Search: “memory-compression”

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

BeaconKV introduces training-free KV cache compression using beacon queries, cutting long-reasoning inference memory up to 5.8x while preserving accuracy.

The paper shows recency-based KV cache compression assumptions fail in long-horizon reasoning because Thought Revisiting Tokens (TRT) re-attend to distant context such as early task-solving plans. TRT queries cluster into a small number of similarity groups, which BeaconKV exploits by maintaining compact beacon query representatives to anticipate revisited KV pairs without storing full query history. The training-free method achieves up to 5.8x memory reduction and over 4.3x throughput improvement across four open-source large reasoning models while nearly preserving full cache accuracy.

Hugging Face daily papers·Sep 3, 20:00 UTC · 12d agoAI research1

33

SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models

SimpleMemVLA passes full timestamped video history straight to a VLA backbone, setting state of the art on four memory benchmarks.

SimpleMemVLA is a vision-language-action model for long-horizon manipulation that removes the dedicated memory module entirely. It keeps sampled history intact and feeds it to the backbone as timestamped video, with the hidden states of a generated sub-task serving as the only channel into a standard flow-matching action head. Prefilling the shared history prefix during action execution keeps latency close to a single-frame VLA. The system sets a new state of the art on four memory benchmarks and outperforms retrieval, compression and recurrent-state mechanisms, with causal interventions confirming the policy genuinely reads its history.

Hugging Face daily papers·Sep 1, 20:00 UTC · 14d agoAI research

25

Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging

Systematic study finds model pruning causes frequency-dependent long-tail forgetting in medical imaging and that gradient-informed methods best preserve explanations.

Across two long-tailed medical imaging datasets, two CNN architectures, four pruning methods, and sparsity up to 95%, the study measures predictive performance, explanation stability, and faithfulness. Rare classes degrade earlier and more severely than frequent ones, while explanation reliability depends mainly on the pruning strategy, with gradient-informed methods degrading least. Mechanistic analysis ties explanation collapse to loss of class-discriminative gradients rather than vanishing feature activations, recommending class- and explanation-aware evaluation of compression.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 17:44 UTC · 8d agoAI research

27

SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions

SQS unifies weight pruning and low-bit quantization via Bayesian variational learning, compressing Llama3.2 and Qwen2.5 at higher rates with comparable accuracy.

SQS introduces a unified Bayesian variational framework performing simultaneous pruning and low-bit quantization, using a spike-and-slab prior for sparsity and Gaussian Mixture Models to model quantized weights. The authors derive an efficient approximation for the intractable objective and provide a consistency result for the variational approach. Experiments on ResNet, BERT-base, Llama3.2, and Qwen2.5 show higher compression rates than prior baselines with comparable performance drops.

Hugging Face daily papers·Sep 6, 20:00 UTC · 9d agoAI research

28

Memory-Efficient Designs for Word-Wise Universal Fully Homomorphic Encryption

BXT framework mitigates FHE memory bottlenecks via ciphertext compression, serialization, delayed seeding, and digit pruning, achieving up to 3.8x CNN inference speedup.

A new paper proposes BXT, an optimization framework for word-wise Universal Fully Homomorphic Encryption that targets the memory bottleneck rather than compute. It combines four techniques: ciphertext compression via seed regeneration, bit-packed ciphertext serialization for L2-to-L1 transfers, delayed PRNG-heavy offline seed generation across aggregated operations, and fault-aware ciphertext digit pruning. On CNN inference, the BXT-CSO50 configuration achieves up to 3.8x speedup over a 100x GPU baseline with under 1% accuracy loss at 50% comparison precision.

arXiv cs.CR·Sep 4, 06:03 UTC · 12d agoResearch

24

Bias-Induced Crossover in Absolute Capacity of Dense Associative Memory

Analysis shows biased patterns cut dense associative memory capacity from N^(n-1)/ln N to O(N^(n/2)), with a bias-induced crossover.

The paper analyzes dense associative memory capacity for biased centered binary patterns under the Krotov-Hopfield single-site criterion. Unbiased patterns (q=1/2) with order-n polynomial interactions yield capacity of order N^(n-1)/ln N, while fixed bias q<1/2 reduces capacity to O(N^(n/2)) for even n>=4 and O(N^((n+1)/2)) for odd n>=5. A bias-dependent crosstalk mean destabilizes sites carrying the frequent value, and an activity-dependent control potential restores the higher capacity within the conditioned-Gaussian approximation.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 17:16 UTC · 17h agoAI research

12

Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs

A survey catalogs inference-efficiency techniques for video and audiovisual LLMs, mapping bottlenecks in sampling, encoding, token reduction, and LLM decoding.

