Daily Papers

Graph-based Retrieval-augmented generation (RAG) has become a widely studied approach for improving the reasoning, accuracy, and factuality of Large Language Models (LLMs). However, many existing graph-based RAG systems overlook the high cost associated with LLM token usage during graph construction, hindering large-scale adoption. To address this, we propose TERAG, a simple yet effective framework designed to build informative graphs at a significantly lower cost. Inspired by HippoRAG, we incorporate Personalized PageRank (PPR) during the retrieval phase, and we achieve at least 80% of the accuracy of widely used graph-based RAG methods while consuming only 3%-11% of the output tokens. With its low token footprint and efficient construction pipeline, TERAG is well-suited for large-scale and cost-sensitive deployment scenarios.

Video Large Language Models (VLMs) have achieved remarkable results on a variety of vision language tasks, yet their practical use is limited by the "needle in a haystack" problem: the massive number of visual tokens produced from raw video frames exhausts the model's context window. Existing solutions alleviate this issue by selecting a sparse set of frames, thereby reducing token count, but such frame-wise selection discards essential temporal dynamics, leading to suboptimal reasoning about motion and event continuity. In this work we systematically explore the impact of temporal information and demonstrate that extending selection from isolated key frames to key clips, which are short, temporally coherent segments, improves video understanding. To maintain a fixed computational budget while accommodating the larger token footprint of clips, we propose an adaptive resolution strategy that dynamically balances spatial resolution and clip length, ensuring a constant token count per video. Experiments on three long-form video benchmarks demonstrate that our training-free approach, F2C, outperforms uniform sampling up to 8.1%, 5.6%, and 10.3% on Video-MME, LongVideoBench and MLVU benchmarks, respectively. These results highlight the importance of preserving temporal coherence in frame selection and provide a practical pathway for scaling Video LLMs to real world video understanding applications. Project webpage is available at https://guangyusun.com/f2c .

Chain-of-Thought (CoT) prompting helps Large Language Models (LLMs) tackle complex reasoning by eliciting explicit step-by-step rationales. However, CoT's verbosity increases latency and memory usage and may propagate early errors across long chains. We propose the Reasoning Capsule (R-Capsule), a framework that aims to combine the efficiency of latent reasoning with the transparency of explicit CoT. The core idea is to compress the high-level plan into a small set of learned latent tokens (a Reasoning Capsule) while keeping execution steps lightweight or explicit. This hybrid approach is inspired by the Information Bottleneck (IB) principle, where we encourage the capsule to be approximately minimal yet sufficient for the task. Minimality is encouraged via a low-capacity bottleneck, which helps improve efficiency. Sufficiency is encouraged via a dual objective: a primary task loss for answer accuracy and an auxiliary plan-reconstruction loss that encourages the capsule to faithfully represent the original textual plan. The reconstruction objective helps ground the latent space, thereby improving interpretability and reducing the use of uninformative shortcuts. Our framework strikes a balance between efficiency, accuracy, and interpretability, thereby reducing the visible token footprint of reasoning while maintaining or improving accuracy on complex benchmarks. Our codes are available at: https://anonymous.4open.science/r/Reasoning-Capsule-7BE0

LLMs process text as sequences of tokens that roughly correspond to words, where less common words are represented by multiple tokens. However, individual tokens are often semantically unrelated to the meanings of the words/concepts they comprise. For example, Llama-2-7b's tokenizer splits the word "northeastern" into the tokens ['_n', 'ort', 'he', 'astern'], none of which correspond to semantically meaningful units like "north" or "east." Similarly, the overall meanings of named entities like "Neil Young" and multi-word expressions like "break a leg" cannot be directly inferred from their constituent tokens. Mechanistically, how do LLMs convert such arbitrary groups of tokens into useful higher-level representations? In this work, we find that last token representations of named entities and multi-token words exhibit a pronounced "erasure" effect, where information about previous and current tokens is rapidly forgotten in early layers. Using this observation, we propose a method to "read out" the implicit vocabulary of an autoregressive LLM by examining differences in token representations across layers, and present results of this method for Llama-2-7b and Llama-3-8B. To our knowledge, this is the first attempt to probe the implicit vocabulary of an LLM.

