11 accepted papers
The computational cost of Multimodal Large Language Models (MLLMs), driven by the quadratic complexity of processing vision tokens, remains a significant barrier to their widespread adoption. While progressive vision token pruning is a promising solution, we find that its full potential has been unr…
Standard Large Language Models (LLMs) operate on a ''read-then-generate'' paradigm, incurring avoidable latency and computational redundancy. Recently, streaming LLMs have attempted to overcome these bottlenecks by allowing input and output to unfold synchronously. However, this introduces a critica…
Large-scale models are at the forefront of time series (TS) forecasting, dominated by two paradigms: fine-tuning text-based Large Language Models for TS (LLM4TS) and training Time Series Foundation Models (TSFMs) from scratch. Both approaches share a foundational assumption that scaling up model cap…
Large language models (LLMs) have demonstrated remarkable capabilities in chain of thought (CoT) reasoning. However, the current LLM reasoning paradigm initiates thinking only after the entire input is available, which introduces unnecessary latency and weakens attention to earlier information in dy…
Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities in Chain-of-Thought (CoT) reasoning. However, existing LVLM reasoning paradigms only begin reasoning after the entire video becomes available, introducing unnecessary latency and diminishing attention to early visual cues
One-stream Transformer-based trackers achieve advanced performance in visual object tracking suffer from significant computational overhead that hinders real-time deployment. While token pruning offers a path to efficiency, a critical limitation persists: no existing work performs pruning jointly ac
Multimodal large language models (MLLMs) project visual tokens into the embedding space of language models, yet the internal structuring and processing of visual semantics remain poorly understood. In this work, we introduce a two-fold analytical framework featuring a novel probing tool, EmbedLens,
Conditional entropy models effectively leverage spatio-temporal contexts to reduce video redundancy. However, incorporating temporal context often introduces additional model complexity and increases computational cost. In parallel, many existing spatial context models lack explicit modeling the ord…
Large Language Models (LLMs) are primarily designed for batch processing. Existing methods for adapting LLMs to streaming rely either on expensive re-encoding or specialized architectures with limited scalability. This work identifies three key mismatches in adapting batch-oriented LLMs to streaming…
Large language models (LLMs) achieve remarkable performance across tasks but incur substantial computational costs due to their deep, multi-layered architectures. Layer pruning has emerged as a strategy to alleviate these inefficiencies, but conventional static pruning methods overlook two critical…
Multimodal Large Language Models (MLLMs) have achieved strong performance across vision-language tasks, but suffer from significant computational overhead due to the quadratic growth of attention computations with the number of multimodal tokens. Though efforts have been made to prune tokens in MLLM