论文检索

Deep Learning · Attention Mechanisms

Yui Oka, Itsumi Saito, Kyosuke Nishida, Kuniko Saito

Rotary Position Embeddings (RoPE) are widely adopted in LLMs, and it is commonly believed that larger base frequencies $\theta$ yield better long-context performance. In this paper, we show that a high-norm RoPE dimension, referred to as the “frequency band,” consistently emerges across multiple models, and we focus on this band to reveal the trade-offs inherent in RoPE. We find that replacing the RoPE dimensions below the frequency band with NoPE during inference has little effect on performance, indicating that these lower-frequency dimensions are only weakly utilized. We further find that the location of the frequency band depends on the RoPE base $\theta$ and the training sequence length. Moreover, the band forms early during pre-training and persists even after context extension via position interpolation. Notably, we show that setting $\theta$ to the training length shifts the band toward lower frequencies and improves extrapolation, whereas increasing $\theta$ enhances interpolation but reduces extrapolation, revealing a clear trade-off between interpolation and extrapolation. We believe this work is a step toward a sharper understanding of positional embeddings in LLMs, with falsifiable diagnostics and practical guidance for choosing $\theta$ that support scaling to longer contexts.

Deep Learning · Attention Mechanisms

Ran Yan, YOUHE JIANG, Zhuoming Chen, Haohui Mai, Beidi Chen, Binhang Yuan

Recent advance in sparse attention mechanisms has demonstrated strong potential for reducing the computational cost of long-context training and inference in large language models (LLMs). Native Sparse Attention (NSA), one state-of-the-art approach, introduces natively trainable, hardware-aligned sparse attention that delivers substantial system-level performance boost while maintaining accuracy comparable to full attention. However, the kernel implementation of NSA forces a loop order that is only efficient with a relatively large number of query heads in each Grouped Query Attention (GQA) group, whereas existing LLMs widely adopt much smaller number of query heads in each GQA group --- such an inconsistency significantly limits the applicability of this sparse algorithmic advance. In this work, we propose **F**lash **S**parse **A**ttention (**FSA**), an alternative kernel implementation that enables efficient NSA computation across a wide range of popular LLMs with varied smaller number of query heads in each GQA group on modern GPUs. Compared to vanilla NSA kernel implementation, our empirical evaluation demonstrates that FSA achieves (i) up to 3.5x and on average 1.6x kernel-level latency reduction, (ii) up to 1.25x and 1.09x on average end-to-end training speedup on state-of-the-art LLMs, and (iii) up to 1.36x and 1.11x on average for prefill-phase speedup in LLM generative inference.

Deep Learning · Attention Mechanisms

Yui Oka, Kentaro Hanafusa, Taku Hasegawa, Kyosuke Nishida, Kuniko Saito

Rotary Position Embeddings (RoPE) are widely used in Transformers to encode positional information in token representations, yet the internal frequency structure of RoPE remains poorly understood. Previous studies have reported conflicting findings on the roles of high- and low-frequency dimensions, offering empirical observations but no unifying explanation. In this paper, we present a systematic framework that bridges these disparate results. We introduce Frequency Entropy (FE), a metric that quantifies the effective utilization of each RoPE frequency dimension, and we provide an analysis of how RoPE’s sinusoidal components contribute to model representations on a per-dimension basis. Based on an analysis of the Llama-4 model, which incorporates both RoPE and NoPE layers, we find that the periodicity captured by FE appears in RoPE layers but not in NoPE layers. Furthermore, FE identifies dimensions in which energy concentrates under RoPE. These characteristics are observed across the spectrum rather than being confined to specific dimensions. Moreover, attenuating extreme-entropy dimensions at inference yields downstream accuracy that is statistically indistinguishable from the baseline, with modest perplexity improvements on average, suggesting that such dimensions are often redundant. Overall, FE provides a simple, general diagnostic for RoPE with implications for analysis and design.

