Context Compression

Conventional cardiac cine MRI relies on breath-hold Cartesian acquisitions, which are vulnerable to motion artifacts and can be uncomfortable or infeasible, particularly for pediatric and other noncompliant patients who cannot reliably hold their breath. Free-breathing radial acquisitions can alleviate these limitations, but robust reconstruction at high acceleration remains challenging due to prominent streak artifacts. To address these limitations, we propose Cine-DL, a clinically oriented framework that couples targeted k-space preprocessing with fast, model-based deep reconstruction. In this pipeline, raw free-breathing radial data undergo retrospective cardiac binning and respiratory gating to resolve cardiac phases and discard motion-corrupted spokes. We then introduce Streak Optimized Coil Compression (SOC), which explicitly preserves cardiac signals while suppressing peripheral interference that typically drives the streak artifacts. The resulting 2D+t cine series is reconstructed with an unrolled network that alternates a ResNet proximal operator with physics-based data consistency updates solved via conjugate gradient. We further employ a memory-efficient training strategy that reduces peak memory usage. We evaluate Cine-DL on free-breathing volunteer data against established baselines (k-t SENSE and iGRASP) and demonstrate clinical translation via hospital deployment on newly acquired patient data. Our experiments show that Cine-DL consistently improves quantitative metrics and visual fidelity, supporting a practical route toward routine, time-sensitive clinical adoption of free-breathing cine MRI.

We propose a scalable tensorization framework for neural network compression based on slice-wise feature distillation. Unlike conventional tensor decomposition methods that rely on costly global finetuning, our approach decomposes the network into slices consisting of either individual layers or blocks (e.g., convolutional layers or MLPs), or small groups of consecutive layers, and tensorizes each slice independently to reproduce the intermediate representations of the original pretrained model. This modular strategy improves accuracy recovery, reduces data requirements, and enables efficient parallel optimization. Experiments on ResNet-34 show significant gains over conventional global tensorization, achieving near-lossless compression at moderate compression rates with faster optimization. Results on GPT-2 XL further demonstrate the scalability of the method and its applicability to large-scale models, particularly in distributed settings.

While 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction, it suffers from significant overhead due to massive redundant primitives. Existing compression methods typically rely on local sampling or fixed pruning thresholds, which often struggle to balance redundancy reduction with high-fidelity rendering. To address this, we propose a novel framework that formulates Gaussian optimization as a global geometric distribution matching problem. Specifically, our approach integrates three components: (1) we introduce a multi-view 3D Gaussian contribution ranking mechanism that filters primitives using geometric consistency instead of local heuristics; (2) we propose a global Optimal Transport (OT)-based aggregation algorithm that merges redundant primitives while preserving the underlying geometry; and (3) we design an OT-based densification operator that maintains the Gaussian's distributional properties for stable optimization. Our approach achieves state-of-the-art rendering quality with only \textbf{10$\%$} primitives and \textbf{10$\times$} accelerated training speeds compared to vanilla 3DGS.

Unlike autoregressive models, which generate one token at a time, dLLMs denoise a chunk of [MASK] tokens jointly and sample one or more tokens per step; despite enabling parallel decoding, this process incurs substantial computational cost due to the large chunk size of masked tokens. We observe that much of this cost is spent on repeatedly processing the preceding context and many [MASK] tokens with the same feature representations, indicating considerable computational redundancy. In this work, we revisit dLLM's redundancy from the perspective of [MASK] tokens. Through systematic analysis, we verify the redundancy of [MASK] tokens while revealing their critical role in providing structural information. Guided by these findings, we propose position-preserving [MASK] token compression and terminal-aware augmentation. By compressing redundant [MASK] computation, this approach accelerates decoding and further provides a natural extension toward context-folding-like long-context scaling under limited input-length constraints for full-sequence dLLMs such as LLaDA-8B-Instruct and LLaDA-1.5. Moreover, for block dLLMs such as LLaDA2.0-mini, it augments the context with a protected terminal [MASK] token to enhance generation quality with negligible overhead.

Volumetric media promises next-generation content delivery applications, but its bandwidth demand remains a key bottleneck. Implicit and hybrid volumetric representations reduce model sizes, yet still require careful coding to reach 2D video-like bitrates. We present CATRF, a standard-codec-in-the-loop compression framework for plane-factorized radiance fields. During training, we quantize and pack 2D feature planes into codec-friendly canvases, run a standard codec roundtrip (JPEG/VP9/HEVC/AV1), then unpack and dequantize the decoded features before volume rendering. We use a straight-through estimator (STE) to insert the non-differentiable, standard codec pipeline into the training loop, allowing radiance-field features to adapt directly to the real, client-side codec distortions without introducing any learned codec parameters. On both static and dynamic benchmarks, CATRF consistently achieves a better rate-distortion trade-off over codec-agnostic and learned-codec-in-the-loop baselines, and also outperforms recent compressed 3DGS methods in both compression efficiency and decoding speed. These results highlight a practical path toward low-bitrate, compression-resilient volumetric representations for free-viewpoint video streaming.

The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length to process, yet introduce non-trivial runtime overhead and encounter catastrophic quality drop under high compression. Other methods applying Sparse Attention focus on attention alone, leaving the MLP fully dense and capping achievable speedup. We propose SparseSAM, a (i) training-free structured sparsification framework that jointly accelerates attention and MLP layers while preserving token identity. SparseSAM introduces (ii) Stripe-Sort Attention, which uses a deterministic Z-order permutation to transform dense attention into static hardware-friendly sparse patterns, eliminating dynamic masking overhead. SparseSAM further introduces a (iii) Residual-Consistency MLP that routes only informative tokens through the MLP while propagating remaining tokens through the residual pathway. Across four segmentation benchmarks, SparseSAM loses only 0.004 mIoU at a 0.4 density and 0.021 mIoU at 0.3, a 2.10x reduction in accuracy loss versus token merging advances, while achieving 2x faster inference and 2.8x memory reduction.

LLM context is not just tokens; it is a set of commitments. Long-running conversations accumulate goals, constraints, decisions, preferences, tool results, retrieved evidence, artifacts, and safety boundaries that future responses must preserve. Existing context-management methods reduce length through truncation, retrieval, summarization, memory systems, or token-level prompt compression, but they rarely specify which semantic commitments must survive compression or how their preservation should be measured. We propose Context Codec, a commitment-level framework for compressing prompts and chat histories. Context Codec represents dialogue state as typed, source-grounded semantic atoms with canonical identity, equivalence, conflict, confidence, risk, and evidence spans. It separates five concerns - extraction, normalization, representation, rendering, and verification - and introduces metrics for Critical Atom Recall, Weighted Atom Recall, Commitment Density, and round-trip recoverability. It also defines a taxonomy of semantic compression errors, a concrete normalization procedure, conservative fallback rules for low-confidence and safety-critical atoms, and Context Compression Language (CCL), an ASCII-first compact rendering of canonical JSON atoms. In a small diagnostic study, CCL-Core occupies a useful middle ground between structured prose and JSON: more explicit and auditable than prose, usually more compact than JSON, and less risky than heavily minified notation. The result is not a claim that shorthand solves compression, but a framework for making context compression verifiable: compress the conversation, keep the commitments.

We prove that the extremum stack of a discrete sequence is a minimal sufficient statistic for the class of all computable, causal, rate-independent functionals, in the sense of Kolmogorov complexity. Specifically, we establish K(Pi_n) - O(1) <= K_R(u_{0:n}) <= K(Pi_n) + O(1), where K_R(u_{0:n}) is the length of the shortest program answering every query in the class R, and the O(1) overhead is independent of both the sequence length n and the stack depth k. Sufficiency follows from the classical wiping property of the Preisach hysteresis operator. Minimality is established via a finite indicator family whose rate-independence is verified explicitly. Any compression of a hysteresis-driven stream that preserves the full class R must therefore retain at least K(Pi_n) - O(1) bits; the stack-based compression algorithm implied by the result carries a Kolmogorov optimality guarantee that none of the standard time-series compression methods provide.