Over the last few years, multi-vector retrieval methods, spearheaded by ColBERT, have become an increasingly popular approach to Neural IR. By storing representations at the token level rather than at the document level, these methods have demonstrated very strong retrieval performance, especially in out-of-domain settings. However, the storage and memory requirements necessary to store the large number of associated vectors remain an important drawback, hindering practical adoption. In this paper, we introduce a simple clustering-based token pooling approach to aggressively reduce the number of vectors that need to be stored. This method can reduce the space & memory footprint of ColBERT indexes by 50% with virtually no retrieval performance degradation. This method also allows for further reductions, reducing the vector count by 66%-to-75% , with degradation remaining below 5% on a vast majority of datasets. Importantly, this approach requires no architectural change nor query-time processing, and can be used as a simple drop-in during indexation with any ColBERT-like model.

Despite the significant success of large language models (LLMs), their extensive memory requirements pose challenges for deploying them in long-context token generation. The substantial memory footprint of LLM decoders arises from the necessity to store all previous tokens in the attention module, a requirement imposed by key-value (KV) caching. In this work, our focus is on developing an efficient compression technique for the KV cache. Empirical evidence indicates a significant clustering tendency within key embeddings in the attention module. Building on this key insight, we have devised a novel caching method with sublinear complexity, employing online clustering on key tokens and online ell_2 sampling on values. The result is a provably accurate and efficient attention decoding algorithm, termed SubGen. Not only does this algorithm ensure a sublinear memory footprint and sublinear time complexity, but we also establish a tight error bound for our approach. Empirical evaluations on long-context question-answering tasks demonstrate that SubGen significantly outperforms existing and state-of-the-art KV cache compression methods in terms of performance and efficiency.

Key-Value (KV) Caching has become an essential technique for accelerating the inference speed and throughput of generative Large Language Models~(LLMs). However, the memory footprint of the KV cache poses a critical bottleneck in LLM deployment as the cache size grows with batch size and sequence length, often surpassing even the size of the model itself. Although recent methods were proposed to select and evict unimportant KV pairs from the cache to reduce memory consumption, the potential ramifications of eviction on the generative process are yet to be thoroughly examined. In this paper, we examine the detrimental impact of cache eviction and observe that unforeseen risks arise as the information contained in the KV pairs is exhaustively discarded, resulting in safety breaches, hallucinations, and context loss. Surprisingly, we find that preserving even a small amount of information contained in the evicted KV pairs via reduced precision quantization substantially recovers the incurred degradation. On the other hand, we observe that the important KV pairs must be kept at a relatively higher precision to safeguard the generation quality. Motivated by these observations, we propose Mixed-precision KV cache~(MiKV), a reliable cache compression method that simultaneously preserves the context details by retaining the evicted KV pairs in low-precision and ensure generation quality by keeping the important KV pairs in high-precision. Experiments on diverse benchmarks and LLM backbones show that our proposed method offers a state-of-the-art trade-off between compression ratio and performance, compared to other baselines.

The escalating demand for long-context applications has intensified the necessity of extending the LLM context windows. Despite recent fine-tuning approaches successfully expanding context lengths, their high memory footprints, especially for activations, present a critical practical limitation. Current parameter-efficient fine-tuning methods prioritize reducing parameter update overhead over addressing activation memory constraints. Similarly, existing sparsity mechanisms improve computational efficiency but overlook activation memory optimization due to the phenomenon of Shadowy Activation. In this paper, we propose LeMo, the first LLM fine-tuning system that explores and exploits a new token-level sparsity mechanism inherent in long-context scenarios, termed Contextual Token Sparsity. LeMo minimizes redundant token involvement by assessing the informativeness of token embeddings while preserving model accuracy. Specifically, LeMo introduces three key techniques: (1) Token Elimination, dynamically identifying and excluding redundant tokens across varying inputs and layers. (2) Pattern Prediction, utilizing well-trained predictors to approximate token sparsity patterns with minimal overhead. (3) Kernel Optimization, employing permutation-free and segment-based strategies to boost system performance. We implement LeMo as an end-to-end fine-tuning system compatible with various LLM architectures and other optimization techniques. Comprehensive evaluations demonstrate that LeMo reduces memory consumption by up to 1.93x and achieves up to 1.36x speedups, outperforming state-of-the-art fine-tuning systems.