This survey covers inference-efficiency mechanisms for visual and audiovisual video LLMs, reporting reductions in parameters, FLOPs, latency, memory, and token counts. It organizes methods by pipeline stage, covering frame sampling, modality encoding, connector-level token reduction, and LLM prefilling and decoding for systems built since late 2022. The authors compile accuracy-cost comparisons under shared host models and input protocols, identify gaps in audiovisual efficiency and standardized evaluation, and maintain a public repository.

Hugging Face daily papers·Sep 8, 20:00 UTC · 7d agoAI research

40

LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs

LACE introduces layer-wise compression for dynamic frame rate audio codecs, cutting sequence lengths and speeding TTS inference while preserving quality.

LACE (Layer-Adaptive Codec Encoding) applies an independent compression step at each quantization layer of a neural audio codec, enabling layer-specific segmentation boundaries instead of shared ones. Union alignment and boundary anchor mechanisms keep durations consistent for downstream text-to-speech. On LibriTTS, LACE achieves a better rate-quality tradeoff than prior dynamic frame rate codecs and improves TTS inference efficiency at competitive synthesis quality. Code is released in the ESPnet3 codec recipe.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 17:46 UTC · 16h agoAI research

15

Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability

A controlled study finds agent memory portability varies sharply: fixed-schema knowledge graphs survive model swaps while compressed notes degrade.

The study compares preserving an agent's history as raw long context, RAG chunks, compressed natural-language notes, or fixed-schema knowledge graphs across model upgrades, using 48 synthetic histories and two open-weight sub-10B-parameter models. Fixed-schema KG accuracy changed by only +0.0004 ± 0.0020 after a writer swap, while compressed NOTES shifted asymmetrically by +9.91 or -13.28 percentage points depending on migration direction. Mixed 50/50 embedding migrations captured only 4.96 of an 11.90-point RAG re-embedding gain; 80% of the NOTES deficit came from information lost at construction, and 81% of the RAG deficit from retrieval failures. Store-only repair of NOTES failed to reach 90% recovery in all 48 cases, while retaining raw histories enabled recovery in 34 of 48 for one direction.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 16:44 UTC · 11d agoAI research

32

The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements

Researchers derive sufficient sample-size conditions for recovering sparse binary signals from sparse Gaussian measurements, quantifying an information-theoretic threshold of order slog(p/s)/log(ds/p).

The paper studies support recovery of sparse binary signals from noisy linear measurements. For sparse Gaussian designs, the authors identify sufficient minimal sample sizes for maximum-likelihood recovery in the high-SNR regime d*s/p -> infinity, yielding an information-theoretic threshold of order slog(p/s)/log(ds/p) that makes the price of measurement sparsity explicit. They also show a regime where the sample-complexity loss from sparsity is only logarithmic while computational gains are nearly linear, and prove that for independently sparsified dense Gaussian designs a sample size of order p/ψ² suffices for support recovery at any fixed error level.

Hugging Face daily papers·Sep 7, 20:00 UTC · 8d agoAI research

12

A Princeton Researcher Proposes Recurrent Looped Transformer (RLT) that Carries Decoder State across Every Token, Fixing 96 Blocks per Token with Unbounded Temporal Depth

Princeton researcher Yifan Zhang proposes Recurrent Looped Transformer, carrying full decoder state across every token for unbounded temporal depth.

Yifan Zhang's technical report defines the Recurrent Looped Transformer (RLT), pairing a causal encoder with a recurrent decoder whose final output and layerwise sliding-window attention cache carry into every subsequent token with no prompt-response boundary reset. The reference configuration ties 48 encoder and 48 decoder layers, executing 96 logical blocks per token while the state path grows to 48t blocks after t tokens at fixed per-token compute. The report details RL replay contracts that rebuild all states under current parameters and exact prefix snapshots for multi-turn serving, but explicitly reports no measured efficiency, reasoning quality, or scaling results.

MarkTechPost·Sep 13, 17:02 UTC · 2d agoAI research1

40

Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction

Grouped Value Attention stores grouped values and reconstructs content keys via a learned linear map, cutting KV-cache size about 45-47% versus GQA.