Streaming video understanding with large vision-language models (VLMs) requires a compact memory that can support future reasoning over an ever-growing visual history. A common solution is to compress the key-value (KV) cache, but existing streaming methods typically rely on local token-wise heuristics, such as recency, temporal redundancy, or saliency, which do not explicitly optimize whether the retained cache is representative of the accumulated history. We propose to view KV-cache compression as a coreset selection problem: rather than scoring tokens independently for retention, we select a small subset that covers the geometry of the accumulated visual cache. Our method operates in a joint KV representation and introduces a bicriteria objective that balances coverage in key and value spaces, preserving both retrieval structure and output-relevant information. To encourage a more diverse retained subset, we further introduce an orthogonality-driven diversity criterion that favors candidates contributing new directions beyond the current selection, and connect this criterion to log-determinant subset selection. Across four open-source VLMs and five long-video and streaming-video benchmarks, our method improves over heuristic streaming compression baselines under a fixed cache budget. These results highlight that representative coreset selection offers a more effective principle, than token-wise pruning, for memory-constrained streaming video understanding.

Sparse Mixture-of-Experts (MoE) layers route tokens through a handful of experts, and learning-free compression of these layers reduces inference cost without retraining. A subtle obstruction blocks every existing compressor in this family: three experts can each be pairwise compatible yet form an irreducible cycle when merged together, so any score that ranks experts on pairwise signals is structurally blind to which triples are jointly mergeable. We show the obstruction is a precise mathematical object, the harmonic kernel of the simplicial Laplacian on a 2-complex whose vertices are experts, whose edges carry KL merge barriers, and whose faces carry triplet barriers; Hodge-decomposing the edge-barrier signal isolates the kernel exactly. We turn the diagnostic into a selection objective: HodgeCover greedily covers the harmonic-critical edges and triplet-critical triangles, and a hybrid variant of HodgeCover pairs it with off-the-shelf weight pruning on survivors. On three open-weight Sparse MoE backbones under aggressive expert reduction, HodgeCover matches state-of-the-art learning-free baselines on the expert-reduction axis, leads on the aggressive-compression frontier of the hybrid axis, and uniquely balances retained mass across all four Hodge components. These results show that exposing the harmonic kernel of a learned MoE structure changes which compressor wins at the regime that matters most.

Recently, a series of works have started studying variations of concepts from learning theory for product spaces, which can be collected under the name high-arity learning theory. In this work, we consider a high-arity variant of sample compression schemes and we prove that the existence of a high-arity sample compression scheme of non-trivial quality implies high-arity PAC learnability.

Vision-Language-Action (VLA) models have shown remarkable promise in robotics manipulation, yet their high computational cost hinders real-time deployment. Existing token pruning methods suffer from a fundamental trade-off: aggressive compression using pruning inevitably discards critical geometric details like contact points, leading to severe performance degradation. This forces a compromise, limiting the achievable compression rate and thus the potential speedup. We argue that breaking this trade-off requires rethinking compression as a geometry-aware, continuous token resampling in the vision encoder. To this end, we propose the Differentiable Grid Sampler (GridS), a plug-and-play module that performs task-aware, continuous resampling of visual tokens in VLA. By adaptively predicting a minimal set of salient coordinates and extracting features via differentiable interpolation, GridS preserves essential spatial information while achieving drastic compression (with fewer than 10% original visual tokens). Experiments on both LIBERO benchmark and a real robotic platform demonstrate that validating the lowest feasible visual token count reported to date, GridS achieves a 76% reduction in FLOPs with no degradation in the success rate. The code is available at https://github.com/Fediory/Grid-Sampler.

Decoupling is a powerful modeling paradigm for representing multivariate functions as compositions of linear transformations and univariate nonlinear functions. A single-layer decoupling can be viewed as a fully connected neural network with a single hidden layer and flexible activation functions, providing a direct link with neural networks. Because of this, the use of decoupling methods has gained increasing attention in neural network domains, particularly compression, since it enables structured approximations with reduced parameter complexity. Existing tensor-based decoupling methods typically rely on polynomial or piecewise-linear parameterizations of the internal nonlinear functions, which can suffer from numerical instability or limited expressiveness. In this work, we introduce a B-spline-based decoupling framework that generalizes these existing approaches. By exploiting the local support and flexible smoothness control of B-splines, the proposed formulation yields a more numerically stable and expressive representation. We derive a constrained coupled matrix-tensor factorization and propose a robust alternating least-squares algorithm, called R-CMTF-BSD, incorporating normalization and Tikhonov regularization. The proposed method is validated through experiments on synthetic data and transformer model compression. Results on the Vision and Swin Transformer architectures demonstrate that B-spline decoupling enables substantial parameter reduction while maintaining competitive accuracy, making the R-CMTF-BSD algorithm a promising tool for structured neural network compression.

A core challenge in program synthesis is online library learning: the incremental acquisition of reusable abstractions under uncertainty about future task demands. Existing algorithms treat library learning as retrospective compression over a static task distribution, where the learned library is determined by the corpus of past tasks. However, real-world learning domains are often non-stationary, with tasks arising from a generative process that evolves over time. We propose and test the hypothesis that in non-stationary domains human library learning selects abstractions prospectively: targeting compression of future tasks. We study this question using the Pattern Builder Task, a visual program synthesis paradigm in which participants construct increasingly complex geometric patterns from a small set of primitives, transformations, and custom helpers that carry forward across trials. Using this task, we conduct two experiments with complementary latent curricula, designed to dissociate between behaviors consistent with prospective compression, and alternative library learning accounts. Using six computational models spanning online library learning strategies, we show that human abstraction behavior reflects sensitivity to latent, non-stationary structure in the task-generating process. This behavior is consistent with prospective compression, and cannot be captured by existing retrospective compression-based algorithms, or inductive biases modeled by LLM-based program synthesis.

This paper studies cross-domain lossy compression through the lens of minimum entropy coupling (MEC) with rate and classification constraints. In this setting, an encoder observes samples from a degraded source domain, while the decoder is required to generate outputs following a prescribed target distribution and to preserve information relevant to a downstream classification task. Motivated by logarithmic-loss distortion, we adopt an information-based objective that maximizes the coupling strength between the source and reconstruction, rather than minimizing a sample-wise distortion. Under common randomness, we formulate a rate-constrained MEC problem (MEC-B) and show that the intermediate representation can be removed without loss of optimality, yielding an equivalent deterministic coupling formulation. For Bernoulli sources, closed-form expressions are derived with and without classification constraints. In addition, we implement a neural restoration framework using quantization, entropy modeling, distribution matching, and classification regularization. Experiments on MNIST super-resolution and SVHN denoising show that increasing the available rate improves classification accuracy and yields more informative reconstructions.

Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks. However, their deployment in long-context scenarios faces high computational overhead and information redundancy. While soft prompt compression has emerged as a promising way to mitigate these costs by compressing sequences into compact embeddings, existing paradigms remain fundamentally constrained by position bias: they primarily rely on learnable tokens insertion at fixed positions or group tokens according to their physical token layout, thereby inducing performance instability and semantic fragmentation. To overcome this bottleneck, we propose Semantic Consistency Context Compression (SeCo), a method that shifts context compression from position-driven to semantic-driven. Rather than constraint by physical token layout, SeCo dynamically anchors compression directly in the semantic space by selecting query-relevant tokens as semantic centers and aggregating remaining tokens via consistency-weighted merging. This design inherently preserves semantic consistency while eliminating position bias. Extensive experiments on 14 benchmarks across two backbone models demonstrate that SeCo consistently shows superiority in downstream tasks, inference latency, and out-of-domain robustness. The code is available at https://anonymous.4open.science/r/seco-EE5E.

We present AQMP, a novel image codec combining Adaptive Quadtree Refinement with Matching Pursuit. Unlike conventional Matching Pursuit methods that operate on fixed-size sub-images, AQMP dynamically adapts block sizes to local image structure, allocating finer partitions where the image is complex and coarser ones where it is smooth. This adaptivity yields superior compression ratios compared to fixed-size block Matching Pursuit at equivalent image quality, while offering significant parallelization opportunities at both the tree-leaf level and during compression of individual nodes. The algorithm is governed by user-specified accuracy and sparsity parameters alongside a small set of additional hyperparameters. To navigate the trade-off between compression efficiency and visual quality, we perform multi-objective hyperparameter optimization using the Tree-Structured Parzen Estimator, producing comprehensive Pareto fronts. Experimental results show that AQMP achieves up to $4\times$ higher compression rates than JPEG at comparable SSIM values, while maintaining competitive quality across a broad range of compression regimes. Performance evaluation is provided using a representative set of test images. To ensure reproducibility and promote adoption, we have made our implementation publicly available on GitHub under the MIT license.

