Embedding
-
How Much Physics Can Vision Learn from Audio? Probing and Distilling Damping Structure
2026-10-15 17:03:14Zainab Afolabi, Vadim Selyutin, Zhao Gao, Babs Khalidson, Mohamed GhoneimAbstract
Physical understanding is crucial for decision making, yet vision models struggle to infer properties such as damping that govern how materials behave. Audio encodes such properties directly, because an object's acoustic response to impact reveals its damping through measurable decay. We probe frozen encoders for the quality factor $Q$, a dimensionless measure of how many oscillations an object completes before its ring dies away, and report how well each embedding orders impacts by $Q$ using the Spearman rank correlation $\rho$, for which $\rho=1$ is a perfect ordering and $\rho=0$ an unrelated one. Audio embeddings reach $\rho=0.73$ and retain most of that advantage on materials withheld from training, while a single video frame taken at the moment of impact, encoded by CLIP, supports only $\rho=0.28$. Having established where the signal lives, we ask how much of that gap vision can recover. We distill a frozen audio teacher into a frozen CLIP backbone through a trained projection head and find that this recovers a useful fraction of the audio advantage. Because pooled correlations on this task are dominated in practice by category identity, we also evaluate under a leave-one-material-out protocol in which the held-out material is withheld from the projection head as well as the probe. Distillation with a four-frame input improves the correlation there from 0.234 to 0.338 (+0.053 over the matched four-frame baseline, 14 of 17 materials), a gain that no category-level strategy can produce. Widening the visual input to four frames spanning the impact supplies half of that improvement at no acoustic cost, which indicates that part of what a single frame misses is visible dynamics.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22221
PDF
-
Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics
2026-10-15 16:29:27Jian Gu, Hongyu Zhang, Chunyang Chen, Aldeida AletiAbstract
The vocabulary of a language model is its native semantics: the embedding and the unembedding fix the meaning of a state at the two ends of the residual stream. Between them, existing methods either reuse a fixed lens or treat the states as a point cloud, and neither reads a state the way the model does. We argue that every hidden state has a native reference frame, induced by the layers that read it next and adaptive to the context. Lexical reference frames approximate it by reading a state through the model's own remaining layers with a stated number of rounds of attention between positions and a typical attention output for the rest, without fitting to the model's output. No lens, with fixed directions per layer, can exceed the square root of the native frame's coherence, 0.30 and 0.35 at mid-depth of SmolLM3-3B and OLMo3-7B, whereas the first-order frame, LexFrame[1], reaches 0.97 and 0.97 and reads a state within 0.16 nats of the model's output. Its coefficients attribute predictions more faithfully than attribution patching, its lexical basis steers a prediction while sparing other tokens, and its confident readings would let an early exit skip 0.45 and 0.42 of the layers, where lenses skip almost none. In this way, lexical reference frames make every hidden state of the model readable, attributable and steerable.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22169
PDF
-
Unfragmenting Nawatl NMT: Single-Variant Specialization for Masewalkopa
2026-10-15 15:51:41Luis A. Mercado-Campos, Alexis PalmerAbstract
In minoritized (low-resource) language technologies, a common response to data sparsity is to aggregate text across multiple varieties and treat the combined data as a single corpus. However, mixed corpora of closely related indigenous variants can produce an artificial register that is accountable to no single speaker community, a structural failure we call variant fragmentation. This issue is acute for minoritized languages native to Mexico, such as Nawatl. Building on a 70,000-pair multi-variant foundation, we specialize an mT5-large checkpoint to Masewalkopa (nhn), the Nawatl variety spoken in Santa Ana Tlacotenco. We curate 2,665 parallel pairs, reserve all sentence-level data for evaluation, and incorporate 192 elder-transcribed target sentences via asymmetric backtranslation. A custom finite-state analyzer reduces unanalyzed surface forms from 82.0% to 19.9% and supplies functional syntax tags as plain-text prefixes, allowing the model to reuse existing subword embeddings rather than relying on frozen special tokens. The resulting LoRA-v9c-b model achieves 58.46 dev chrF++ and 58.20/57.90 directional test chrF++. Finally, CTranslate2 int8 quantization reduces CPU latency from 137.5 to 1.8-2.6 seconds per request, enabling cost-bounded Cloud Run deployment.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22110
PDF
-
Decoding Naturalistic Speech from fMRI with Temporal Modeling and Multimodal Alignment
2026-10-15 15:17:15Corentin Caris, Louis Jalouzot, Nona Rajabi, G\'eraud Ilinca, Ahmed Hassayoune, Asilbek Muminov, Thadd\'ee Delebarre, Clara Fonteneau, Charles Maussion, Bertrand Thirion, Alexis Thual, Antoine CollasAbstract