General Machine Learning · Representation Learning

Henry Conklin, Tom Hosking, Yi-Chern Tan, Jonathan Cohen, Sarah-Jane Leslie, Thomas L. Griffiths, Max Bartolo, Seraphina Goldfarb-Tarrant

Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to learning in humans. We argue LLMs are best seen as an instance of lossy compression, where over training they learn by retaining only information in their training data relevant to their objective(s). We show pre-training results in models that are optimally compressed for next-sequence prediction, approaching the Information Bottleneck bound on compression. Across an array of open weights models, each compresses differently, likely due to differences in the data and training recipes used. However even across different families of LLMs the optimality of a model's compression, and the information present in it, can predict downstream performance on across a wide array of benchmarks, letting us directly link representational structure to actionable insights about model performance. In the general case the work presented here offers a unified Information-Theoretic framing for how these models learn that is deployable at scale.

Deep Learning · Attention Mechanisms

Liang Zhang, Yu Zhao, Longyue Wang, Tianqi Shi, Weihua Luo, Kaifu Zhang, Jinsong Su

While Long Chain-of-Thought (CoT) reasoning significantly improves Large Language Models (LLMs) performance on complex reasoning tasks, the substantial computational and memory costs of generating long CoT sequences limit their efficiency and practicality. Existing studies usually enhance the reasoning efficiency of LLMs by compressing CoT sequences. However, this approach conflicts with test‑time scaling, limiting the reasoning capacity of LLMs. In this paper, we propose an efficient reasoning framework that models the reasoning process of LLMs as a state‑transition process. Specifically, we first apply a linear attention mechanism to estimate the LLM’s reasoning state, which records the historical reasoning information from previous reasoning steps. Then, based on the query prompt and the reasoning state, the LLM can efficiently perform the current reasoning step and update the state. With the linear attention, each token in the current reasoning step can directly retrieve relevant historical reasoning information from the reasoning state, without explicitly attending to tokens in previous reasoning steps. In this way, the computational complexity of attention is reduced from quadratic to linear, significantly improving the reasoning efficiency of LLMs. In addition, we propose a state-based reasoning strategy to mitigate the over-thinking issue caused by noisy reasoning steps. Extensive experiments across multiple datasets and model sizes demonstrate that our framework not only improves the reasoning efficiency of LLMs but also enhances their reasoning performance.

Deep Learning · Algorithms

Zhixin Li, Yuheng Jia, Guanliang Chen, Hui LIU, Junhui Hou

As an important branch of unsupervised learning, deep clustering has seen substantial progress in recent years. However, the majority of current deep clustering methods operate under the assumption of balanced or near-balanced cluster distributions. This assumption contradicts the common long-tailed class distributions in real-world data, leading to severe performance degradation in deep clustering. Although many long-tailed learning methods have been proposed, these approaches typically rely on label information to differentiate treatment across different classes, which renders them inapplicable to deep clustering scenarios. How to re-weight the training of deep clustering models in an unsupervised setting remains an open challenge. To address this, we propose a mini-cluster guided long-tailed deep clustering method, termed MiniClustering. We introduce a specialized clustering head that divide data into much more clusters than the target number of clusters. These predicted clusters are referred to as mini-clusters. The mini-cluster-level predictions serve as the guide for estimating the appropriate weights for classes with varying degrees of long-tailedness. The weights are then incorporated to re-weight the self-training loss in model training. In this way, we can mitigate model bias by re-weighting gradients from different classes. We evaluate our method on multiple benchmark datasets with different imbalance ratios to demonstrate its effectiveness. Further, our method can be readily applied to the downstream of existing unsupervised representation learning frameworks for long-tailed deep clustering. It can also adapt label-dependent long-tailed learning methods to unsupervised clustering tasks by leveraging the estimated weights. The code is available at https://github.com/LZX-001/MiniClustering.