Text embedding and generative tasks are usually trained separately based on large language models (LLMs) nowadays. This causes a large amount of training cost and deployment effort. Context compression is also a challenging and pressing task, which is vital to reasoning-driven generation, and agentic tasks requiring long context and continual learning. In this paper, we explore how to unify reasoning-driven generation, reasoning-enhanced text representation and context compression tasks in one forward pass for LLMs. Through meta latent tokens and a unified generative, representative and compressive tuning approach, we propose a training framework named GRC that bridges the three tasks. The trained models can accomplish three objectives in a single forward pass while maintaining modular, LEGO-style flexibility during inference. This design greatly reduces the deployment effort for retrieval-augmented generation (RAG) and achieves efficient inference and three times data utilization during training. Furthermore, this framework design enables a new paradigm for text embedding: self-reason-latent embeds, and a new generation paradigm, latent memory-augmented generation, where compressed and internalized KV cache with O(1) length is used as the updatable memory. We also propose hybrid paged attention to speed up the inference of our models. Extensive experiments on reasoning-intensive retrieval benchmarks, generative tasks, document compression, latency evaluation, and RAG settings demonstrate the effectiveness of our method and may shed light on the truly unified model that can handle reasoning-driven generation, embedding and compression tasks seamlessly.

Visual encoding constitutes a major computational bottleneck in Multimodal Large Language Models (MLLMs), especially for high-resolution image inputs. The prevailing practice typically adopts global encoding followed by post-ViT compression. Global encoding produces massive token sequences, while post-ViT compression incurs the full quadratic attention cost of the ViT before any token reduction takes place. In this work, we revisit this convention along two dimensions: the encoding strategy and visual token compression. First, controlled experiments show that slice-based encoding outperforms global encoding across benchmarks, suggesting that preserving local details through sliced views can be more beneficial than applying global attention for fine-grained perception. Second, we introduce intra-ViT early compression, which reduces tokens in shallow ViT layers and substantially lowers visual-encoding FLOPs while preserving downstream performance. By integrating intra-ViT compression into the slice-based encoding framework, we present LLaVA-UHD v4, an efficient and compute-controllable visual encoding scheme tailored for high-resolution inputs. Across a diverse set of benchmarks covering document understanding, OCR, and general VQA, LLaVA-UHD v4 reduces visual-encoding FLOPs by 55.8% while matching or even surpassing baseline performance. These results suggest that visual-encoding efficiency can be substantially improved without sacrificing downstream performance, providing a practical design direction for efficient high-resolution MLLMs. All model weights and code will be publicly released to support further research.

Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex tasks. However, manually designing optimal communication topologies is labor-intensive, while automated expansion methods often result in bloated structures with redundant agents, leading to excessive token consumption. To address this problem, we introduce \textbf{AgentSlimming}, a plug-and-play compression framework for graph-structured multi-agent workflows. Motivated by pruning and quantization in neural networks, AgentSlimming compresses workflows by first estimating the importance score of each agent with a hybrid mechanism, and then removes redundant agents or replaces them with low-cost ones, where each operation is validated using a baseline-anchored acceptance rule to prevent performance collapse. Experiments show that AgentSlimming reduces average token cost by up to 78.9% with negligible performance degradation, and sometimes even improves accuracy, achieving a strong Pareto-optimal trade-off between cost and quality. \textit{Our code is publicly available at https://github.com/CitrusYL/AgentSlimming

Reasoning-centric large language models (LLMs) achieve strong performance by generating intermediate reasoning trajectories, but often incur excessive token usage and high inference-time decoding cost. We observe that, when solving the same problems, larger reasoning models can often produce more concise traces, whereas smaller reasoning models tend to generate longer and more redundant trajectories. This is especially problematic in real-world deployment, where memory, latency, and serving-cost constraints often favor smaller models. Our observations suggest that reasoning compression can be transferred from large models to small ones rather than enforced through explicit length constraints. Based on this insight, we propose Mixed-Policy Distillation (MPD), a reasoning compression framework that transfers concise reasoning behavior from a larger-sized teacher to a smaller student by distilling teacher-compressed student trajectories. Unlike on-policy distillation, which aligns the student with teacher distributions over verbose student trajectories, or off-policy distillation, which relies on teacher-generated trajectories and may suffer from distribution mismatch, MPD combines the strengths of both. Given a student-sampled trajectory, the teacher rewrites it into a more concise reasoning trace, and the student is trained via KL-based alignment on the compressed trajectory. This preserves student-policy exploration while injecting teacher-guided compression. Experiments on Qwen3-1.7B show that MPD reduces token usage by up to 27.1% while improving performance across multiple reasoning benchmarks, demonstrating an effective approach to efficient small-model reasoning.

Earth observation is becoming one of the largest data-producing activities in science, yet current pipelines still treat compression as a storage and transmission tool rather than a new way to use data. We present a generative compression framework that learns from historical Earth observation archives and enables on-demand 100x to 10,000x data reduction across downstream tasks. Unlike general visual data, Earth observation repeatedly measures the same evolving planet, making historical-prior learning feasible for extreme compression. To realize this paradigm, we train large generative compression models at exascale on the LineShine Armv9 CPU supercomputer, with co-optimization across model design, kernels, memory hierarchy, runtime, and parallelism. Our implementation sustains 1.54 EFLOP/s and peaks at 2.16 EFLOP/s in end-to-end training. This work shows that historical-prior generative compression can turn Earth observation data into an active, task-adaptive foundation for acquisition, delivery, storage, and scientific use.

Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at $448{\times}448$ resolution already yield >8,000 visual tokens in Qwen3-VL, making LLM prefill the dominant throughput bottleneck. Existing methods often rely on global similarity or attention-guided compression, incurring offsets to their gains. We propose \textbf{Temporal Token Fusion (TTF)}, a training-free, plug-and-play pre-LLM token compression framework that exploits structured temporal redundancy in video. TTF automatically selects an anchor frame, then for each subsequent frame, performs a local window similarity search (e.g.,$3\times 3$), fusing tokens that exceed a threshold. The compressed sequence maintains positional consistency across both prefill and decoding through coordinate realignment, enabling seamless integration with existing VLM pipelines. On Qwen3-VL-8B with threshold t=0.70, TTF removes about 67% of visual tokens while retaining 99.5% of the baseline accuracy and introducing only ${\approx}0.16$,GFLOPs of matching overhead. Overall, TTF offers a practical, efficient solution for video understanding. The code is available at \href{https://github.com/Cominder/ttf}{https://github.com/Cominder/ttf}

When distilling reasoning from large language models (LLMs) into smaller ones, teacher rationales for similar problems often vary wildly in structure and strategy. Like a chef who makes the same dish differently each time, this inconsistency burdens the student with noisy supervision that is hard to internalize. We propose Distillation through Reasoning Path Compression (D-RPC), which constrains the teacher to follow a compact, dynamically maintained bank of reusable high-level reasoning paths. For each training question, D-RPC retrieves the most relevant path and conditions the teacher to follow it, producing rationales that are consistent across similar problems yet diverse enough to cover different problem types. A PAC-Bayes analysis formalizes the resulting trade-off between bank size and coverage: smaller banks reduce supervision entropy but risk coverage gaps, and the generalization bound identifies an optimal intermediate size confirmed by our ablations. Across five math and commonsense reasoning benchmarks with two student models, D-RPC consistently outperforms chain-of-thought distillation, freeform rationale generation, direct distillation, and structured-supervision baselines, while using fewer tokens than template-heavy alternatives.

Video large multimodal models increasingly face a scalability bottleneck: long videos produce excessively long visual-token sequences, which sharply increase memory and latency during inference. While existing compression methods are effective in specific settings, most are either weakly query-aware or apply a fixed compression policy across frames, proving suboptimal when visual evidence is unevenly distributed over time. To address this, we present VideoRouter, a query-adaptive dual-router framework built on InternVL for budgeted evidence allocation. The Semantic Router predicts the dominant allocation policy, choosing between broad temporal coverage and adaptive high-resolution preservation, while the Image Router uses early LLM layers to score frame relevance. This enables aggressive compression on less relevant frames while preserving detail on critical evidence frames. To train both routers, we build Video-QTR-10K for allocation-policy supervision and Video-FLR-200K for frame-relevance supervision. Experiments on VideoMME, MLVU, and LongVideoBench show that VideoRouter consistently improves over the InternVL baseline under comparable or lower budgets, achieving up to a 67.9% token reduction.

