Related papers: Shuffle the Context: RoPE-Perturbed Self-Distillat…

While many advanced LLMs are designed to handle long sequence data, we can still observe notable quality degradation even within the sequence limit. In this work, we introduce a novel approach called Scaling to Emphasize Attention for…

Broad textual understanding and in-context learning require language models that utilize full document contexts. Due to the implementation challenges associated with directly training long-context models, many methods have been proposed for…

Large language models (LLMs) have demonstrated their ability to learn in-context, allowing them to perform various tasks based on a few input-output examples. However, the effectiveness of in-context learning is heavily reliant on the…

The pretrain-finetuning paradigm in large-scale sequence models has made significant progress in natural language processing and computer vision tasks. However, such a paradigm is still hindered by several challenges in Reinforcement…

Despite recent advancements in Large Language Models (LLMs), their performance on tasks involving long contexts remains sub-optimal. In this work, we propose DoubleDipper, a novel In-Context-Learning method that automatically generates…

Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-document understanding, video analysis, and multi-turn tool use in agentic workflows. Yet…

Large language models (LLMs) have received significant attention by achieving remarkable performance across various tasks. However, their fixed context length poses challenges when processing long documents or maintaining extended…

The ability to process ultra-long contexts is crucial for large language models (LLMs) to perform long-horizon tasks. While recent efforts have extended context windows to 1M and beyond, model performance degrades when sequence length…

Algorithm Distillation (AD) was recently proposed as a new approach to perform In-Context Reinforcement Learning (ICRL) by modeling across-episodic training histories autoregressively with a causal transformer model. However, due to…

Large language models (LLMs) are increasingly strong contenders in machine translation. In this work, we focus on document-level translation, where some words cannot be translated without context from outside the sentence. Specifically, we…

Self-consistency (SC) improves the performance of large language models (LLMs) across various tasks and domains that involve short content. However, does this support its effectiveness for long-context problems? We challenge the assumption…

Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization methods offer preliminary solutions, they fall short in…

Despite the fact that Transformers perform well in NLP tasks, recent studies suggest that self-attention is theoretically limited in learning even some regular and context-free languages. These findings motivated us to think about their…

Large language models (LLMs) with long-context processing are still challenging because of their implementation complexity, training efficiency and data sparsity. To address this issue, a new paradigm named Online Long-context Processing…

Large Language Model agents excel at solving complex tasks through iterative reasoning and tool use, but typically depend on ultra-large, costly backbones. Existing distillation approaches train smaller students to imitate full teacher…

Large language models suffer issues when operated on long contexts that are larger than their training context length due to the standard position encoding for tokens in the attention layer. Tokens a long distance apart will rarely have an…

Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences.…

Central to many self-improvement pipelines for large language models (LLMs) is the assumption that models can improve by reflecting on past mistakes. We study a phenomenon termed contextual drag: the presence of failed attempts in the…

Large-scale vision-language models (VLMs), e.g., CLIP, learn broad visual concepts from tedious training data, showing superb generalization ability. Amount of prompt learning methods have been proposed to efficiently adapt the VLMs to…

Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information across long contexts. Recent works like Recursive Language…