Related papers: Compressing Many-Shots in In-Context Learning
Large language models (LLMs) can adapt to new tasks via in-context learning (ICL) without parameter updates, making them powerful learning engines for fast adaptation. While extensive research has examined ICL as a few-shot learner, whether…
In-Context Learning (ICL) empowers Large Language Models (LLMs) to tackle diverse tasks by incorporating multiple input-output examples, known as demonstrations, into the input of LLMs. More recently, advancements in the expanded context…
In-context learning (ICL) has emerged as an effective solution for few-shot learning with large language models (LLMs). However, how LLMs leverage demonstrations to specify a task and learn a corresponding computational function through ICL…
Prompt optimization is essential for enhancing the performance of Large Language Models (LLMs) in a range of Natural Language Processing (NLP) tasks, particularly in scenarios of few-shot learning where training examples are incorporated…
In-context Learning (ICL) is an emerging few-shot learning paradigm based on modern Language Models (LMs), yet its inner mechanism remains unclear. In this paper, we investigate the mechanism through a novel perspective of information…
Video Large Language Models (VideoLLMs) have demonstrated remarkable understanding capabilities, but are found struggling to tackle multi-shot scenarios,e.g., video clips with varying camera angles or scene changes. This challenge can…
Large language models (LLMs) famously exhibit emergent in-context learning (ICL) -- the ability to rapidly adapt to new tasks using few-shot examples provided as a prompt, without updating the model's weights. Built on top of LLMs, vision…
Large reasoning models (LRMs) typically solve reasoning-intensive tasks by generating long chain-of-thought (CoT) traces, leading to substantial inference overhead. We identify a reproducible inference-time phenomenon, termed…
Image Compression for Machines (ICM) aims to compress images for machine vision tasks rather than human viewing. Current works predominantly concentrate on high-level tasks like object detection and semantic segmentation. However, the…
Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be obscured by noise, truncated due to limited windows, and…
LLMs face significant challenges in systematic generalization, particularly when dealing with reasoning tasks requiring compositional rules and handling out-of-distribution examples. To address these challenges, we introduce an in-context…
In-context learning (ICL) has transformed the use of large language models (LLMs) for NLP tasks, enabling few-shot learning by conditioning on labeled examples without finetuning. Despite its effectiveness, ICL is prone to errors,…
Large language models (LLMs) have demonstrated impressive few-shot in-context learning (ICL) abilities. Still, we show that they are sometimes prone to a `copying bias', where they copy answers from provided examples instead of learning the…
Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale…
In this paper, by treating in-context learning (ICL) as a meta-optimization process, we explain why LLMs are sensitive to the order of ICL examples. This understanding leads us to the development of Batch-ICL, an effective, efficient, and…
Large language models (LLMs) have achieved significant performance gains using advanced prompting techniques over various tasks. However, the increasing length of prompts leads to high computational costs and often obscures crucial…
Large Language Models (LLMs) have demonstrated exceptional abilities across a broad range of language-related tasks, including generating solutions to complex reasoning problems. An effective technique to enhance LLM performance is…
In-context learning (ICL) enables Large Vision-Language Models (LVLMs) to adapt to new tasks without parameter updates, using a few demonstrations from a large support set. However, selecting informative demonstrations leads to high…
Multilinear Compressive Learning (MCL) is an efficient signal acquisition and learning paradigm for multidimensional signals. The level of signal compression affects the detection or classification performance of a MCL model, with higher…
Most recent few-shot learning approaches are based on meta-learning with episodic training. However, prior studies encounter two crucial problems: (1) \textit{the presence of inductive bias}, and (2) \textit{the occurrence of catastrophic…