Privacy-preserving action recognition (PPAR) enables machines to understand human activities in videos without revealing sensitive visual content. Among the various strategies for PPAR, encryption-based methods achieve strong privacy protection while maintaining high recognition performance. However, these methods lead to a catastrophic decrease in recognition performance and visual quality when the encrypted videos are compressed. That is, the previous methods are not compression-friendly. To address these issues, in this paper, we propose the first compression-friendly encryption method for PPAR, called CFE-PPAR. In CFE-PPAR, videos encrypted with secret keys can be directly recognized by a video transformer, which uses parameters transformed by the same keys as those used for video encryption. In experiments, it is verified that CFE-PPAR outperforms previous methods on the UCF101 and HMDB51 datasets under Motion-JPEG and H.264 compression.

We introduce Telegraph English (TE), a prompt-compression protocol that rewrites natural language into a symbol-rich, formally-structured dialect. Where token-deletion methods such as LLMLingua-2 train a classifier to delete low-importance tokens at a fixed ratio, TE performs a full semantic rewrite: it decomposes the input into atomic fact lines, substitutes verbose phrases with $\sim$40 logical and relational symbols, and lets the compression ratio adapt to each document's information density. A consequence of the line-structure rule is that compression and semantic chunking become the same operation -- each output line is an independently addressable fact, so the compressed representation is simultaneously a semantic index. We evaluate TE on 4{,}081 question-answer pairs from LongBench-v2 across five OpenAI models and two difficulty levels. At roughly 50% token reduction, TE preserves 99.1% accuracy on key facts with GPT-4.1 and outperforms LLMLingua-2 at matched compression ratios on every model and task tested. The gap widens on smaller models -- up to 11 percentage points on fine-detail tasks -- suggesting that explicit relational structure compensates for limited model capacity. We release the grammar specification, compression prompt, benchmark data, and reference implementation.

Scientists increasingly rely on sensor-based data; however transforming raw streams into insights across the edge-to-cloud continuum remains difficult due to the breadth of expertise required to coordinate the necessary data and computation flow. This paper introduces a pattern-based, AI-assisted methodology for rapid development of sensor-driven applications. Using Pegasus workflows executing on the FABRIC testbed, we demonstrate a 5-step development loop that shifts workflow construction and deployment from code-first to intent-first design. Starting from an existing Orcasound hydrophone workflow as a reusable template, we generate and refine workflows for air quality, earthquake, and soil moisture monitoring applications. We further show how these workflows extend to edge resources-including BlueField-3 DPUs and Raspberry Pis-through configuration and placement rather than workflow redesign. Our evaluation, from the perspective of a novice Pegasus user, shows that AI-assisted pattern reuse compresses multi-stage workflow development to 1-1.5 days per workflow while preserving the rigor and portability of workflow-based execution.

Adapting large pretrained models to diverse tasks is now routine, yet the two dominant strategies of parameter-efficient fine-tuning (PEFT) and low-rank compression are typically composed in sequence. This decoupled practice first compresses and then fine-tunes adapters, potentially misaligning the compressed subspace with downstream objectives and squandering a global parameter budget. To overcome this limitation, we introduce JACTUS (Joint Adaptation and Compression with a Task-aware Union of Subspaces), a single framework that unifies compression and adaptation. From a small calibration set, JACTUS estimates input and pre-activation gradient covariances, forms their orthogonal union with the pretrained weight subspace, performs a projected low-rank approximation inside this union, allocates rank globally by marginal gain per parameter, and trains only a compact core matrix. This explicitly mitigates the potential misalignment between the compressed subspace and downstream objectives by coupling the directions preserved for compression with those required for adaptation, yielding a deployable low-rank model that avoids retaining full frozen weights while enabling fast and robust tuning. On vision, JACTUS attains an average 89.2% accuracy on ViT-Base across eight datasets at 80% retained parameters, surpassing strong 100% PEFT baselines (e.g., DoRA 87.9%). On language, JACTUS achieves an 80.9% average on Llama2-7B commonsense QA at the same 80% retained-parameter budget, outperforming 100% PEFT (e.g., DoRA 79.7%) and exceeding prior compress-then-finetune pipelines under the same ratained-parameter budget. We will release code.

Production agent frameworks (OpenAI Function Calling, Anthropic Tool Use, MCP) transmit tool schemas as JSON, a format designed for machine parsing, not for interpretation by language models. For small models (4B-14B), this protocol mismatch accounts for the majority of tool-use failure at production catalog sizes. We present TSCG, a deterministic tool-schema compiler that resolves this mismatch at the API boundary, converting JSON schemas into token-efficient structured text without model access, fine-tuning, or runtime search. TSCG combines eight composable operators with a formal compression bound (>=51% on well-formed schemas). On TSCG-Agentic-Bench (about 19,000 calls, 12 models, 5 scenarios), TSCG restores Phi-4 14B from 0% to 84.4% accuracy at 20 tools (90.3% at 50 tools) and achieves 108-181% accuracy-retained ratio across three models on BFCL. Format-versus-compression decomposition (R^2=0.88 -> 0.03) establishes representation change as the dominant mechanism. Per-operator isolation across three frontier models reveals three distinct operator-response profiles: operator-hungry (Opus 4.7), operator-sensitive (GPT-5.2), and operator-robust (Sonnet 4), providing per-model deployment guidance. Scaling experiments show accuracy advantages persisting on heavy production MCP schemas (+5.0 pp at about 10,500 input tokens) despite saturation on light synthetic catalogs, with 52-57% token savings throughout. The synthetic benchmark generalizes to real MCP schemas within 0.1 accuracy points. TSCG ships as a 1,200-line zero-dependency TypeScript package.

Model quantization has become essential for efficient large language model deployment, yet existing approaches involve clear trade-offs: methods such as GPTQ and AWQ achieve practical compression but are lossy, while lossless techniques preserve fidelity but typically do not accelerate inference. This paper explores the middle ground of statistically-lossless compression through three complementary notions of losslessness for quantized LLMs. First, task-lossless compression preserves zero-shot benchmark accuracy within natural sampling variance and remains achievable at aggressive bitwidths. Second, we formalize the stricter notion of distribution-lossless compression, requiring the quantized model's next-token distribution to be practically indistinguishable from the original, and propose the Expected Acceptance Rate (EAR), the maximum token-agreement probability under optimal coupling, as a directly interpretable fidelity metric (for example, EAR >= 0.99 indicates 99% agreement). Third, we prove a gamma-squared variance law showing that symmetric quantization inflates noise variance by gamma squared relative to asymmetric quantization, making asymmetry necessary for distribution-lossless fidelity but not for task-level preservation. Using SLQ, a layer-wise non-uniform method with asymmetric quantization and wide bitwidth search, we achieve task-lossless compression at well below 4 bits per parameter (as low as 3.3 bits depending on the model), distribution-lossless compression at 5 to 6 bits per parameter on average, and inference speedups of 1.7 to 3.6x relative to FP16 with optimized kernels. Source code is available at https://github.com/IST-DASLab/SLQ.

