: • Using `torch...
Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology
arXiv:2507.07999v2 Announce Type: replace-cross Abstract: Models like OpenAI-o3 pioneer visual grounded reasoning by dynamically referencing...
TRACE: Textual Relevance Augmentation and Contextual Encoding for Multimodal Hate Detection
arXiv:2504.17902v2 Announce Type: replace-cross Abstract: Social media memes are a challenging domain for hate detection...
TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG
arXiv:2512.07515v2 Announce Type: replace Abstract: Detecting hallucinations in Retrieval-Augmented Generation remains a challenge. Prior approaches...
ToxSearch: Evolving Prompts for Toxicity Search in Large Language Models
arXiv:2511.12487v2 Announce Type: replace-cross Abstract: Large Language Models remain vulnerable to adversarial prompts that elicit...
ToxiTwitch: Toward Emote-Aware Hybrid Moderation for Live Streaming Platforms
arXiv:2601.15605v1 Announce Type: new Abstract: The rapid growth of live-streaming platforms such as Twitch has...
ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection
arXiv:2508.11281v1 Announce Type: new Abstract: Detecting toxic content using language models is crucial yet challenging...
Towards Understanding the Cognitive Habits of Large Reasoning Models
arXiv:2506.21571v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs), which autonomously produce a reasoning Chain...
Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models
arXiv:2508.17184v1 Announce Type: new Abstract: Instruction tuning is a pivotal technique for aligning large language...
Towards Active Synthetic Data Generation for Finetuning Language Models
arXiv:2512.00884v2 Announce Type: replace-cross Abstract: A common and effective means for improving language model capabilities...
