The softmax function is crucial in Transformer attention, which normalizes each row of the attention scores with summation to one, achieving superior performances over other alternative functions. However, the softmax function can face a gradient vanishing issue when some elements of the attention scores approach extreme values, such as probabilities close to one or zero. In this paper, we propose Self-Adjust Softmax (SA-Softmax) to address this issue by modifying $softmax(x)$ to $x \cdot softmax(x)$ and its normalized variant $\frac{(x - min(x_{\min},0))}{max(0,x_{max})-min(x_{min},0)} \cdot softmax(x)$. We theoretically show that SA-Softmax provides enhanced gradient properties compared to the vanilla softmax function. Moreover, SA-Softmax Attention can be seamlessly integrated into existing Transformer models to their attention mechanisms with minor adjustments. We conducted experiments to evaluate the empirical performance of Transformer models using SA-Softmax compared to the vanilla softmax function. These experiments, involving models with up to 2.7 billion parameters, are conducted across diverse datasets, language tasks, and positional encoding methods.

Efficiently handling long contexts is crucial for large language models (LLMs). While rotary position embeddings (RoPEs) enhance length generalization, effective length extrapolation remains challenging and often requires costly fine-tuning. In contrast, recent training-free approaches suffer from the attention sink phenomenon, leading to severe performance degradation. In this paper, we introduce ParallelComp, a novel training-free method for long-context extrapolation that extends LLMs' context length from 4K to 128K while maintaining high throughput and preserving perplexity, and integrates seamlessly with Flash Attention. Our analysis offers new insights into attention biases in parallel attention mechanisms and provides practical solutions to tackle these challenges. To mitigate the attention sink issue, we propose an attention calibration strategy that reduces biases, ensuring more stable long-range attention. Additionally, we introduce a chunk eviction strategy to efficiently manage ultra-long contexts on a single A100 80GB GPU. To further enhance efficiency, we propose a parallel KV cache eviction technique, which improves chunk throughput by 1.76x, thereby achieving a 23.50x acceleration in the prefilling stage with negligible performance loss due to attention calibration. Furthermore, ParallelComp achieves 91.17% of GPT-4's performance on long-context tasks using an 8B model trained on 8K-length context, outperforming powerful closed-source models such as Claude-2 and Kimi-Chat.

Detecting anomalies in temporal data has gained significant attention across various real-world applications, aiming to identify unusual events and mitigate potential hazards. In practice, situations often involve a mix of segment-level labels (detected abnormal events with segments of time points) and unlabeled data (undetected events), while the ideal algorithmic outcome should be point-level predictions. Therefore, the huge label information gap between training data and targets makes the task challenging. In this study, we formulate the above imperfect information as noisy labels and propose NRdetector, a noise-resilient framework that incorporates confidence-based sample selection, robust segment-level learning, and data-centric point-level detection for multivariate time series anomaly detection. Particularly, to bridge the information gap between noisy segment-level labels and missing point-level labels, we develop a novel loss function that can effectively mitigate the label noise and consider the temporal features. It encourages the smoothness of consecutive points and the separability of points from segments with different labels. Extensive experiments on real-world multivariate time series datasets with 11 different evaluation metrics demonstrate that NRdetector consistently achieves robust results across multiple real-world datasets, outperforming various baselines adapted to operate in our setting.

Long context understanding remains challenging for large language models due to their limited context windows. This paper introduces Long Input Fine-Tuning (LIFT) for long context modeling, a novel framework that enhances LLM performance on long-context tasks by adapting model parameters to the context at test time. LIFT enables efficient processing of lengthy inputs without the computational burden of offline long-context adaptation, and can improve the long-context capabilities of arbitrary short-context models. The framework is further enhanced by integrating in-context learning and pre-LIFT supervised fine-tuning. The combination of in-context learning and LIFT enables short-context models like Llama 3 to handle arbitrarily long contexts and consistently improves their performance on popular long-context benchmarks like LooGLE and LongBench. We also provide a comprehensive analysis of the strengths and limitations of LIFT on long context understanding, offering valuable directions for future research. Large Language Models (LLMs), such as GPT-4 (Achiam et al., 2023), have revolutionized the field of natural language processing, driving breakthroughs in text generation and significant advancements in tasks like translation, summarization, and conversation. Lengthy sequences, which can span up to millions of tokens, are common in real-world applications including long books (Kočiskỳ et al., 2018), high-resolution videos (Wu et al., 2024; Tapaswi et al., 2016), and audio signals (Yang et al., 2024). Extending the context window allows models to capture dependencies across larger text spans and improve coherence, understanding, and accuracy in tasks that require reasoning over extended inputs.

Autoregressive modeling has been a huge success in the field of natural language processing (NLP). Recently, autoregressive models have emerged as a significant area of focus in computer vision, where they excel in producing high-quality visual content. Autoregressive models in NLP typically operate on subword tokens. However, the representation strategy in computer vision can vary in different levels, \textit{i.e.}, pixel-level, token-level, or scale-level, reflecting the diverse and hierarchical nature of visual data compared to the sequential structure of language. This survey comprehensively examines the literature on autoregressive models applied to vision. To improve readability for researchers from diverse research backgrounds, we start with preliminary sequence representation and modeling in vision. Next, we divide the fundamental frameworks of visual autoregressive models into three general sub-categories, including pixel-based, token-based, and scale-based models based on the strategy of representation. We then explore the interconnections between autoregressive models and other generative models. Furthermore, we present a multi-faceted categorization of autoregressive models in computer vision, including image generation, video generation, 3D generation, and multi-modal generation. We also elaborate on their applications in diverse domains, including emerging domains such as embodied AI and 3D medical AI, with about 250 related references. Finally, we highlight the current challenges to autoregressive models in vision with suggestions about potential research directions. We have also set up a Github repository to organize the papers included in this survey at: \url{https://github.com/ChaofanTao/Autoregressive-Models-in-Vision-Survey}.