GVA stores only grouped values and reconstructs content keys with a learned linear map absorbed into the query at decode time, while a small shared decoupled RoPE channel preserves positional information via a separately cached positional key. At 350M parameters trained on 30B FineWeb-Edu tokens, the 16-dimensional positional variant scores 44.18 average accuracy across five tasks versus 44.36 for GQA and 43.88 for MLA. Custom decoding kernels are in development with an open-source release planned.

Hugging Face daily papers·Sep 7, 20:00 UTC · 8d agoAI research

42

Generative Late-Interaction Embeddings For Visual Document Retrieval

GLIE compresses visual document retrieval embeddings to four vectors per page while retaining nearly 80% of uncompressed nDCG@5 accuracy.

Researchers analyzing late-interaction retrieval embeddings found they lie exactly on the unit sphere and concentrate near a manifold of intrinsic dimension five to six. GLIE learns a few k vectors per page that serve as a lightweight index and a basis to regenerate the full embedding set for exact rescoring of top candidates at query time. On ViDoRe v1 with four vectors per page, GLIE retains nearly 80% of uncompressed nDCG@5 versus 70% for the best prior post-hoc method, using a 415K-parameter network trained in under three GPU-minutes on 1,000 pages.

Hugging Face daily papers·Sep 9, 20:00 UTC · 6d agoAI research

28

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

Hugging Face published a tutorial on training and finetuning multi-vector embedding models using the Sentence Transformers library.

Hugging Face's blog walks through training and finetuning multi-vector embedding models with Sentence Transformers. Multi-vector approaches store multiple vectors per document to support late-interaction retrieval. The post is a practical guide for developers building retrieval pipelines with the library.

Hugging Face Blog·Aug 26, 00:00 UTC · 21d agoAI tools & infra1

20

Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout

Researchers propose Mask Forcing, a dual-noise masking rollout that mitigates mode collapse in autoregressive video diffusion distillation.

The paper targets over-saturation and over-smoothing in autoregressive video diffusion models distilled via Distribution Matching Distillation, attributed to reverse-KL mode-seeking behavior. Mask Forcing perturbs the student self-rollout with random masks along spatial and temporal axes, injecting cleaner tokens that act as denoising guidance for noisier tokens. Experiments show improved visual quality across multiple distillation methods without using real video data or extra post-training stages.

Hugging Face daily papers·Sep 7, 20:00 UTC · 8d agoAI research

22

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Composing data, function, and weight anchors with merged LoRA raises 100-task long-horizon retention from 1.2% to 34.9% in continual fine-tuning.

The paper introduces long-horizon memorization: a model learns 100 query-answer tasks through continual supervised fine-tuning without retaining earlier examples or receiving task identifiers at inference. No single continual learning mechanism maintains strong retention at this horizon, so the authors compose complementary mechanisms along data/function/weight anchors and low-rank allocation rules. The best method combining all three anchors with merged LoRA ranks among the top 3 methods on all three datasets and raises average final retention from 1.2% to 34.9%, a 28-fold improvement.

Hugging Face daily papers·Sep 6, 20:00 UTC · 9d agoAI research

42

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

NVIDIA researchers detail an end-to-end system for online draft co-training that speeds speculative decoding in large-scale long-context RL post-training.

The paper tackles scaling online draft co-training for speculative decoding in RL post-training, where rollout generation dominates cost. It extends packed, load-balanced zigzag ring attention to merge rank-local branch attention with causal main-sequence attention for context parallelism, and introduces TapChannel to transport target features across pipeline-parallel stages without changing the schedule. Experiments show co-trained drafts tracking the policy baseline with substantial rollout and end-to-end speedups up to 122B parameters and strong scaling at 256K tokens.

Hugging Face daily papers·Sep 6, 20:00 UTC · 9d agoAI research

26

MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents

MeClear uses cooperative Shapley attribution to clear harmful memories from long-horizon LLM agents, boosting task recovery by 25.5 points over baselines.

The paper introduces MeClear, a task-conditioned memory clearance framework for long-horizon LLM agents that identifies and selectively suppresses memories with negative downstream utility without permanently altering the persistent memory bank. It combines Leave-One-Out screening with sampled cooperative Shapley attribution to distribute utility across interacting evidence, resolving redundant conflict masking that single-removal evaluations miss. Across ten long dialogue memory pools it achieves 85.9% target recall and 82.3% overall task recovery, a 25.5 percentage-point improvement over LOO baselines.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:46 UTC · 7d agoAI research

32

Rethinking Heterogeneous System Disaggregation for Subquadratic Attention

SQD disaggregates LLM inference by quadratic versus subquadratic attention layers, improving energy efficiency up to 56% on heterogeneous systems versus GPU-only baselines.