Applications · Neuroscience, Cognitive Science

Max Wolff, Thomas Klein, Evgenia Rusak, Felix Wichmann, Wieland Brendel

Despite their impressive performance on computer vision benchmarks, Deep Neural Networks (DNNs) still fall short of adequately modeling human visual behavior, as measured by error consistency and shape bias. Recent work hypothesized that behavioral alignment can be drastically improved through generative - rather than discriminative - classifiers, with far-reaching implications for models of human vision. Here, we instead show that the increased alignment of generative models can be largely explained by a seemingly innocuous resizing operation in the generative model which effectively acts as a low-pass filter. In a series of controlled experiments, we show that removing high-frequency spatial information from discriminative models like CLIP drastically increases their behavioral alignment. Simply blurring images at test-time - rather than training on blurred images - achieves a new state-of-the-art score on the model-vs-human benchmark, halving the current alignment gap between DNNs and human observers. Furthermore, low-pass filters are likely optimal, which we demonstrate by directly optimizing filters for alignment. To contextualize the performance of optimal filters, we compute the frontier of all possible pareto-optimal solutions to the benchmark, which was formerly unknown. We explain our findings by observing that the frequency spectrum of optimal Gaussian filters roughly matches the spectrum of band-pass filters implemented by the human visual system. We show that the contrast sensitivity function, describing the inverse of the contrast threshold required for humans to detect a sinusoidal grating as a function of spatiotemporal frequency, is approximated well by Gaussian filters of a specific width.

Deep Learning · Algorithms

Xiaojing Qi, Lun Du, Xinyuan Zhang, Lanning Wei, Tao Jin, Da Zheng

The utilization of large language models (LLMs) has become increasingly widespread, and has attracted considerable attention. Although the emergence of discrete diffusion large language models (dLLMs) mitigates the inference latency inherent in autoregressive LLM decoding, its computational overhead remains substantial. To address this challenge, we propose Hierarchy-dLLM, a hierarchical decoding framework inspired by the divide-and-conquer principle. Our method recursively partitions masked spans into smaller sub-decoding areas and decodes tokens according to their confidence, which substantially increases the number of tokens generated per forward pass and improves information utilization. Extensive experiments conducted on multiple benchmarks demonstrate that Hierarchy-dLLM achieves accuracy comparable to or even surpassing existing baselines. Meanwhile, it is up to 17× faster than vanilla decoding and about 1.5× faster than the Fast-dLLM. These results establish hierarchical decoding as a practical solution for efficient dLLMs inference.

Deep Learning · Algorithms

Xiangxiang Chu, Hailang Huang, Xiao Zhang, Fei Wei, Yong Wang

Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and propose a minimalist RL approach termed Group Policy Gradient (GPG). Unlike conventional methods, GPG directly optimizes the original RL objective, thus obviating the need for surrogate loss functions. By eliminating the critic and reference models, avoiding KL divergence constraints, and addressing the advantage and gradient estimation bias, our approach significantly simplifies the training process compared to Group Relative Policy Optimization (GRPO). Our approach achieves superior performance without relying on auxiliary techniques or adjustments. As illustrated in Figure 1, extensive experiments demonstrate that our method not only reduces computational costs but also consistently outperforms GRPO across various unimodal and multimodal tasks.

Applications · Language, Speech and Dialog

Sitong Cheng, Bianweizhen, Xinsheng Wang, Ruibin Yuan, Jianyi Chen, Shunshun Yin, Yike Guo, Wei Xue

The ultimate goal of expressive speech-to-speech translation (S2ST) is to accurately translate spoken content while preserving the speaker identity and emotional style. However, progress in this field is largely hindered by three key challenges: the scarcity of paired speech data that retains expressive styles, the complexity of multi-stage processing pipelines, and the limited transfer of translation capabilities from large language models (LLMs). In this work, we address these challenges by introducing UniSS, a novel single-stage framework for expressive S2ST. Our approach features carefully designed speech semantic and style modeling, enabling seamless integration with existing text-based LLM frameworks to develop a unified text-speech language model. To transfer translation capabilities from text to speech, we propose a cross-modal chain-of-thought prompting process that progressively aligns audio semantics with text and ensures style preservation in the decoded results. Furthermore, we construct and release a large-scale, high-quality expressive S2ST dataset, UniST, comprising 44.8k hours of data. Experimental results show that UniSS significantly outperforms previous methods in translation fidelity and speech quality while preserving voice, emotion, and duration consistency. Our work establishes a simpler and more effective paradigm for building the next generation of expressive S2ST systems. Audio samples are available at https://cmots.github.io/uniss-demo/.