Autoformalization aims to convert informal mathematical proofs into machine-verifiable formats, bridging the gap between natural and formal languages. However, ensuring semantic alignment between the informal and formalized statements remains challenging. Existing approaches heavily rely on manual verification, hindering scalability. To address this, we introduce \textsc{FormalAlign}, the first automated framework designed for evaluating the alignment between natural and formal languages in autoformalization. \textsc{FormalAlign} trains on both the autoformalization sequence generation task and the representational alignment between input and output, employing a dual loss that combines a pair of mutually enhancing autoformalization and alignment tasks. Evaluated across four benchmarks augmented by our proposed misalignment strategies, \textsc{FormalAlign} demonstrates superior performance. In our experiments, \textsc{FormalAlign} outperforms GPT-4, achieving an Alignment-Selection Score 11.58\% higher on \forml-Basic (99.21\% vs. 88.91\%) and 3.19\% higher on MiniF2F-Valid (66.39\% vs. 64.34\%). This effective alignment evaluation significantly reduces the need for manual verification. Both the dataset and code can be accessed via~\url{https://github.com/rookie-joe/FormalAlign}.

The attention mechanism is a fundamental component of the Transformer model, contributing to interactions among distinct tokens, in contrast to earlier feedforward neural networks. In general, the attention scores are determined simply by the key-query products. However, this work's occasional trial (combining DAPE and NoPE) of including additional MLPs on attention scores without position encoding indicates that the classical key-query multiplication may limit the performance of Transformers. In this work, we conceptualize attention as a feature map and apply the convolution operator (for neighboring attention scores across different heads) to mimic the processing methods in computer vision. Specifically, the main contribution of this paper is identifying and interpreting the Transformer length extrapolation problem as a result of the limited expressiveness of the naive query and key dot product, and we successfully translate the length extrapolation issue into a well-understood feature map processing problem. The novel insight, which can be adapted to various attention-related models, reveals that the current Transformer architecture has the potential for further evolution. Extensive experiments demonstrate that treating attention as a feature map and applying convolution as a processing method significantly enhances Transformer performance. However, the quadratic cost of the key-query multiplication for processing a sequence raised much concern about the modern architecture of Transformers especially for long context inputs.

Deploying large language models (LLMs) is challenging due to their high memory and computational demands, especially during long-context inference. While keyvalue (KV) caching accelerates inference by reusing previously computed keys and values, it also introduces significant memory overhead. Existing KV cache compression methods--such as eviction and merging--typically compress the KV cache after it is generated and overlook the hidden states, failing to improve the speed of the prefilling stage. Additionally, applying a uniform compression rate across different attention heads can harm crucial retrieval heads in needle-in-ahaystack tasks due to excessive compression. In this paper, we propose UNComp, an uncertainty-aware compression scheme that leverages matrix entropy to estimate model uncertainty across layers and heads at the token sequence level. By grouping layers and heads based on their uncertainty, UNComp adaptively compresses both the hidden states and the KV cache. Our method achieves a 1.6 speedup in the prefilling stage and reduces the KV cache to 4.74% of its original size, resulting in a 6.4 increase in throughput and a 1.4 speedup in inference with only a 1.41% performance loss. Remarkably, in needle-in-a-haystack tasks, UNComp outperforms the full-size KV cache even when compressed to 9.38% of its original size. Our approach offers an efficient, training-free Grouped-Query Attention paradigm that can be seamlessly integrated into existing KV cache schemes. The proliferation of large language models (LLMs) has led to unprecedented advancements in natural language processing (Achiam et al., 2023; Kaplan et al., 2020), enabling capabilities ranging from simple text generation to complex reasoning and dialogue.

We present UncertaintyRAG, a novel approach for long-context Retrieval-Augmented Generation (RAG) that utilizes Signal-to-Noise Ratio (SNR)-based span uncertainty to estimate similarity between text chunks. This span uncertainty enhances model calibration, improving robustness and mitigating semantic inconsistencies introduced by random chunking. Leveraging this insight, we propose an efficient unsupervised learning technique to train the retrieval model, alongside an effective data sampling and scaling strategy. UncertaintyRAG outperforms baselines by 2.03% on LLaMA-2-7B, achieving state-of-the-art results while using only 4% of the training data compared to other advanced open-source retrieval models under distribution shift settings. Our method demonstrates strong calibration through span uncertainty, leading to improved generalization and robustness in long-context RAG tasks. Additionally, UncertaintyRAG provides a lightweight retrieval model that can be integrated into any large language model with varying context window lengths, without the need for fine-tuning, showcasing the flexibility of our approach.

With the increasing application of automated robotic digestive endoscopy (RDE), ensuring safe and efficient navigation in the unstructured and narrow digestive tract has become a critical challenge. Existing automated reinforcement learning navigation algorithms, often result in potentially risky collisions due to the absence of essential human intervention, which significantly limits the safety and effectiveness of RDE in actual clinical practice. To address this limitation, we proposed a Human Intervention (HI)-based Proximal Policy Optimization (PPO) framework, dubbed HI-PPO, which incorporates expert knowledge to enhance RDE's safety. Specifically, we introduce an Enhanced Exploration Mechanism (EEM) to address the low exploration efficiency of the standard PPO. Additionally, a reward-penalty adjustment (RPA) is implemented to penalize unsafe actions during initial interventions. Furthermore, Behavior Cloning Similarity (BCS) is included as an auxiliary objective to ensure the agent emulates expert actions. Comparative experiments conducted in a simulated platform across various anatomical colon segments demonstrate that our model effectively and safely guides RDE.