The deployment of Large Language Models (LLMs) for specialized engineering domains, such as circuit analysis, often faces a trade-off between reasoning accuracy and computational efficiency. Traditional evaluation methods treat model performance as a flat metric, failing to account for the hierarchical nature of engineering knowledge. We propose a performance-aware model compression strategy that utilizes prerequisite graphs to optimize model selection for circuit analysis tasks. By structuring electronics design concepts as Directed Acyclic Graphs (DAGs), we can identify the specific complexity horizons of an LLM's compressed variants' tiers. Our framework introduces an agentic pipeline for generating prerequisite-based datasets and a strategic evaluation engine that dynamically cascades queries across a spectrum of compressed variants of an LLM. This approach allows to select the smallest compressed model, given its conceptual knowledge boundaries in circuit analysis. Experimental results on analog electronics datasets demonstrate that prerequisite graphs provide a granular map of model compression with respect to the performance given circuit analysis complexity. (Source Code: https://github.com/pacomesimon/LLM_prereq_graphs_circuit_analysis, Demo: https://huggingface.co/spaces/pacomesimon/LLM_prereq_graphs_circuit_analysis)

Learning, prediction, and compression are intimately connected: a model that accurately predicts the next symbol in a sequence can be coupled with a source coder to compress that sequence near its information-theoretic limit. When tokenized characters arriving at a fixed reading pace are encoded into variable-length codewords and streamed over a fixed-rate channel, a queue forms whose per-token delay depends on the mean and variance of the bit lengths and on the coder's algorithmic latency. This paper investigates the compression--delay tradeoff that arises when a causal language model serves as the sequential predictor within a predict-then-code architecture for real-time text transmission. Several coding schemes are compared: Shannon (ideal), Huffman, arithmetic coding, rANS at various block sizes, and gzip. The analysis separates algorithmic delay, inherent to the coder, from computational delay, which shrinks as hardware improves. Huffman is the practical choice for over-provisioned channels, with zero algorithmic delay and modest compression overhead. Arithmetic coding achieves near-optimal compression at the cost of decodability delay. Findings are validated across two scales: GPT-2 (124M) and Llama~3.2 (3B), a twenty-five-fold parameter range. This scaling yields an approximately 38% reduction in bits per character, effectively over-provisioning the channel and thereby changing which coder is optimal.

Contemporary systems serving large language models (LLMs) have adopted prefill-decode disaggregation to load-balance between the compute-bound prefill phase and the memory-bound decode phase. Under this design, prefill workers generate a KV cache that must be transferred to decode workers before generation can begin. With these workers residing on different physical systems, this transfer becomes a significant bottleneck to serving LLMs at scale, especially for long-input and agentic workloads. Existing lossless codecs are unsuitable here as they primarily target offline weight compression, run on CPUs, or use variable-length coding whose compression cannot keep up with KV production during prefill. We introduce SplitZip, a GPU-friendly lossless compressor for KV cache transfer that preserves KV tensors bitwise and integrates into existing serving frameworks without modifying model execution. SplitZip exploits redundancy in floating-point exponents of KV activations, encoding frequent exponent values with fixed-length codes and routing rare exponents through a sparse escape stream of (position, value). A calibrated top-16 exponent codebook eliminates online histogramming, while the regular dense path and sparse escape correction make both encoding and decoding efficient on GPUs. On real BF16 activation tensors, SplitZip achieves $613.3$ GB/s compression throughput and $2181.8$ GB/s decompression throughput, outperforming prior lossless compressors on the critical codec path. End-to-end transfer experiments show up to $1.32\times$ speedup for BF16 KV cache transfer, $1.30\times$ speedup for TTFT, and $1.23\times$ increase in Request Throughput. The same approach extends to FP8 KV caches, providing up to $1.14\times$ compression over native E5M2. Code is available at https://github.com/Intelligent-Microsystems-Lab/SplitZip

Training large language models (LLMs) is highly memory-intensive, as training must store not only weights and optimizer states but also intermediate activations for backpropagation. While existing memory-efficient methods largely focus on gradients and optimizer states, activation compression is less well established due to the lack of LLM-tailored theory and guarantees. In this work, we develop a theoretical framework showing that activation compression is safe for linear operators when activation compression is unbiased, but problematic for nonlinear ones. We further derive gradient variance bound and establish convergence guarantees for applying activation compression to all linear operators under the standard $L$-smoothness assumption, showing that it does not change the convergence rate. Guided by the theory, we propose an activation-gradient co-compression method that reuses low-rank activation factors to compress linear-layer gradients without extra computation or additional gradient error. We conduct extensive experiments on Qwen and LLaMA models using a pretraining benchmark and multiple fine-tuning benchmarks to validate our theory and demonstrate competitive performance of our method in both accuracy and compression efficiency. We provide our code in the supplementary material for reproducibility.

Reasoning language models often generate long chain-of-thought (CoT), which accumulates a massive KV cache during the decoding phase and incurs high decoding latency and limited throughput. To address these issues, KV cache compression has emerged as a promising technique for reducing memory overhead by selectively removing unimportant KV pairs while preserving useful ones for subsequent decoding. Nevertheless, we identify two key limitations in existing KV cache compression methods: 1) their threshold-triggered compression policy may provide limited throughput improvement or even reduce throughput, and may fully eliminate KV pairs from certain blocks of the sequence, potentially worsening information loss. 2) they typically retain either isolated KV pairs or fixed-size chunks with rigid boundaries, failing to preserve important flexible-sized chunks at arbitrary token positions. To overcome these limitations, we propose Kara, a sliding-window KV cache compression method that performs decoding-time compression by operating only on the recently generated context. Kara leverages bidirectional attention to score and select informative KV pairs in the window. To enable flexible preservation of important semantic information, we design a Token2Chunk module to expand a subset of selected KV pairs into chunks. Furthermore, we adapt Kara to PagedAttention and develop KvLLM, an inference framework built upon vLLM, which reduces KV cache memory usage and effectively improves output throughput. Extensive experiments demonstrate consistent performance improvements of proposed Kara and KvLLM.

Model merging has attracted attention as an effective path toward multi-task adaptation by integrating knowledge from multiple task-specific models. Among existing approaches, dynamic merging mitigates performance degradation caused by conflicting parameter updates across tasks by flexibly combining task-specific parameters at inference time, thereby maintaining high performance. However, these methods require storing independent parameters for each task, resulting in prohibitive storage overhead. To address this issue, we first experimentally demonstrate that the fine-tuned weight increments (referred to as task vectors) exhibit an impulse-like activation pattern and high robustness to low-bit representations. Driven by this insight, we propose T-Switch, which decomposes task vectors into three compact components: a binary sparse mask, a sign vector, and a scalar scaling factor, achieving high-fidelity approximation at high compression ratios. We then introduce Auto-Switch, a training-free merging scheme that automatically composes task vectors via feature similarity retrieval. Building on this, we develop Auto-Switch, a training-free merging scheme that automatically assembles task vectors through feature similarity retrieval. Furthermore, to transform task vector sparsification and quantization from static rules to adaptive learning, we propose FlexSwitch, a learnable framework which jointly optimizes the compression strategy for each model unit via Learnable Gating Sparsification (LGS) and Bit-width Adaptive Selection (BAS), while employing the Sparsity-Aware Storage Strategy (SASS) to select the optimal storage encoding structure. Finally, by incorporating a K-Nearest Neighbor (KNN) inference scheme with a learnable low-rank metric, we present Auto-FlexSwitch, a dynamic model merging approach that supports highly efficient task vector compression.

Communication has emerged as a critical bottleneck in the distributed training of large language models (LLMs). While numerous approaches have been proposed to reduce communication overhead, the potential of lossless compression has remained largely underexplored since compression and decompression typically consume larger overheads than the benefits of reduced communication traffic. We observe that the communication data, including activations, gradients and parameters, during training often follows a near-Gaussian distribution, which is a key feature for data compression. Thus, we introduce ZipCCL, a lossless compressed communication library of collectives for LLM training. ZipCCL is equipped with our novel techniques: (1) theoretically grounded exponent coding that exploits the Gaussian distribution of LLM tensors to accelerate compression without expensive online statistics, (2) GPU-optimized compression and decompression kernels that carefully design memory access patterns and pipeline using communication-aware data layout, and (3) adaptive communication strategies that dynamically switch collective operations based on workload patterns and system characteristics. Evaluated on a 64-GPU cluster using both mixture-of-experts and dense transformer models, ZipCCL reduces communication time by up to 1.35$\times$ and achieves end-to-end training speedups of up to 1.18$\times$ without any impact on model quality.

Exponential growth in the scale of modern foundation models has led to the widespread adoption of Low-Rank Adaptation (LoRA) as a parameter-efficient fine-tuning technique. However, standard LoRA implementations disregard the varying intrinsic dimensionality of model layers and enforce a uniform rank, leading to parameter redundancy. We propose Post-Optimization Adaptive Rank Allocation (PARA), a data-free compression method for LoRA that integrates seamlessly into existing fine-tuning pipelines. PARA leverages Singular Value Decomposition to prune LoRA ranks using a global threshold over singular values across all layers. This results in non-uniform rank allocation based on layer-wise spectral importance. As a post-hoc method, PARA circumvents the training modifications and resulting instabilities that dynamic architectures typically incur. We empirically demonstrate that PARA reduces parameter count by 75-90% while preserving the predictive performance of the original, uncompressed LoRA across multiple vision and language benchmarks. Code will be published upon acceptance.

