Related papers: BEAVER: A Training-Free Hierarchical Prompt Compre…
Existing approaches for improving the efficiency of Large Vision-Language Models (LVLMs) are largely based on the concept of visual token reduction. This approach, however, creates an information bottleneck that impairs performance,…
Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and distillation, have been embraced to compress LLMs, targeting…
Multimodal large language models (MLLMs) have made remarkable strides, largely driven by their ability to process increasingly long and complex contexts, such as high-resolution images, extended video sequences, and lengthy audio input.…
In modern large language models (LLMs), increasing the context length is crucial for improving comprehension and coherence in long-context, multi-modal, and retrieval-augmented language generation. While many recent transformer models…
Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spanning hundreds of words, make inference substantially more…
Despite their remarkable achievements, modern Large Language Models (LLMs) face exorbitant computational and memory footprints. Recently, several works have shown significant success in training-free and data-free compression (pruning and…
Efficient long-context LLM deployment is stalled by a dichotomy between amortized compression, which struggles with out-of-distribution generalization, and Test-Time Training, which incurs prohibitive synthetic data costs and requires…
Large Language Models (LLMs) have recently achieved remarkable progress by leveraging Reinforcement Learning and extended Chain-of-Thought (CoT) techniques. However, the challenge of performing efficient language reasoning--especially…
We propose a novel, lightweight supervised dictionary learning framework for text classification based on data compression and representation. This two-phase algorithm initially employs the Lempel-Ziv-Welch (LZW) algorithm to construct a…
Assessing the quality of outputs generated by generative models, such as large language models and vision language models, presents notable challenges. Traditional methods for evaluation typically rely on either human assessments, which are…
While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven…
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…
The Key-Value (KV) cache in generative large language models (LLMs) introduces substantial memory overhead. Existing works mitigate this burden by offloading or compressing the KV cache. However, loading the entire cache incurs significant…
Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…
As the context length of current large language models (LLMs) rapidly increases, the memory demand for the Key-Value (KV) cache is becoming a bottleneck for LLM deployment and batch processing. Traditional KV cache compression methods…
Large Language Models (LLMs) have demonstrated remarkable proficiency in language comprehension and generation; however, their widespread adoption is constrained by substantial bandwidth and computational demands. While pruning and low-rank…
Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large…
Standard Large Language Models (LLMs) struggle with handling dialogues with long contexts due to efficiency and consistency issues. According to our observation, dialogue contexts are highly structured, and the special token of…
The integration of extensive, dynamic knowledge into Large Language Models (LLMs) remains a significant challenge due to the inherent entanglement of factual data and reasoning patterns. Existing solutions, ranging from non-parametric…
Large Language Models (LLMs) struggle with long-horizon tasks due to the "context bottleneck" and the "lost-in-the-middle" phenomenon, where accumulated noise from verbose environments degrades reasoning over multi-turn interactions. To…