Reconstructing what a person perceives from their brain activity is a stringent test of whether neural recordings carry meaningful information. Naturalistic speech offers a rich testbed for this challenge: it unfolds over multiple timescales, but fMRI's noisy, temporally smeared measurements make this structure hard to recover. We introduce NOEMA, a temporal convolutional decoder that aligns windows of consecutive fMRI measurements with multimodal stimulus embeddings. These embeddings combine complementary text, audio, and speech representations of the same stimulus segment, enabling its retrieval directly from brain activity. On two naturalistic speech datasets, Cephalonauts One and LeBel, NOEMA retrieves the correct segment among 2,000 candidates within the top 10 for more than 42% of held-out queries. This substantially outperforms baseline decoders, an advantage that persists when the candidate pool is extended with thousands of distractors absent from training. Controlled ablations establish the contributions of temporal modeling and complementary stimulus representations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22049
PDF
-
N-Gram Memories at Two Bits: Quantizing Lookup Tables in Large Language Models
2026-10-15 12:57:19Donghoon Han, Minseop Jung, Dong Woo Kwak, SeungJae Lee, Junhoo LeeAbstract
Conditional memory expands language-model capacity through selective lookup, but the full embedding table must remain available for every possible input. We introduce Conditional Program (CP), a compressed representation that reconstructs only the rows an input requests. CP represents each row by a short code and a local scale, with a reconstruction program shared across the table. We instantiate this representation with a Gaussian trellis, norm restoration and independently decodable row records. CP's two-bit code lowers output KL by 41--63\% relative to 2-bit round-to-nearest. Analysis across three trained n-gram memory families shows that Gaussian-like coordinate statistics coexist with learned relationships among rows; at matched storage budgets, the shared trellis outperforms the fitted codebooks and low-rank residual variants we test. For DeepSeek, it reduces table storage from 203GB to 51GB, leaving room for larger workloads when the table is kept on GPU.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21810
PDF
-
CIM-Embed: Learning Instruction-Conditioned Multimodal Embeddings for Clustering
2026-10-15 12:54:17Yinghua Xu, Pengyang Xie, Yanxiang Zhou, Chuanzhi Tong, Xiao Xiao, Chaoqun Feng, Xiaoqing WangAbstract
Multimodal objects can require different partitions under different instructions, as when products in an e-commerce catalog are grouped by color, material, or both. Retrieval-oriented embeddings may not recover these partitions, while generative clustering often relies on intermediate descriptions or iterative decisions. This paper presents CIM-Embed, a framework for learning instruction-conditioned multimodal embeddings for clustering. Supervised contrastive learning uses same-group positives and negatives from other groups, optionally including other tasks; heterogeneous structured batches accommodate tasks with different group counts. At inference, the model maps each object's image, text, and instruction directly to an embedding; HDBSCAN then forms a partition without the ground-truth cluster count. We construct ProductMIC from product metadata in Amazon Reviews 2023, comprising training data and an evaluation benchmark for instruction-conditioned clustering. The benchmark contains 5,373 products and 449 single-attribute and compositional grouping tasks spanning 50 leaf categories excluded from our training. With full-dimensional embeddings and HDBSCAN, direct within-task SupCon training achieves a mean per-task V-measure of 95.01, compared with 53.06 for WeMM 9B, the strongest general-purpose embedding baseline evaluated. Frozen product-trained encoders also improve out-of-domain conditional grouping, while controlled transfer experiments distinguish partition transfer from instruction response. We will release the code and dataset upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21805
PDF
-
FuseAdapt: Parameter-Efficient Multimodal Fusion for Semantic Segmentation with Missing Modalities
2026-10-15 12:36:38Xin Zhang, Robby T. TanAbstract
Multi-modal semantic segmentation benefits from complementary sensors, but this benefit is fragile when some modalities are degraded or missing at test time. Many existing methods rely on dedicated fusion modules or multi-branch cross-modal encoders, and the fusion often becomes unreliable when modalities are absent, leading to substantial performance drops. We propose \textbf{FuseAdapt}, a parameter-efficient framework that performs fusion within the adaptation space of a frozen vision foundation model (VFM), exploring whether VFM priors can serve as an effective shared backbone for multi-modal segmentation. Instead of attaching a standalone fusion network, FuseAdapt assigns each modality a lightweight adaptation branch and performs \emph{adaptation-space fusion} by keeping Q/V low-rank adaptation private to each modality and routing only FFN low-rank residual activations across modalities inside the frozen backbone. The pretrained VFM remains fixed while modality-specific corrections and explicit cross-modal interaction are learned through the adaptation paths. To handle missing modalities, we further introduce \textbf{Predictive Modality Modeling (PMM)}, a direct representation-level objective for cross-modal redundancy. During training, PMM masks a target modality and predicts its embedding from the visible ones, supervised by a teacher target computed under full-modality input. PMM is used only during training and adds no inference-time overhead. Across three multi-modal segmentation benchmarks (MCubeS, DELIVER, MUSES), FuseAdapt consistently improves both modality-complete and modality-incomplete segmentation with a small trainable budget, yielding up to +3.01 mIoU under full modalities and +12.56 mIoU under missing modalities over prior state-of-the-art. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21779