The Airborne Collision Avoidance System Xu (ACAS-Xu) relies on large certified Look-Up Tables (LUTs) that encode the exact decision logic used in operation. Neural-network-based approximations have been proposed to reduce memory requirements, but they inherently introduce approximation errors and complicate formal verification. This paper presents a symbolic compression approach based on Binary Decision Diagrams (BDDs) that preserves the exact semantics of the ACAS-Xu LUTs. The resulting representation is canonical, deterministic, and fully equivalent to the original tables, enabling sound and exact reasoning over the complete decision logic. By expressing both the system behavior and domain-specific operational properties within a common Boolean framework, verification reduces to efficient BDD operations and emptiness checks, with precise counterexamples generated when properties are violated. We demonstrate that the proposed BDD-based representation significantly reduces memory usage, achieves predictable and low-latency execution, and can be deployed on embedded platforms. These results highlight BDDs as a compelling alternative for exact, verifiable, and embedded deployment of ACAS-Xu decision logic.

The accelerating adoption of Large Language Models (LLMs) in software engineering (SE) has brought with it a silent crisis: unsustainable computational cost. While these models demonstrate remarkable capabilities in different SE tasks, they are unmanageably large, slow to deploy, memory-intensive, and carbon-heavy. This reality threatens not only the scalability and accessibility of AI-powered SE, but also its long-term environmental sustainability. The research challenge is clear: we must go beyond accuracy and address efficiency and environmental cost as first-class design constraints. To meet this challenge, we introduce Carbon-Taxed Transformers (CTT), a systematic multi-architectural compression principled pipeline ordering inspired by economic carbon taxation principles. Drawing from the economic concept of carbon pricing, CTT operationalizes a computational carbon tax that penalizes architectural inefficiencies and rewards deployment-ready compression. We evaluate CTT across three core SE tasks: code clone detection, code summarization, and code generation, with models spanning encoder-only, encoder-decoder, and decoder-only architecture. Our results show that CTT delivers on inference: (1) up to 49x memory reduction, (2) time reduction up to 8-10x for clone detection, up to 3x for summarization, and 4-7x for generation, (3) up to 81% reduction in CO2 emissions and (4) CTT retains around 98% accuracy on clone detection, around 89% on summarization, and up to 91% (textual metrics) and 68% (pass@1) for generation. Two ablation studies show that pipeline ordering and individual component contributions are both essential, providing empirical justification for CTT's design and effectiveness. This work establishes a viable path toward responsible AI in SE through aggressive yet performance-preserving compression.

Video Capsule Endoscopy (VCE) is a promising method for improving the medical examination of the small intestine in the gastrointestinal tract. A key challenge is their limited size, resulting in a short battery lifetime which conflicts with high energy consumption for image capturing and transmission to an on-body device. Thus, we propose an image compression pipeline that substantially reduces the transmitted data while preserving diagnostic image quality. Furthermore, we exploit characteristics of the compression process to identify frames with low diagnostic value mainly caused by bubbles, without requiring additional image analysis. For low-visibility frames, a dynamic bubble-aware frame rate adaptation strategy reduces image acquisition and transmission during these phases while preserving sensitivity to potential anomalies. The proposed compression and frame rate adaptation are evaluated on a RISC-V platform using the Kvasir-Capsule and Galar datasets. The compression method achieves a compression ratio of 5.748 (82.6%) at a peak signal-to-noise ratio of 40.3 dB, indicating negligible loss of visual quality. The compression accomplished a mean energy reduction of the whole system by 20.58%. Additionally, the proposed bubble-aware frame rate adaptation reduced the energy consumption by up to 40%. These results demonstrate the potential of our method to increase the applicability of VCE.

Handling communication overhead in large-scale tensor-parallel training remains a critical challenge due to the dense, near-zero distributions of intermediate tensors, which exacerbate errors under frequent communication and introduce significant computational overhead during compression. To this end, we propose TACO (Tensor-parallel Adaptive COmmunication compression), a robust FP8-based framework for compressing TP intermediate tensors. First, we employ a data-driven reshaping strategy combined with an Adaptive Scale-Hadamard Transform to enable high-fidelity FP8 quantization, while its Dual-Scale Quantization mechanism ensures numerical stability throughout training. Second, we design a highly fused compression operator to reduce memory traffic and kernel launch overhead, allowing efficient overlap with communication. Finally, we integrate TACO with existing state-of-the-art methods for Data and Pipeline Parallelism to develop a compression-enabled 3D-parallel training framework. Detailed experiments on GPT models and Qwen model demonstrate up to 1.87X end-to-end throughput improvement while maintaining near-lossless accuracy, validating the effectiveness and efficiency of TACO in large-scale training.

Recent large audio language models (LALMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet incur high inference costs. Token compression is an effective method that directly reduces redundant tokens in the sequence. Existing compression methods usually assume that all attention heads in LALMs contribute equally to various audio tasks and calculate token importance by averaging scores across all heads. However, our analysis demonstrates that attention heads exhibit distinct behaviors across diverse audio domains. We further reveal that only a sparse subset of attention heads actively responds to audio, with completely different performance when handling semantic and acoustic tasks. In light of this observation, we propose HeadRouter, a head-importance-aware token pruning method that perceives the varying importance of attention heads in different audio tasks to maximize the retention of crucial tokens. HeadRouter is training-free and can be applied to various LALMs. Extensive experiments on the AudioMarathon and MMAU-Pro benchmarks demonstrate that HeadRouter achieves state-of-the-art compression performance, exceeding the baseline model even when retaining 70% of the audio tokens and achieving 101.8% and 103.0% of the vanilla average on Qwen2.5-Omni-3B and Qwen2.5-Omni-7B, respectively.

Convolutional neural networks (CNNs) have become increasingly difficult to deploy in resource-constrained environments due to their large memory and computational requirements. Although low-rank compression methods can reduce this burden, most existing approaches compress spatial and channel redundancy independently and therefore do not fully exploit the localised structure within convolutional feature maps. This paper proposes a hierarchical spatio-channel low-rank compression framework for CNNs that exploits redundancy across spatial regions and channel activations. Unlike conventional methods, which apply a uniform decomposition across an entire layer, the proposed approach first partitions feature maps into spatial regions, then groups channels according to their co-activation patterns within each region, and finally applies rank-adaptive SVD to each resulting spatio-channel cluster. The method is evaluated on an AlexNet-based brain tumour MRI classification model and compared with Global SVD and Tucker decomposition under $3\times$ and $6\times$ compression budgets. Our method outperforms both baselines, reducing FLOPs from $8.21\,\mathrm{G}$ to $1.55\,\mathrm{G}$ ($81.1\%$ reduction), achieving a $1.38\times$ inference speed-up, and increasing classification accuracy from $87.76\%$ to $89.80\%$. The method also improves the macro $F_1$-score and performance on challenging classes such as meningioma. A hyper-parameter trade-off analysis demonstrates that the framework provides Pareto-optimal configurations, enabling control over the balance between compression and predictive performance. Moderate clustering with adaptive rank selection yields strong results. Bootstrap standard errors are reported for all classification metrics.

Long-context large language models remain computationally expensive to run and often fail to reliably process very long inputs, which makes context compression an important component of many systems. Existing compression approaches typically rely on trained compressors, dense retrieval-style selection, or heuristic trimming, and they often struggle to jointly preserve task relevance, topic coverage, and cross-sentence coherence under a strict token budget. To address this, we propose a training-free and model-agnostic compression framework that selects a compact set of sentences guided by structural graph priors. Our method constructs a sparse hybrid sentence graph that combines mutual k-NN semantic edges with short-range sequential edges, extracts a topic skeleton via clustering, and ranks sentences using an interpretable score that integrates task relevance, cluster representativeness, bridge centrality, and a cycle coverage cue. A budgeted greedy selection with redundancy suppression then produces a readable compressed context in original order. Experimental results on four datasets show that our approach is competitive with strong extractive and abstractive baselines, demonstrating larger gains on long-document benchmarks.