When predicting the next token in a sequence, vanilla transformers compute attention over all previous tokens, resulting in quadratic scaling of compute with sequence length. State-space models compress the entire sequence of tokens into a fixed-dimensional representation to improve efficiency, while other architectures achieve sub-quadratic complexity via low-rank projections or sparse attention patterns over the sequence. In this paper, we introduce Attamba, a novel architecture that uses state-space models to compress chunks of tokens and applies attention on these compressed key-value representations. We find that replacing key and value projections in a transformer with SSMs can improve model quality and enable flexible token chunking, resulting in 24% improved perplexity with transformer of similar KV-Cache and attention footprint, and ~4 times smaller KV-Cache and Attention FLOPs for 5% perplexity trade-off. Attamba can perform attention on chunked-sequences of variable length, enabling a smooth transition between quadratic and linear scaling, offering adaptable efficiency gains.

Visual Autoregressive (VAR) modeling has gained popularity for its shift towards next-scale prediction. However, existing VAR paradigms process the entire token map at each scale step, leading to the complexity and runtime scaling dramatically with image resolution. To address this challenge, we propose FastVAR, a post-training acceleration method for efficient resolution scaling with VARs. Our key finding is that the majority of latency arises from the large-scale step where most tokens have already converged. Leveraging this observation, we develop the cached token pruning strategy that only forwards pivotal tokens for scale-specific modeling while using cached tokens from previous scale steps to restore the pruned slots. This significantly reduces the number of forwarded tokens and improves the efficiency at larger resolutions. Experiments show the proposed FastVAR can further speedup FlashAttention-accelerated VAR by 2.7times with negligible performance drop of <1%. We further extend FastVAR to zero-shot generation of higher resolution images. In particular, FastVAR can generate one 2K image with 15GB memory footprints in 1.5s on a single NVIDIA 3090 GPU. Code is available at https://github.com/csguoh/FastVAR.

We present OmniVLM, a sub-billion-parameter vision-language model for efficient on-device inference. OmniVLM introduces a token compression mechanism that reduces visual token sequence length from 729 to 81 tokens, significantly reducing computational overhead while preserving visual-semantic fidelity. Through a multi-stage training pipeline of pretraining, supervised fine-tuning, and minimal-edit Direct Preference Optimization (DPO), OmniVLM matches the performance of larger models. On multiple benchmarks including ScienceQA, POPE, and MMMU, OmniVLM outperforms existing baselines like nanoLLAVA within a 968M-parameter footprint. Empirical results on the same laptop demonstrate 9.1x faster time-to-first-token (0.75s vs 6.82s) and 1.5x higher decoding speed (29.41 vs 19.20 tokens/s) compared to nanoLLAVA, enabling efficient deployment on edge devices. The model weights can be accessed on huggingface: https://huggingface.co/NexaAIDev/OmniVLM-968M, and the inference examples can be find in Appendix B.

As large language models (LLMs) continue to scale, the memory footprint of key-value (KV) caches during inference has become a significant bottleneck. Existing approaches primarily focus on compressing KV caches within a single prompt or reusing shared prefixes or frequently ocurred text segments across prompts. However, such strategies are limited in scenarios where prompts are semantically similar but lexically different, which frequently occurs in tasks such as multi-document summarization and conversational agents. We propose SemShareKV, a KV cache sharing and compression framework that accelerates LLM inference by reusing KVCache in semantically similar prompts. Instead of relying on exact token matches, SemShareKV applies fuzzy token matching using locality-sensitive hashing (LSH) on token embeddings and incorporates Rotary Position Embedding (RoPE) to better preserve positional information. By selectively reusing relevant key-value pairs from a reference prompt's cache, SemShareKV reduces redundant computation while maintaining output quality. Experiments on diverse summarization datasets show up to 6.25times speedup and 42\% lower GPU memory usage with 5k tokens input, with negligible quality degradation. These results highlight the potential of semantic-aware cache sharing for efficient LLM inference.