Deep Learning · Algorithms

Jonathan Cook, Silvia Sapora, Arash Ahmadian, Akbir Khan, Tim Rocktaeschel, Jakob Foerster, Laura Ruis

Large language models (LLMs) are typically trained to acquire behaviours from demonstrations or experience, yet much of their training data is declarative: instructions, rules, and descriptions that specify behaviours without showing how to execute them. We introduce **Programming by Backprop (PBB)**: a training regime that enables LLMs to acquire *procedural* knowledge (i.e., reusable behaviours) from *declarative* instructions encountered during training. With PBB, instructions in training data provide an opportunity to "program" specific behaviours into model weights. The core principle underpinning PBB is the separation of learning how instructions map to behaviour from internalising new instructions. We devise two distinct PBB curricula that leverage this principle. Through controlled experiments across two domains (algorithmic execution from Python source code and text generation from context-free grammars), we demonstrate the benefit of these curricula over training on a homogeneous data mixture. Crucially, PBB is highly sample efficient, with *a single instruction substituting for up to 100 execution examples*. Though execution of instructions in training data remains less reliable than when instructions are given in-context, our results demonstrate that procedural knowledge can be noisily `programmed' into LLMs through PBB, with important implications for data curation and safety.

Deep Learning · Algorithms

Haiyu Wang, Yutong Wang, Jack Jiang, Sai Qian Zhang

Singular Value Decomposition (SVD) has become an important technique for reducing the computational burden of Vision Language Models (VLMs), which play a central role in tasks such as image captioning and visual question answering. Although multiple prior works have proposed efficient SVD variants to enable low-rank operations, we find that in practice it remains difficult to achieve substantial latency reduction during model execution. To address this limitation, we introduce a new computational pattern and apply SVD at a finer granularity, enabling real and measurable improvements in execution latency. Furthermore, recognizing that weight elements differ in their relative importance, we adaptively allocate relative importance to each element during SVD process to better preserve accuracy, then extend this framework with quantization applied to both weights and activations, resulting in a highly efficient VLM. Collectively, we introduce Weighted SVD (WSVD), which outperforms other approaches by achieving over $1.8\times$ decoding speedup while preserving accuracy. We open source our code at: https://github.com/SAI-Lab-NYU/WSVD.

Deep Learning · Algorithms

Song Bian, Tao Yu, Shivaram Venkataraman, Youngsuk Park

Scaling the number of parameters and the size of training data has proven to be an effective strategy for improving large language model (LLM) performance. Yet, as these models grow increasingly powerful and widely deployed, the cost of inference has become a pressing concern. Despite its importance, the trade-off between model accuracy and inference efficiency remains underexplored. In this work, we examine how key architectural factors, hidden size, the allocation of parameters between MLP and attention (mlp-to-attention ratio), and grouped-query attention (GQA), influence both inference cost and accuracy. We introduce a conditional scaling law that augments the Chinchilla framework with architectural information, along with a search framework for identifying architectures that are simultaneously inference-efficient and accurate. To validate our approach, we train more than 200 models spanning 80M to 3B parameters and 8B to 100B training tokens, and fit the proposed conditional scaling law. Our results show that the conditional scaling law reliably predicts optimal architectural choices and that the resulting models outperform existing open-source baselines. Under the same training budget, optimized architectures achieve up to 2.1\% higher accuracy and 42\% greater inference throughput compared to LLaMA-3.2.

