Related papers: Anchored Decoding: Provably Reducing Copyright Ris…

Large-scale vision-and-language models, such as CLIP, are typically trained on web-scale data, which can introduce inappropriate content and lead to the development of unsafe and biased behavior. This, in turn, hampers their applicability…

Dense retrieval calls for discriminative embeddings to represent the semantic relationship between query and document. It may benefit from the using of large language models (LLMs), given LLMs' strong capability on semantic understanding.…

Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current…

In this study, we propose a homotopy-inspired prompt obfuscation framework to enhance understanding of security and safety vulnerabilities in Large Language Models (LLMs). By systematically applying carefully engineered prompts, we…

Controlling Large Language Models (LLMs) to prevent the generation of undesirable content, such as profanity and personally identifiable information (PII), has become increasingly critical. While earlier approaches relied on post-processing…

Large Language Models (LLMs) achieve strong performance across tasks, but face storage and compute challenges on edge devices. We propose EntroLLM, a compression framework combining mixed quantization and entropy coding to reduce storage…

In this paper, we highlight a critical threat posed by emerging neural models: data plagiarism. We demonstrate how modern neural models (e.g., diffusion models) can replicate copyrighted images, even when protected by advanced watermarking…

Large language models(LLMs) are currently at the forefront of the machine learning field, which show a broad application prospect but at the same time expose some risks of privacy leakage. We combined Fully Homomorphic Encryption(FHE) and…

Federated Learning (FL) offers a decentralized framework for training and fine-tuning Large Language Models (LLMs) by leveraging computational resources across organizations while keeping sensitive data on local devices. It addresses…

A deep learning system typically suffers from a lack of reproducibility that is partially rooted in hardware or software implementation details. The irreproducibility leads to skepticism in deep learning technologies and it can hinder them…

Diffusion Language Models (DLMs) promise parallel generation and bidirectional context, yet they underperform autoregressive (AR) models in both likelihood modeling and generated text quality. We identify that this performance gap arises…

Diffusion-based large language models (dLLMs) rely on bidirectional attention, which prevents lossless KV caching and requires a full forward pass at every denoising step. Existing approximate KV caching methods reduce this cost by…

Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Context compression techniques can reduce these costs, but the most effective approaches…

The most common training pipeline for large language models includes pretraining, finetuning and aligning phases, with their respective resulting models, such as the pretrained model and the finetuned model. Finetuned and aligned models…

To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this method first drafts…

Learning token embeddings based on token co-occurrence statistics has proven effective for both pre-training and fine-tuning in natural language processing. However, recent studies have pointed out that the distribution of learned…

Adapting pre-trained deep learning models to customized tasks has become a popular choice for developers to cope with limited computational resources and data volume. More specifically, probing--training a downstream head on a pre-trained…

Learning, prediction, and compression are intimately connected: a model that accurately predicts the next symbol in a sequence can be coupled with a source coder to compress that sequence near its information-theoretic limit. When tokenized…

Diffusion models have demonstrated strong potential in language modeling, offering various advantages over traditional autoregressive approaches. Their ability to generate and revise entire responses in parallel enables faster generation…

Speculative decoding has emerged as a popular method to accelerate the inference of Large Language Models (LLMs) while retaining their superior text generation performance. Previous methods either adopt a fixed speculative decoding…