相关论文: LaPA$^2$: Length-Aware Prefix and Prompt Attention…

Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes $T$ times longer sequence than the latter under the current attention of quadratic complexity $(T^2N^2)$. The existing…

Column Type Annotation (CTA) is a fundamental step towards enabling schema alignment and semantic understanding of tabular data. Existing encoder-only language models achieve high accuracy when fine-tuned on labeled columns, but their…

Parameter-Efficient Fine-Tuning (PEFT) has become the standard for customising Foundation Models (FMs) to user-specific downstream tasks. However, typical PEFT methods require storing multiple task-specific adapters, creating scalability…

Prompt-tuning is an emerging strategy to adapt large language models (LLM) to downstream tasks by learning a (soft-)prompt parameter from data. Despite its success in LLMs, there is limited theoretical understanding of the power of…

In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression,…

Random-feature-based attention (RFA) is an efficient approximation of softmax attention with linear runtime and space complexity. However, the approximation gap between RFA and conventional softmax attention is not well studied. Built upon…

Prefilling computational costs pose a significant bottleneck for Large Language Models (LLMs) and Large Multimodal Models (LMMs) in long-context settings. While token pruning reduces sequence length, prior methods rely on heuristics that…

Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on long-context data can help but is expensive due to the quadratic scaling of Attention. We…

Large reasoning models have achieved remarkable performance through extended chain-of-thought sequences, yet this computational freedom leads to excessive token generation even for simple problems. We present Length-Adaptive Policy…

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks. However, diffusion models often struggle to produce images that accurately reflect the intended…

We present LLaMA-Adapter, a lightweight adaption method to efficiently fine-tune LLaMA into an instruction-following model. Using 52K self-instruct demonstrations, LLaMA-Adapter only introduces 1.2M learnable parameters upon the frozen…

Recent text-to-image (T2I) diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, they fail to semantically align the generated images with the prompts due to their limited…

Existing approaches typically rely on fixed length penalties, but such penalties are hard to tune and fail to adapt to the evolving reasoning abilities of LLMs, leading to suboptimal trade-offs between accuracy and conciseness. To address…

Generating rare compositional concepts in text-to-image synthesis remains a challenge for diffusion models, particularly for attributes that are uncommon in the training data. While recent approaches, such as R2F, address this challenge by…

Speaker recognition models face challenges in multi-lingual settings due to the entanglement of linguistic information within speaker embeddings. The overlap between vocal traits such as accent, vocal anatomy, and a language's phonetic…

While RAG demonstrates remarkable capabilities in LLM applications, its effectiveness is hindered by the ever-increasing length of retrieved contexts, which introduces information redundancy and substantial computational overhead. Existing…

Large Language Models (LLMs) have made significant strides in natural language processing and generation, yet their ability to handle long-context input remains constrained by the quadratic complexity of attention computation and…

State-of-the-art text-to-image diffusion models can produce impressive visuals but may memorize and reproduce training images, creating copyright and privacy risks. Existing prompt perturbations applied at inference time, such as random…

Paraphrase generation strives to generate high-quality and diverse expressions of a given text, a domain where diffusion models excel. Though SOTA diffusion generation reconciles generation quality and diversity, textual diffusion suffers…