In this work, we developed and tested 3 techniques for vector quantization (VQ) based model weight compression. To mitigate codebook collapse and enable end-to-end training, we adopted cosine similarity-based assignment. Building on ideas from attention-based formulations in Differentiable K-Means (DKM), we further improved this approach by using cosine similarity for assignment combined with top-1 sampling and a straight-through estimator, thereby eliminating the need for weighted-average reconstruction. Finally, we investigated the use of differentiable neural architecture search (NAS) to adaptively select layer-wise quantization configurations, further optimizing the compression process. Although our method does not consistently outperform existing approaches across all quantization levels, it provides useful insights into the design trade-offs and behaviors of VQ-based model compression methods.

Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in information retrieval. However, its reliance on feeding full passage texts into the LLM introduces two critical bottlenecks: the "lost in the middle" phenomenon degrades ranking quality as input length grows, and the inference latency scales super-linearly with sequence length, rendering it impractical for industrial deployment. In this paper, we present ResRank, a unified retrieval-reranking framework that fundamentally addresses both challenges. Inspired by multimodal LLMs that project visual inputs into compact token representations, ResRank employs an Encoder-LLM to compress each candidate passage into a single embedding, which is then fed alongside the query text into a Reranker-LLM for listwise ranking. To alleviate the misalignment between the compressed representation space and the ranking space, we introduce a residual connection structure that combines encoder embeddings with contextualized hidden states from the reranker. Furthermore, we replace the conventional autoregressive decoding with a one-step cosine-similarity-based scoring mechanism, eliminating the generation bottleneck entirely. ResRank is trained through a carefully designed dual-stage, multi-task, end-to-end joint optimization strategy that simultaneously trains the encoder and reranker, achieving learning objective alignment between retrieval and reranking while substantially reducing training complexity. Extensive experiments on TREC Deep Learning and eight BEIR benchmark datasets demonstrate that ResRank achieves competitive or superior ranking effectiveness compared to existing approaches while requiring zero generated tokens and processing only one token per passage, yielding a fundamentally better balance between effectiveness and efficiency.

High-quality digital terrain models derived from airborne laser scanning (ALS) data are essential for a wide range of geospatial analyses, and their generation typically relies on robust ground filtering (GF) to separate point clouds across diverse landscapes into ground and non-ground parts. Although current deep-learning-based GF methods have demonstrated impressive performance, especially in specific challenging terrains, their cross-scene generalization remains limited by two persistent issues: the context-detail dilemma in large-scale processing due to limited computational resources, and the random misclassification of tall objects arising from classification-only optimization. To overcome these limitations, we propose SparseGF, a height-aware sparse segmentation framework enhanced with context compression. It is built upon three key innovations: (1) a convex-mirror-inspired context compression module that condenses expansive contexts into compact representations while preserving central details; (2) a hybrid sparse voxel-point network architecture that effectively interprets compressed representations while mitigating compression-induced geometric distortion; and (3) a height-aware loss function that explicitly enforces topographic elevation priors during training to suppress random misclassification of tall objects. Extensive evaluations on two large-scale ALS benchmark datasets demonstrate that SparseGF delivers robust GF across urban to natural terrains, achieving leading performance in complex urban scenes, competitive results on mixed terrains, and moderate yet non-catastrophic accuracy in densely forested steep areas. This work offers new insights into deep-learning-based GF research and encourages further exploration toward truly cross-scene generalization for large-scale environmental monitoring.

Transformer inference often requires a large KV cache, especially for long-context language modeling and multimodal generation. Existing compression methods usually reduce cache cost by selecting, evicting, quantizing, or compressing cached tokens, or by reducing the visual-token sequence before language-model inference. We introduce sub-token routing, a KV-compression method that adds a finer control axis inside retained tokens. It splits each retained value vector into groups and keeps only selected groups, while leaving query and key states unchanged. The method is designed to work after token-level reduction. First, a token-reduction method determines which tokens are retained. Then, sub-token routing compresses the value states inside those retained tokens. Experiments under matched KV budgets show that adding sub-token routing improves token-level reduction performance in both LLM and VLM settings, including Quest on LLaMA-2-7B and Qwen2.5-7B, and FastV/VisionZip across LLaVA and Qwen-VL models. The gains are larger at smaller KV budgets, suggesting that value-group routing is especially useful when further token removal becomes costly. Overall, token-level reduction and sub-token routing provide complementary ways to reduce KV cost.

Compressing large language models (LLMs) for deployment on commodity GPUs remains challenging: conventional scalar quantization is limited to fixed bit-widths (e.g., 8/4/3-bit), offers only a few discrete compression points, and typically requires calibration data. We present FASQ (Flexible Accelerated Subspace Quantization), a calibration-free framework that applies product quantization to LLM weight matrices. By tuning two parameters, sub-vector size and codebook cardinality, FASQ exposes a continuous design space spanning 27-49% of the original FP16 model size, filling compression gaps that fixed-bit schemes cannot reach. On Meta-Llama-3-8B, FASQ surpasses 4-bit GPTQ and AWQ in accuracy (67.1-67.7 avg.) at 37-42% model size, with consistent results on Qwen3-8B and Qwen3.5-9B-Base. To make product quantization practical at inference time, we design custom CUDA kernels: a LUT-free direct-compute GEMV for decode and an output-stationary double-buffered LUT GEMM for prefill, both with split-K parallelism. On an RTX~3090, FASQ achieves 45.2 tok/s decode at effective 4-bit (2.56x memory reduction) and 51.8 tok/s at effective 3-bit (2.80x), both surpassing FP16 tensor-core performance (43.9 tok/s) and delivering 1.6 to 1.8x the throughput of AWQ, 2.5 to 2.5x of GPTQ, and 4.3 to 5x of RTN. FASQ is the only compressed method that accelerates decode beyond FP16, offering calibration-free compression, continuous size-quality trade-offs, and real-time inference on a single consumer GPU.

We introduce \textbf{AAC} (Architecturally Admissible Compressor), a differentiable landmark-selection module for ALT (A*, Landmarks, and Triangle inequality) shortest-path heuristics whose outputs are admissible by construction: each forward pass is a row-stochastic mixture of triangle-inequality lower bounds, so the heuristic is admissible for \emph{every} parameter setting without requiring convergence, calibration, or projection. At deployment, the module reduces to classical ALT on a learned subset, composing end-to-end with neural encoders while preserving the classical toolchain. The construction is the first differentiable instance of the compress-while-preserving-admissibility tradition in classical heuristic search. Under a matched per-vertex memory protocol, we establish that ALT with farthest-point-sampling landmarks (FPS-ALT) has provably near-optimal coverage on metric graphs, leaving at most a few percentage points of headroom for \emph{any} selector. AAC operates near this ceiling: the gap is $0.9$--$3.9$ percentage points on 9 road networks and ${\leq}1.3$ percentage points on synthetic graphs, with zero admissibility violations across $1{,}500+$ queries and all logged runs. At matched memory, AAC is also $1.2$--$1.5{\times}$ faster than FPS-ALT at the median query on DIMACS road networks, amortizing its offline cost within $170$--$1{,}924$ queries. A controlled ablation isolates the binding constraint: training-objective drift under default initialization, not architectural capacity; identity-on-first-$m$ initialization closes the expansion-count gap entirely. We release the module, a reusable matched-memory benchmarking protocol with paired two-one-sided-test (TOST) equivalence and pre-registration, and a reference compressed-differential-heuristics baseline.

As terminal agents scale to long-horizon, multi-turn workflows, a key bottleneck is not merely limited context length, but the accumulation of noisy terminal observations in the interaction history. Retaining raw observations preserves useful environment feedback, but also leads to context saturation and high token cost; conversely, naive compression may discard task-critical signals needed for subsequent actions. Because terminal environments are highly heterogeneous across repositories, commands, and execution states, heuristic-based or fixed-prompt compression methods are difficult to generalize. We propose TACO, a plug-and-play, training-free, self-evolving Terminal Agent Compression framework for existing terminal agents. TACO automatically discovers, refines, and reuses structured compression rules from interaction trajectories, enabling workflow-adaptive filtering of low-value terminal outputs while preserving task-relevant observations. Experiments on TerminalBench (TB 1.0 and TB 2.0) and four additional terminal-related benchmarks, including SWE-Bench Lite, CompileBench, DevEval, and CRUST-Bench, show that TACO consistently improves task performance and token efficiency across agent scaffolds and backbone models. On TerminalBench, TACO yields 1%-4% accuracy gains across strong agentic models and improves accuracy by around 2%-3% under the same token budget. On additional terminal-related benchmarks, it reduces total token consumption while maintaining or improving task success rates. These results suggest that self-evolving, workflow-adaptive observation compression is an effective path toward more reliable and efficient long-horizon terminal agents. The code is publicly available at https://github.com/multimodal-art-projection/TACO.