Deep Learning · Algorithms

YU CHENYUE, Lingao Xiao, Jinhong Deng, Ivor Tsang, Yang He

Large-scale image datasets are fundamental to deep learning, but their high storage demands pose challenges for deployment in resource-constrained environments. While existing approaches reduce dataset size by discarding samples, they often ignore the significant redundancy within each image -- particularly in the color space. To address this, we propose Dataset Color Quantization (DCQ), a unified framework that compresses visual datasets by reducing color-space redundancy while preserving information crucial for model training. DCQ achieves this by enforcing consistent palette representations across similar images, selectively retaining semantically important colors guided by model perception, and maintaining structural details necessary for effective feature learning. Extensive experiments across CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet-1K show that DCQ significantly improves training performance under aggressive compression, offering a scalable and robust solution for dataset-level storage reduction.

Computer Vision · Everything Else

Qingxuan Wu, Zhiyang Dou, chuan guo, Yiming Huang, Qiao Feng, Bing Zhou, Jian Wang, Lingjie Liu

Modeling human–human interactions from text remains challenging because it requires not only realistic individual dynamics but also precise, text-consistent spatiotemporal coupling between agents. Currently, progress is hindered by 1) limited two-person training data, inadequate to capture the diverse intricacies of two-person interactions; and 2) insufficiently fine-grained text-to-interaction modeling, where language conditioning collapses rich, structured prompts into a single sentence embedding. To address these limitations, we propose our Text2Interact framework, designed to generate realistic, text-aligned human–human interactions through a scalable high-fidelity interaction data synthesizer and an effective spatiotemporal coordination pipeline. First, we present InterCompose, a scalable synthesis-by-composition pipeline that aligns LLM-generated interaction descriptions with strong single-person motion priors. Given a prompt and a motion for an agent, InterCompose retrieves candidate single-person motions, trains a conditional reaction generator for another agent, and uses a neural motion evaluator to filter weak or misaligned samples—expanding interaction coverage without extra capture. Second, we propose InterActor, a text-to-interaction model with word-level conditioning that preserves token-level cues (initiation, response, contact ordering) and an adaptive interaction loss that emphasizes contextually relevant inter-person joint pairs, improving coupling and physical plausibility for fine-grained interaction modeling. Extensive experiments show consistent gains in motion diversity, fidelity, and generalization, including out-of-distribution scenarios and user studies. Code will be released at github.com/Qingxuan-Wu/Text2Interact.

Deep Learning · Algorithms

Daniil Medyakov, Stanko Sergey, Gleb Molodtsov, Philip Zmushko, Grigoriy Evseev, Egor Petrov, Aleksandr Beznosikov

Large language models have achieved major advances across domains, yet training them remains extremely resource-intensive. We revisit Sign-SGD, which serves both as a memory-efficient optimizer for single-node training and as a gradient compression mechanism for distributed learning. This paper addresses a central limitation: the effective stepsize cannot be determined a priori because it relies on unknown, problem-specific quantities. We present a parameter-free Sign-SGD that removes manual stepsize selection. We analyze the deterministic single-node case, and extend the method to stochastic single-node training and multi-node settings. We also incorporate the momentum technique into our algorithms and propose a memory-efficient variant that stores only gradient signs instead of full gradients. We evaluate our methods on pre-training LLaMA models (130M and 350M) and fine-tuning a Swin Transformer (28M). Across considered tasks, the proposed methods match the performance of tuned Sign-SGD and AdamW (grid-searched stepsizes with a cosine schedule), while avoiding tuning overhead. Employing parameter-free training yields approximately $1.5\times$ end-to-end speedup compared to runs with grid-searched stepsizes.

