Related papers: Universal YOCO for Efficient Depth Scaling
Inference-time computation is a critical yet challenging paradigm for enhancing the reasoning performance of large language models (LLMs). While existing strategies improve reasoning stability and consistency, they suffer from notable…
Over the past years, YOLOs have emerged as the predominant paradigm in the field of real-time object detection owing to their effective balance between computational cost and detection performance. Researchers have explored the…
This paper tackles the memory hurdle of processing long context sequences in Large Language Models (LLMs), by presenting a novel approach, Dropping In Convolutions for Long Context Compression (LoCoCo). LoCoCo employs only a fixed-size…
The processing of omnidirectional 360-degree images poses significant challenges for object detection due to inherent spatial distortions, wide fields of view, and ultra-high-resolution inputs. Conventional detectors such as YOLO are…
Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the…
Inference-time scaling has emerged as a powerful way to improve large language model (LLM) performance by generating multiple candidate responses and selecting among them. However, existing work on dynamic allocation for test-time compute…
Transformers process tokens in parallel but are temporally shallow: at position $t$, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer…
Large Language Models (LLMs) for complex reasoning is often hindered by high computational costs and latency, while resource-efficient Small Language Models (SLMs) typically lack the necessary reasoning capacity. Existing collaborative…
DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs). While recent methods have attempted to replicate R1's reasoning capabilities in multimodal settings, they face limitations, including inconsistencies…
Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value (KV) cache during…
Domain-specific large language models (LLMs), typically developed by fine-tuning a pre-trained general-purpose LLM on specialized datasets, represent a significant advancement in applied AI. A common strategy in LLM fine-tuning is…
Although Transformers with fully connected self-attentions are powerful to model long-term dependencies, they are struggling to scale to long texts with thousands of words in language modeling. One of the solutions is to equip the model…
Transformers evaluated in a single, fixed-depth pass are provably limited in expressive power to the constant-depth circuit class TC0. Running a Transformer autoregressively removes that ceiling -- first in next-token prediction and, more…
Recently, dynamic computation methods have shown notable acceleration for Large Language Models (LLMs) by skipping several layers of computations through elaborate heuristics or additional predictors. However, in the decoding process of…
The growing demand for on-device large language model (LLM) inference highlights the need for efficient mobile edge computing (MEC) solutions, especially in resource-constrained settings. Speculative decoding offers a promising solution by…
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…
Recently, sharing key-value (KV) cache across layers has been found effective in efficient inference of large language models (LLMs). To systematically investigate different techniques of cross-layer KV sharing, we propose a unified…
While large language models (LLMs) have shown strong performance in math and logic reasoning, their ability to handle combinatorial optimization (CO) -- searching high-dimensional solution spaces under hard constraints -- remains…
The rapid development of the Transformer-based Large Language Models (LLMs) in recent years has been closely linked to their ever-growing and already enormous sizes. Many LLMs contain hundreds of billions of parameters and require dedicated…
Generative large language models (LLMs) have garnered significant attention due to their exceptional capabilities in various AI tasks. Traditionally deployed in cloud datacenters, LLMs are now increasingly moving towards more accessible…