Scaling language models unlocks impressive capabilities, but the accompanying computational and memory demands make both training and deployment expensive. Existing efficiency efforts typically target either parameter sharing or adaptive computation, leaving open the question of how to attain both simultaneously. We introduce Mixture-of-Recursions (MoR), a unified framework that combines the two axes of efficiency inside a single Recursive Transformer. MoR reuses a shared stack of layers across recursion steps to achieve parameter efficiency, while lightweight routers enable adaptive token-level thinking by dynamically assigning different recursion depths to individual tokens. This allows MoR to focus quadratic attention computation only among tokens still active at a given recursion depth, further improving memory access efficiency by selectively caching only their key-value pairs. Beyond these core mechanisms, we also propose a KV sharing variant that reuses KV pairs from the first recursion, specifically designed to decrease prefill latency and memory footprint. Across model scales ranging from 135M to 1.7B parameters, MoR forms a new Pareto frontier: at equal training FLOPs and smaller model sizes, it significantly lowers validation perplexity and improves few-shot accuracy, while delivering higher throughput compared with vanilla and existing recursive baselines. These gains demonstrate that MoR is an effective path towards large-model quality without incurring large-model cost.

Mixture-of-Experts (MoE) model architecture has emerged as a promising solution for scaling transformer models efficiently, offering sparse activation that reduces computational costs while increasing model capacity. However, as MoE models scale, they need to be distributed across GPU devices, thus face critical performance bottlenecks due to their large memory footprint. Expert parallelism distributes experts across GPUs, however, faces key challenges including an unbalanced token routing and expert activation, resulting in communication tail latency and processing inefficiencies. While existing solutions address some of these issues, they fail to resolve the dual challenges of load imbalance and communication skew. The imbalance in token processing load across experts causes uneven processing times on different GPUs, while communication skew between GPUs leads to unbalanced inter-GPU data transfers. These factors degrade the performance of MoE models by increasing tail latency and reducing overall throughput. To address these limitations, we propose an Integer Linear Programming (ILP) formulation to optimize expert placement by jointly considering token load, communication, and computation costs. We exploit the property that there is a token routing dependency across layers, where tokens routed to a specific expert in one layer are likely to be routed to a limited set of experts in the subsequent layer. Our solution, MoETuner, offers an optimal expert-to-GPU assignment that minimizes inter-GPU token routing costs and balances token processing across devices, thereby reducing tail latency and end-to-end execution time. Experimental results demonstrate 9.3% and 17.5% of end-to-end speedups for single-node and multi-node inference respectively, showcasing the potential of our ILP-based optimization for offering expert parallel solutions for next-generation MoEs.

The pre-training of masked language models (MLMs) consumes massive computation to achieve good results on downstream NLP tasks, resulting in a large carbon footprint. In the vanilla MLM, the virtual tokens, [MASK]s, act as placeholders and gather the contextualized information from unmasked tokens to restore the corrupted information. It raises the question of whether we can append [MASK]s at a later layer, to reduce the sequence length for earlier layers and make the pre-training more efficient. We show: (1) [MASK]s can indeed be appended at a later layer, being disentangled from the word embedding; (2) The gathering of contextualized information from unmasked tokens can be conducted with a few layers. By further increasing the masking rate from 15% to 50%, we can pre-train RoBERTa-base and RoBERTa-large from scratch with only 78% and 68% of the original computational budget without any degradation on the GLUE benchmark. When pre-training with the original budget, our method outperforms RoBERTa for 6 out of 8 GLUE tasks, on average by 0.4%.

Transformer-based large language models (LLMs) demonstrate impressive performance in long context generation. Extending the context length has disproportionately shifted the memory footprint of LLMs during inference to the key-value cache (KV cache). In this paper, we propose HEADINFER, which offloads the KV cache to CPU RAM while avoiding the need to fully store the KV cache for any transformer layer on the GPU. HEADINFER employs a fine-grained, head-wise offloading strategy, maintaining only selective attention heads KV cache on the GPU while computing attention output dynamically. Through roofline analysis, we demonstrate that HEADINFER maintains computational efficiency while significantly reducing memory footprint. We evaluate HEADINFER on the Llama-3-8B model with a 1-million-token sequence, reducing the GPU memory footprint of the KV cache from 128 GB to 1 GB and the total GPU memory usage from 207 GB to 17 GB, achieving a 92% reduction compared to BF16 baseline inference. Notably, HEADINFER enables 4-million-token inference with an 8B model on a single consumer GPU with 24GB memory (e.g., NVIDIA RTX 4090) without approximation methods.