Federated fine-tuning of Large Language Models (LLMs) is obstructed by a trilemma of challenges: protecting LLMs intellectual property (IP), ensuring client privacy, and mitigating performance loss on heterogeneous data. Existing methods like Offsite-Tuning (OT) secure the LLMs IP by having clients train only lightweight adapters, yet our analysis reveals they suffer from a fundamental performance bottleneck, leaving a significant gap compared to centralized training. To bridge this gap, we introduce FedProxy, a new federated adaptation framework. FedProxy replaces weak adapters with a unified, powerful Proxy Small Language Model (SLM), compressed from the proprietary LLM, to serve as a high-fidelity surrogate for collaborative fine-tuning. Our framework systematically resolves the trilemma through a three-stage architecture: (i) Efficient Representation via server-guided compression to create a resource-friendly proxy; (ii) Robust Optimization through an interference-mitigating aggregation strategy to handle data heterogeneity; and (iii) Effortless Fusion via a training-free "plug-in" mechanism to integrate learned knowledge back into the LLM. Experiments show FedProxy significantly outperforms OT methods and approaches centralized performance, establishing a new benchmark for secure and high-performance federated LLM adaptation.

Lossy compression is widely used to reduce storage and I/O costs for large-scale particle datasets in scientific applications such as cosmology, molecular dynamics, and fluid dynamics, where clustering structures (e.g., single-linkage or Friends-of-Friends) are critical for downstream analysis; however, existing compressors typically provide only pointwise error bounds on particle positions and offer no guarantees on preserving clustering outcomes, and even small perturbations can alter cluster connectivity and compromise scientific validity. We propose a correction-based technique to preserve single-linkage clustering under lossy compression, operating on decompressed data from off-the-shelf compressors such as SZ3 and Draco. Our key contributions are threefold: (1) a clustering-aware correction algorithm that identifies vulnerable particle pairs via spatial partitioning and local neighborhood search; (2) an optimization-based formulation that enforces clustering consistency using projected gradient descent with a loss that encodes pairwise distance violations; and (3) a scalable GPU-accelerated and distributed implementation for large-scale datasets. Experiments on cosmology and molecular dynamics datasets show that our method effectively preserves clustering results while maintaining competitive compression performance compared with SZ3, ZFP, Draco, LCP, and space-filling-curve-based schemes.

Off-policy learning in constrained MDPs with large binary state spaces faces a fundamental tension: causal identification of transition dynamics requires structural assumptions, while sample-efficient policy learning requires state-space compression. We introduce PI-CMDP, a framework for CMDPs whose constraint dependencies form a layered DAG under a Lifecycle Ordering Assumption (LOA). We propose an Identify-Compress-Estimate pipeline: (i) Identify: LOA enables backdoor identification of causal edge weights for cross-layer pairs, with formal partial-identification bounds when LOA is violated; (ii) Compress: a Markov abstraction compresses state cardinality from 2^(WL) to (W+1)^L under layer-priority regularity and exchangeability; and (iii) Estimate: a physics-guided doubly-robust estimator remains unbiased and reduces the variance constant when the physics prior outperforms a learned model. We instantiate PI-CMDP on constraint repair in engineering simulation pipelines. On the TPS benchmark (4,206 episodes), PI-CMDP achieves 76.2% repair success rate with only 300 training episodes versus 70.8% for the strongest baseline (+5.4 pp), narrowing to +2.8 pp (83.4% vs. 80.6%) in the full-data regime, while substantially reducing cascade failure rates. All improvements are consistent across 5 independent seeds (paired t-test p < 0.02).

KV cache memory is the dominant bottleneck for long-context LLM inference. Existing compression methods each act on a single axis of the four-dimensional KV tensor -- token eviction (sequence), quantization (precision), low-rank projection (head dimension), or cross-layer sharing -- but apply the same recipe to every layer. We show that this homogeneity leaves accuracy on the table: different layers respond very differently to each compression operation, and the optimal per-layer mix of eviction and quantization is far from uniform. We propose MoE-nD, a mixture-of-experts framework that routes each layer to its own (eviction-ratio, K-bits, V-bits) tuple under a global memory budget. An offline-calibrated greedy solver chooses the routing that minimizes predicted quality loss; at inference time, per-layer heterogeneous eviction and quantization are applied jointly through a single attention patch. On a 4-task subset of LongBench-v1 (16k inputs, n=50 per task, adapted reasoning-model protocol; see section Experiments), MoE-nD's hetero variant matches our uncompressed 1.9GB baseline at 14x compression (136MB) while every other compressed baseline we tested (1d, 2d_uniform, 2d) at comparable or smaller memory stays under 8/100. The gains hold on AIME reasoning benchmarks (+6 to +27 pts over the strongest per-layer-quantization baseline across eight configurations). Two null results -- MATH-500 and LongBench's TREC -- share a principled cause (short inputs, solver picks keep=1.0 on most layers), cleanly characterizing when per-layer eviction routing has headroom to help.

This paper investigates communication-efficient neural network transmission by exploiting structured symmetry constraints in convolutional kernels. Instead of transmitting all model parameters, we propose a degrees-of-freedom (DoF) based codec that sends only the unique coefficients implied by a chosen symmetry group, enabling deterministic reconstruction of the full weight tensor at the receiver. The proposed framework is evaluated under quantization and noisy channel conditions across multiple symmetry patterns, signal-to-noise ratios, and bit-widths. To improve robustness against transmission impairments, a projection step is further applied at the receiver to enforce consistency with the symmetry-invariant subspace, effectively denoising corrupted parameters. Experimental results on MNIST and CIFAR-10 using a DeepCNN architecture demonstrate that DoF-based transmission achieves substantial bandwidth reduction while preserving significantly higher accuracy than pruning-based baselines, which often suffer catastrophic degradation. Among the tested symmetries, \textit{central-skew symmetry} consistently provides the best accuracy-compression tradeoff, confirming that structured redundancy can be leveraged for reliable and efficient neural model delivery over constrained links.

Long Chain-of-Thought (CoT) reasoning is pivotal for the success of recent reasoning models but suffers from high computational overhead and latency. While prior works attempt to compress CoT via external compressor, they often fail to align with the model's internal reasoning dynamics, resulting in the loss of critical logical steps. This paper presents \textbf{C}ompressing \textbf{R}edundancy in Chain-of-Thought via \textbf{I}ntrinsic \textbf{S}aliency \textbf{P}runing (\textbf{CRISP}), a framework that compresses CoT by exploiting the model's intrinsic saliency. Our analysis reveals a distinct phenomenon: the reasoning termination token \texttt{[object Object]} acts as an information anchor, where its attention pattern effectively demarcates essential reasoning from redundancy. Based on this finding, we design a policy that utilizes these intrinsic attention signals to guide atomic compression operations. In contrast to coarse-grained pruning strategies, CRISP strategically distills the reasoning chain to maximize information density while preserving logical coherence. Empirical results across various backbone models and mathematical datasets demonstrate that CRISP achieves a 50-60% reduction in token count without compromising accuracy, effectively mitigating the efficiency bottleneck of long-context reasoning. We open-source our implementation to facilitate further research in efficient reasoning.

The spectral kernel field equation R[k] = T[k] lacks a conservation-law analog. We prove (i) the fixed-point flow is strictly volume-expanding (tr DF > 0), precluding automatic conservation, and (ii) the conservation deficit per mode equals the Hessian stability margin exactly: D_m = -Delta'. Closing the deficit requires a scene-side compensating contribution, which we formalise as the distinction dynamics equation dc/dt = G[c, h_t], with MaxCal-optimal realisation G_opt. On fixed-topology 3D surface graphs we derive a conditional topology-preserving compression theorem: retaining k >= beta_0 + beta_1 modes (under a spectral-ordering assumption) preserves all Betti-number charges; we include a worked short-cycle counterexample (figure-eight) calibrating when the assumption fails. A triple necessary spectral diagnostic -- Fiedler-mode concentration, elevated curl energy, anomalous beta_1 -- is derived for planetary drainage networks at O(N) cost. Two internal real-data sequences serve as preliminary consistency checks; full benchmarks and adaptive-topology extensions are deferred.