SQD (SubQuadratic Disaggregation) splits decode not by operator type but by quadratic versus subquadratic attention, matching their distinct arithmetic intensity and memory footprints. For sparse attention LLMs it separates top-k selection (requiring full KV indexing) from top-k attention plus FFN; for linear and sliding-window models it separates dense attention layers from subquadratic layers plus FFN. On an adjusted 8xB200 heterogeneous proxy, tokens-per-joule improves 53% on GLM 5.2, 31% on Nemotron 3 Ultra, and 56% on Gemma 4 31B. A Rubin plus LPX analytical model shows 1.2x-1.5x tighter achievable latencies and up to 3.6x higher throughput versus attention-FFN disaggregation.

arXiv cs.AI / cs.LG / cs.CL·Sep 11, 17:55 UTC · 4d agoAI research

28

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

Multiverse Computing details quantization-aware healing, producing a 4-bit compressed model that reportedly outperforms its full-precision original.

A Hugging Face blog post by Multiverse Computing's CAI team introduces quantization-aware healing for compressed models. The post claims the resulting 4-bit model outperforms the original full-precision model. No additional details or benchmarks were available in the provided text.

Hugging Face Blog·Aug 25, 11:39 UTC · 21d agoAI research

40

Studying Image Tokenizers as Visual Languages in Unified Multimodal Models

A controlled pure-autoregressive testbed shows task-specific validation losses rank image tokenizers differently, with I2T loss the most consistent signal.

Researchers built a controlled pure-autoregressive testbed and tracked task-specific validation losses during multimodal continual pretraining across text, image, text-to-image (T2I), and image-to-text (I2T) prediction. They find losses should be analyzed per task because they exhibit distinct scaling behavior and rank tokenizers differently, and that the loss-performance relationship depends on the predicted token space. I2T loss, computed over a shared text vocabulary, correlates consistently with both generation and visual understanding performance after supervised finetuning. Case studies revisit the discriminator, semantic supervision, and vocabulary size as tokenizer design axes.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:57 UTC · 7d agoAI research1

30

The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding

Researchers introduced Brain2Semantics2Text, decoding sentence meaning from non-invasive MEG brain recordings via a semantic bottleneck, improving on prior Brain2Text methods.

The paper proposes Brain2Semantics2Text, a non-invasive speech decoding method that maps sentence-level magnetoencephalography (MEG) responses into a semantic embedding space and inverts those embeddings into natural language. Motivated by evidence that high-level semantic representations are distributed across cortex and evolve on slower timescales, the approach targets meaning rather than phonemes or words, avoiding the need for word-level alignment. The authors report improved sentence-level results compared to prior non-invasive Brain2Text methods despite the low signal-to-noise ratio of neural recordings.

Hugging Face daily papers·Sep 8, 20:00 UTC · 7d agoAI research2

25

ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation

ReMoMask-2 rebuilds retrieval in the generator's latent space for text-to-motion generation, achieving lowest FID on KIT-ML and SnapMoGen.

ReMoMask-2 is a retrieval-augmented text-to-motion framework that constructs its retrieval database directly in the generator's pre-quantization latent space and aligns text queries through a distilled lightweight projector, eliminating the representation gap. The framework combines Hierarchical Bidirectional Momentum contrastive learning, Semantic Spatial-Temporal Attention, and Topology Structured Masking to handle hierarchical motion structure. The retriever achieves state-of-the-art accuracy, and ReMoMask-2 attains the lowest FID on KIT-ML and SnapMoGen, with a single mask-transformer stage outperforming the previous two-stage pipeline while delivering the fastest inference.

Hugging Face daily papers·Sep 7, 20:00 UTC · 8d agoAI research

25

Pre-Whitening and BCJR Posterior Distillation for Bi-LSTM Detection in Faster-than-Nyquist Signaling

Study shows nested-window Bi-LSTM architectures do not improve faster-than-Nyquist detection; pre-whitening plus BCJR distillation cuts bit error rates.

Across roughly 260 controlled trainings, processing nested intersymbol-interference windows in separate recurrent branches never significantly beat a plain Bi-LSTM at matched parameter budgets. The authors attribute the limitation to the observation model rather than architecture, and instead pre-whiten inputs and distill BCJR soft posteriors into the network. With 3.4% more parameters, the method reaches 1.05x the BCJR bit error rate at compression factor 0.8 and 1.89x at 0.7, improving to 1.47x with a wider whitened window.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 17:07 UTC · 8d agoAI research

10

Studying Image Tokenizers as Visual Languages in Unified Multimodal Models

A controlled autoregressive testbed shows validation losses must be analyzed per task, and image tokenizer choice affects joint multimodal text modeling.