We propose a novel spectral generative modeling framework for natural language processing that jointly learns a global time varying Fourier dictionary and per token mixing coefficients, replacing the ubiquitous self attention mechanism in transformer architectures. By enforcing reconstruction losses in both the time domain (embedding reconstruction) and the frequency domain (via Short Time Fourier Transform magnitude matching) alongside a standard language modeling objective, and fitting a Gaussian Mixture Model (GMM) prior over the learned mixing vectors, our approach achieves competitive perplexity and generation quality on standard benchmarks such as WikiText2 and Penn Treebank. In contrast to the quadratic computation complexity of self attention, our method operates with linear complexity, delivering substantial efficiency gains. We demonstrate that spectral dictionary models can achieve competitive performance compared to transformer baselines while significantly reducing inference latency and memory footprint, offering a compelling alternative for scalable language modeling.

Ultra-high-resolution (UHR) remote sensing (RS) imagery offers valuable data for Earth observation but pose challenges for existing multimodal foundation models due to two key bottlenecks: (1) limited availability of UHR training data, and (2) token explosion caused by the large image size. To address data scarcity, we introduce SuperRS-VQA (avg. 8,376times8,376) and HighRS-VQA (avg. 2,000times1,912), the highest-resolution vision-language datasets in RS to date, covering 22 real-world dialogue tasks. To mitigate token explosion, our pilot studies reveal significant redundancy in RS images: crucial information is concentrated in a small subset of object-centric tokens, while pruning background tokens (e.g., ocean or forest) can even improve performance. Motivated by these findings, we propose two strategies: Background Token Pruning and Anchored Token Selection, to reduce the memory footprint while preserving key semantics.Integrating these techniques, we introduce GeoLLaVA-8K, the first RS-focused multimodal large language model capable of handling inputs up to 8Ktimes8K resolution, built on the LLaVA framework. Trained on SuperRS-VQA and HighRS-VQA, GeoLLaVA-8K sets a new state-of-the-art on the XLRS-Bench.

Key-value (KV) caching has emerged as a crucial optimization technique for accelerating inference in large language models (LLMs). By allowing the attention operation to scale linearly rather than quadratically with the total sequence length, KV caching significantly enhances generation throughput. However, due to large context lengths in the modern LLMs, the memory footprint of the KV is a huge bottleneck for model deployment directly impacting the model's batch size, hindering its ability to deliver high-throughput. Existing research addresses this challenge using several techniques, such as discarding low-attention tokens, quantization, and matrix approximation which typically lead to a negative impact on the model accuracy. In this paper, We propose KVCrush technology which can be combined with many KV compression technologies to improve the model accuracy at a much smaller memory. KVCrush provides an alternate representation scheme for key-value states, along with a low-overhead token pruning algorithm that accounts for the token distribution in the KV cache, which in turn allows for a a smaller footprint while maintaining the accuracy of the model. Based on our results, KVCrush reduces LongBench KV Cache size by 4x with less than 1% accuracy drop and achieves state-of-the-art average accuracy with minimal overhead, incurring less than 0.5% total inference latency. KVCrush not only outperforms the accuracy of state-of-the-art importance-based token retention schemes but is also compatible with typical practical LLM deployments using KV cache paging schemes such as vLLM and mixed precision quantization.

As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency. However, such power comes at a cost: it incurs a huge computation burden and heavy memory footprint as pairwise token interaction across all spatial locations is computed. A series of works attempt to alleviate this problem by introducing handcrafted and content-agnostic sparsity into attention, such as restricting the attention operation to be inside local windows, axial stripes, or dilated windows. In contrast to these approaches, we propose a novel dynamic sparse attention via bi-level routing to enable a more flexible allocation of computations with content awareness. Specifically, for a query, irrelevant key-value pairs are first filtered out at a coarse region level, and then fine-grained token-to-token attention is applied in the union of remaining candidate regions (\ie, routed regions). We provide a simple yet effective implementation of the proposed bi-level routing attention, which utilizes the sparsity to save both computation and memory while involving only GPU-friendly dense matrix multiplications. Built with the proposed bi-level routing attention, a new general vision transformer, named BiFormer, is then presented. As BiFormer attends to a small subset of relevant tokens in a query adaptive manner without distraction from other irrelevant ones, it enjoys both good performance and high computational efficiency, especially in dense prediction tasks. Empirical results across several computer vision tasks such as image classification, object detection, and semantic segmentation verify the effectiveness of our design. Code is available at https://github.com/rayleizhu/BiFormer.