Social Aspects · Fairness, Equity, Justice and Safety

Yifan Wang, Mayank Jobanputra, Ji-Ung Lee, Soyoung Oh, Isabel Valera, Vera Demberg

Natural language processing (NLP) models often replicate or amplify social bias from training data, raising concerns about fairness. At the same time, their black-box nature makes it difficult for users to recognize biased predictions and for developers to effectively mitigate them. While some studies suggest that input-based explanations can help detect and mitigate bias, others question their reliability in ensuring fairness. Existing research on explainability in fair NLP has been predominantly qualitative, with limited large-scale quantitative analysis. In this work, we conduct the first systematic study of the relationship between explainability and fairness in hate speech detection, focusing on both encoder- and decoder-only models. We examine three key dimensions: (1) identifying biased predictions, (2) selecting fair models, and (3) mitigating bias during model training. Our findings show that input-based explanations can effectively detect biased predictions and serve as useful supervision for reducing bias during training, but they are unreliable for selecting fair models among candidates. Our code is available at https://github.com/Ewanwong/fairness_x_explainability.

Optimization · Everything Else

Zihao Zeng, Siyi Li, Xinyu Yan, Lei Xiao, Wei Yang Bryan Lim

Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models by integrating external knowledge sources, but at the cost of substantial computational overhead from extended input sequences. Current RAG systems exhibit two fundamental inefficiencies: redundant processing of frequently retrieved text chunks across multiple queries, and uniform deep retrieval that over-provisions context regardless of query complexity. We present AdaCache, an adaptive caching framework that addresses these limitations through dual optimization strategies. First, we introduce a cache-aware partial recomputation mechanism that profiles attention patterns to construct selective cache variants, enabling flexible reuse while preserving cross-chunk dependencies. Second, we develop adaptive context augmentation that dynamically determines optimal retrieval depth via lightweight confidence estimation, avoiding unnecessary overhead on simple queries. Comprehensive experiments across diverse datasets and LLMs demonstrate that AdaCache delivers substantial improvements in Time-To-First-Token compared to state-of-the-art RAG caching systems, while preserving generation quality.

Optimization · Everything Else

FEIYE HUO, Jianchao Tan, Jiahao Liu, Zixu Jiang, Jiacheng Li, Jingang Wang, Xunliang Cai, Shengli Sun

As the parameter size of large language models (LLMs) continues to grow, the latency of autoregressive inference increases due to memory-bound computational inefficiency. To address this, speculative decoding has been proposed, where a large target model verifies multiple tokens generated in parallel by a smaller draft model. However, the performance of speculative decoding is fundamentally limited by the draft model’s capacity, which stems from the parameter gap between the two models. To overcome this limitation, we propose RepSpec, which combines structural re-parameterization with draft model training. During training, redundant linear structures are introduced and later merged into the backbone network during inference, thus enhancing the draft model’s training effectiveness without increasing inference cost. By applying our method to improve the current state-of-the-art approach, EAGLE, we achieve a significant improvement in accepted sequence length. Furthermore, considering the specific characteristics of the speculative decoding scenario, we explore a hybrid training strategy that combines linear and nonlinear structures, which yields a further improvement in acceptance length.

Optimization · Everything Else

ChentongChen, Mengyuan Zhong, Jialong Shi, Jianyong Sun, Ye Fan

This paper investigates the application of Large Language Models (LLMs) in Automated Heuristic Design (AHD), where their integration into evolutionary frameworks reveals a significant gap in global control and long-term learning. We propose the Hindsight-Foresight Prompt (HiFo-Prompt), a novel framework for LLM-based AHD designed to overcome these limitations. This is achieved through two synergistic strategies: Foresight and Hindsight. Foresight acts as a high-level meta-controller, monitoring population dynamics(e.g., stagnation and diversity collapse) to switch the global search strategy between exploration and exploitation explicitly. Hindsight builds a persistent knowledge base by distilling successful design principles from past generations, making this knowledge reusable. This dual mechanism ensures that the LLM is not just a passive operator but an active reasoner, guided by a global plan (Foresight) while continuously improving from its cumulative experience (Hindsight). Empirical results demonstrate that HiFo-Prompt significantly outperforms a comprehensive suite of state-of-the-art AHD methods, discovering higher-quality heuristics with substantially improved convergence speed and query efficiency. Our code is available at https://github.com/Challenger-XJTU/HiFo-Prompt.