相关论文: DeCoVec: Building Decoding Space based Task Vector…

Large Language Models (LLMs) have become widely used for Software Engineering (SE) tasks, spanning from function-level code generation to complex repository-level workflows. However, the high latency of autoregressive inference remains a…

Large Pre-trained Transformers exhibit an intriguing capacity for in-context learning. Without gradient updates, these models can rapidly construct new predictors from demonstrations presented in the inputs. Recent works promote this…

Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that the information needed to…

Vision-language (VL) pre-training has recently gained much attention for its transferability and flexibility in novel concepts (e.g., cross-modality transfer) across various visual tasks. However, VL-driven segmentation has been…

In-context learning, which offers substantial advantages over fine-tuning, is predominantly observed in decoder-only models, while encoder-decoder (i.e., seq2seq) models excel in methods that rely on weight updates. Recently, a few studies…

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…

Recent advances in pre-trained Vision Language Models (VLM) have shown promising potential for effectively adapting to downstream tasks through prompt learning, without the need for additional annotated paired datasets. To supplement the…

Large Vision-Language Models (LVLMs) have advanced rapidly by aligning visual patches with the text embedding space, but a fixed visual-token budget forces images to be resized to a uniform pretraining resolution, often erasing fine-grained…

Multimodal Large Language Models (MLLMs) have demonstrated strong performance across a wide range of vision-language tasks, yet their internal processing dynamics remain underexplored. In this work, we introduce a probing framework to…

While Vision-Language Models (VLMs) excel in many areas, they struggle with complex spatial reasoning, which requires problem decomposition and strategic tool use. Fine-tuning smaller, more deployable models offers an efficient path to…

Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigates this through a guess-and-verify strategy, but existing training-free variants face…

Building state-of-the-art Vision-Language Models (VLMs) with strong captioning capabilities typically necessitates training on billions of high-quality image-text pairs, requiring millions of GPU hours. This paper introduces the…

Steering has emerged as a promising approach in controlling large language models (LLMs) without modifying model parameters. However, most existing steering methods rely on large-scale datasets to learn clear behavioral information, which…

With the continuous expansion of Large Language Models (LLMs) and advances in reinforcement learning, LLMs have demonstrated exceptional reasoning capabilities, enabling them to address a wide range of complex problems. Inspired by these…

Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…

Large Vision Language Models (LVLMs) achieve strong performance across multimodal tasks by integrating visual perception with language understanding. However, how vision information contributes to the model's decoding process remains…

Large language models (LLMs) have become increasingly prominent in academia and industry due to their remarkable performance in diverse applications. As these models evolve with increasing parameters, they excel in tasks like sentiment…

In the paradigm of AI-generated content (AIGC), there has been increasing attention to transferring knowledge from pre-trained text-to-image (T2I) models to text-to-video (T2V) generation. Despite their effectiveness, these frameworks face…

With Transformers achieving outstanding performance on individual remote sensing (RS) tasks, we are now approaching the realization of a unified model that excels across multiple tasks through multi-task learning (MTL). Compared to…

A variety of recent methods guide large language model outputs via the inference-time addition of steering vectors to residual-stream or attention-head representations. In contrast, we propose to inject steering vectors directly into the…