Related papers: Hierarchical Token Prepending: Enhancing Informati…

The deployment of pre-trained models (PTMs) has greatly advanced the field of continual learning (CL), enabling positive knowledge transfer and resilience to catastrophic forgetting. To sustain these advantages for sequentially arriving…

Transformer-based LLMs achieve strong results on many language tasks; however, long inputs remain challenging because context windows are finite, and prefill latency and memory grow rapidly with prompt length. Flat token-stream processing…

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…

Large Vision-Language Models (LVLMs) have shown impressive performance across multi-modal tasks by encoding images into thousands of tokens. However, the large number of image tokens results in significant computational overhead, and the…

Large Language Models (LLMs) have become a cornerstone in Natural Language Processing (NLP), achieving impressive performance in text generation. Their token-level representations capture rich, human-aligned semantics. However, pooling…

As LLMs scale to multi-million-token KV histories, real-time autoregressive decoding under tight Token-to-Token Latency (TTL) constraints faces growing pressure. Two core bottlenecks dominate: accessing Feed-Forward Network (FFN) weights…

Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-time deployment due to the high computational cost of…

To alleviate the data scarcity problem in training question answering systems, recent works propose additional intermediate pre-training for dense passage retrieval (DPR). However, there still remains a large discrepancy between the…

Hierarchical text classification (HTC) assigns documents to multiple levels of a pre-defined taxonomy. Automated patent subject classification represents one of the hardest HTC scenarios because of domain knowledge difficulty and a huge…

Autoregressive decoding in language models is inherently slow, generating only one token per forward pass. We propose Parallel Token Prediction (PTP), a general-purpose framework for predicting multiple tokens in a single model call. PTP…

With the rapid proliferation of textual data, predicting long texts has emerged as a significant challenge in the domain of natural language processing. Traditional text prediction methods encounter substantial difficulties when grappling…

Large language models (LLMs) have shown promising efficacy across various tasks, becoming powerful tools in numerous aspects of human life. However, Transformer-based LLMs suffer a performance degradation when modeling long-term contexts…

Vision-Language Models (VLMs) encode images and videos into abundant tokens, which contain substantial redundancy and computation cost. While visual token pruning mitigates the issue, most existing methods lack insight into the intrinsic…

Multimedia or spoken content presents more attractive information than plain text content, but the former is more difficult to display on a screen and be selected by a user. As a result, accessing large collections of the former is much…

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.…

Large language models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per query leads to over-computation on easy inputs and…

The growing demand for large language models (LLMs) requires serving systems to handle many concurrent requests with diverse service level objectives (SLOs). This exacerbates head-of-line (HoL) blocking during the compute-intensive prefill…

Despite recent advancements in large language models (LLMs), their performance on complex reasoning problems requiring multi-step thinking and combining various skills is still limited. To address this, we propose a novel framework HDFlow…

Interleaved texts, where posts belonging to different threads occur in one sequence, are a common occurrence, e.g., online chat conversations. To quickly obtain an overview of such texts, existing systems first disentangle the posts by…

Next-token prediction (NTP) has driven the success of large language models (LLMs), but it struggles with long-horizon reasoning, planning, and creative writing, with these limitations largely attributed to teacher-forced training.…