Researchers built a pure-autoregressive testbed to study image tokenizers as the 'visual language' of unified multimodal models, tracking task-specific validation losses during multimodal continual pretraining across text, image, text-to-image (T2I), and image-to-text (I2T) prediction. They found that losses exhibit distinct scaling behavior per task and rank tokenizers differently, and that I2T loss over a shared text vocabulary gives a more consistent loss–performance signal than T2I loss. Better reconstruction does not necessarily yield lower task-specific losses or stronger downstream performance, and tokenizer choice can affect text modeling under joint optimization. Case studies examine the discriminator, semantic supervision, and vocabulary size design axes.

Hugging Face daily papers·Sep 7, 20:00 UTC · 8d agoAI research1

40

Measuring benchmark optimization in speech recognition

Hugging Face examines how much speech recognition systems overfit benchmarks and how to measure benchmark optimization in ASR.

A Hugging Face post on measuring benchmark optimization in automatic speech recognition, analyzing how model improvements on benchmarks reflect genuine capability gains versus overfitting. It is evaluation methodology research with no direct security impact.

Hugging Face Blog·Aug 21, 00:00 UTC · 26d agoAI research

22

Disentangling Representation Evolution in Transformers through Directional Decomposition

Decomposes transformer representation updates into parallel and perpendicular components, linking geometry to editing robustness and better pretraining.

The paper decomposes learned transformer updates into parallel and perpendicular components relative to the hidden state, finding substantial parallel components beyond the residual identity path across pretrained models. Targeted edits reveal exclude-self value-space parallel manipulation is more robust than residual-space or perpendicular alternatives, and perpendicular error separates compression methods more clearly. Applying full-aggregate parallel suppression during from-scratch pretraining lowers validation loss and improves downstream averages, with the value-space variant strongest. Code is released on GitHub.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 17:56 UTC · 1d agoAI research 2 sources1

35

Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents

Researchers propose provenance-guided selective replay letting LLM agents forget revoked information without restarts, matching full reset behavior.

The paper formalizes execution-state unlearning for stateful LLM agents, requiring that agents behave as if a revoked memory record was never observed across transcripts, compressed memory, tool plans, and KV caches. It proves exact unlearning requires at least T-τ+1 recomputed transitions and that Provenance-Guided Selective Replay attains this bound via a provenance graph, KV cache cropping, and sanitized replay. In audits across three agent suites, nine baselines, and three model families, memory deletion left leakage unchanged, instruction-based forgetting collapsed under elicitation (Leak@probes = 1.00), and selective replay matched full resets at up to 9x fewer recomputed tokens.

arXiv cs.CR·Sep 4, 08:31 UTC · 12d agoAI safety & security1

42

PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control

PhysStream autoregressive video model enables physics-grounded mid-generation motion control, cutting trajectory error 12% and FVMD 33% versus strongest baselines.

PhysStream is an autoregressive image-to-video model that incorporates structured scene memory—positional maps and object tracking maps derived online from previously generated frames—and supports fine-grained motion control via sparse velocity-increment signals encoding physical quantities. Training proceeds in two stages: a bidirectional model finetuned with motion-control conditioning, then a causal autoregressive model with scene memory. It reduces motion distribution distance (FVMD) by 33% and trajectory error by 12% over the strongest baselines, and human evaluators prefer it in over 85% of in-the-wild comparisons.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 17:55 UTC · 16h agoAI research 2 sources

25

OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution

OracleZoom enables recursive extreme-scale image super-resolution via reference-constrained on-policy distillation, reducing hallucinations at deep zoom scales.

OracleZoom tackles recursive super-resolution, where repeated feeding of predictions back into the same model leaves deeper-scale outputs unsupervised as required source resolution grows geometrically. The framework trains on its own trajectory while carrying the last ground-truth evidence beyond the supervision boundary, combining direct and cross-scale supervision, a no-reference quality objective, a KL-constrained pretrained latent prior, and EMA consistency. Across seven datasets it achieves state-of-the-art SR quality across zoom scales, averaging 0.713 CLIPIQA with larger gains at deeper scales and significantly reduced hallucinations. Code, data, and models are publicly released.

Hugging Face daily papers·Sep 5, 20:00 UTC · 10d agoAI research

20