Large model inference is shifting from cloud to edge due to concerns about the privacy of user interaction data. However, edge devices often struggle with limited computing power, memory, and bandwidth, requiring collaboration across multiple devices to run and speed up LLM inference. Pipeline parallelism, the mainstream solution, is inefficient for single-user scenarios, while tensor parallelism struggles with frequent communications. In this paper, we argue that tensor parallelism can be more effective than pipeline on low-resource devices, and present a compute- and memory-efficient tensor parallel inference system, named TPI-LLM, to serve 70B-scale models. TPI-LLM keeps sensitive raw data local in the users' devices and introduces a sliding window memory scheduler to dynamically manage layer weights during inference, with disk I/O latency overlapped with the computation and communication. This allows larger models to run smoothly on memory-limited devices. We analyze the communication bottleneck and find that link latency, not bandwidth, emerges as the main issue, so a star-based allreduce algorithm is implemented. Through extensive experiments on both emulated and real testbeds, TPI-LLM demonstrated over 80% less time-to-first-token and token latency compared to Accelerate, and over 90% compared to Transformers and Galaxy, while cutting the peak memory footprint of Llama 2-70B by 90%, requiring only 3.1 GB of memory for 70B-scale models.

With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key-value (KV) cache expands with the sequence length, the increasing memory footprint and the need to access it for each token generation both result in low throughput when serving long-context LLMs. While various dynamic sparse attention methods have been proposed to speed up inference while maintaining generation quality, they either fail to sufficiently reduce GPU memory consumption or introduce significant decoding latency by offloading the KV cache to the CPU. We present ShadowKV, a high-throughput long-context LLM inference system that stores the low-rank key cache and offloads the value cache to reduce the memory footprint for larger batch sizes and longer sequences. To minimize decoding latency, ShadowKV employs an accurate KV selection strategy that reconstructs minimal sparse KV pairs on-the-fly. By evaluating ShadowKV on a broad range of benchmarks, including RULER, LongBench, and Needle In A Haystack, and models like Llama-3.1-8B, Llama-3-8B-1M, GLM-4-9B-1M, Yi-9B-200K, Phi-3-Mini-128K, and Qwen2-7B-128K, we demonstrate that it can support up to 6times larger batch sizes and boost throughput by up to 3.04times on an A100 GPU without sacrificing accuracy, even surpassing the performance achievable with infinite batch size under the assumption of infinite GPU memory. The code is available at https://github.com/bytedance/ShadowKV.

We present memory-based language modeling as an efficient, eco-friendly alternative to deep neural network-based language modeling. It offers log-linearly scalable next-token prediction performance and strong memorization capabilities. Implementing fast approximations of k-nearest neighbor classification, memory-based language modeling leaves a relatively small ecological footprint both in training and in inference mode, as it relies fully on CPUs and attains low token latencies. Its internal workings are simple and fully transparent. We compare our implementation of memory-based language modeling, OLIFANT, with GPT-2 and GPT-Neo on next-token prediction accuracy, estimated emissions and speeds, and offer some deeper analyses of the model.

Recent advances in attention-free sequence models rely on convolutions as alternatives to the attention operator at the core of Transformers. In particular, long convolution sequence models have achieved state-of-the-art performance in many domains, but incur a significant cost during auto-regressive inference workloads -- naively requiring a full pass (or caching of activations) over the input sequence for each generated token -- similarly to attention-based models. In this paper, we seek to enable mathcal O(1) compute and memory cost per token in any pre-trained long convolution architecture to reduce memory footprint and increase throughput during generation. Concretely, our methods consist in extracting low-dimensional linear state-space models from each convolution layer, building upon rational interpolation and model-order reduction techniques. We further introduce architectural improvements to convolution-based layers such as Hyena: by weight-tying the filters across channels into heads, we achieve higher pre-training quality and reduce the number of filters to be distilled. The resulting model achieves 10x higher throughput than Transformers and 1.5x higher than Hyena at 1.3B parameters, without any loss in quality after distillation.