PDF
-
Beyond Generation: Using Multimodal LLMs as Detectors of LLM-Generated Deepfake Facial Images
2026-10-15 12:16:09Olivia Salamon, Virginia N. L. Franqueira, Shujun LiAbstract
As image generation models become increasingly capable of producing highly realistic content, traditional forensic techniques are struggling to keep up. This paper investigates whether MLLMs can instead be used as a form of forensic analysis by identifying synthetic media. Specifically, the study aims to determine whether these models detect fake images by recognising physical inconsistencies, or whether they rely on digital artefacts such as embedded this http URL MLLMs: GPT-4o, GPT-5, GPT-5.2, Gemini 2.5, Gemini 3, and Seed 1.6, are benchmarked using a dataset of 400 images. Fifty images are authentic photographs, while the remaining 350 are generated using seven leading image models: Gemini 3, Gemini 2.5, Flux.2 Pro, GPT-Image-1, GPT-Image-1.5, Seedream 4.0, and Seedream 4.5. The evaluation is structured in three stages: single-image classification, pairwise comparison, and a focused "self-detection" experiment on Gemini. Several MLLMs achieved a high detection accuracy, with GPT-5.2 reaching a peak of 97.9% in the pairwise experiment, against specific generators and an overall mean pairwise accuracy of 82.5% by identifying structural or physical inconsistencies within images. However, results from the self-detection experiment indicate that the presence of invisible SynthID watermarks leads to a 10% reduction in Gemini's detection accuracy compared to the clean control group. One possible explanation is that SynthID embedding reduces some of the visible artefacts the models rely on for this http URL results imply that MLLMs can detect structural artefacts without relying on watermarks, but performance varies substantially across model generations. The findings from comparison C5 also suggest that SynthID embedding may suppress some of the structural artefacts used during detection.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21760
PDF
-
Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems
2026-10-15 11:32:41Linda Bekov\'a, Rodrigo AlvesAbstract
Language embeddings are increasingly used in recommenders to represent item content, but their privacy risks remain poorly understood. We study whether item embeddings can reveal item identities when an adversary has access to auxiliary item text from external sources. We show that a simple cosine-similarity attack can recover item identities with high mean reciprocal rank across language models and candidate-set settings on two real-world datasets. Leakage is strongest when the adversary's partial information overlaps with the victim representation, but it also persists through semantic alignment between independently sourced descriptions. We further show that item leakage can propagate to user re-identification from sparse ratings. Finally, we evaluate obfuscated descriptions as a mitigation and find a clear leakage-utility tradeoff.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21713
PDF
-
Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection
2026-10-15 11:07:21Christos Panourgias, Roberto Stanzione, Adrien Petralia, Themis Palpanas, Paul BoniolAbstract
Anomaly detection is a fundamental task for time-series analytics, with important implications for the downstream performance of many applications. Despite the large number of anomaly detection methods proposed in the literature, recent benchmark studies have shown that no single detector performs best across highly heterogeneous time series. Therefore, a practical and scalable solution is to develop a model-selection method that, for a given time series, selects the anomaly detector most likely to perform well. Nevertheless, the model selection approaches proposed in the literature suffer from a significant drop in accuracy when applied in Out-of-Distribution (OOD) settings. In this paper, we tackle the aforementioned limitation and propose RAMSAD, a retrieval-based framework for model selection in time-series anomaly detection. Given a new time series, our method queries a knowledge base of previously observed instances, retrieves the top-k most similar series, and transfers detector recommendations from their performance profiles. The framework can operate with standard similarity measures as well as embedding-based representations. Our results show that RAMSAD outperforms existing baselines in In-Distribution (ID) settings and is the most robust selector in OOD, where, when selecting a small subset of detectors, it matches or exceeds ensembles that run the entire detector pool, at a fraction of their cost. Overall, we demonstrate that similarity-based retrieval constitutes a strong and efficient foundation for model selection in time-series anomaly detection.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20243
PDF
-
Training-Free Target-Aware Refinement of 3D Gaussian Language Map
2026-10-15 10:00:53Sibaek Lee, Kyeongsu Kang, Seongbo Ha, Yewon Jeon, Joonyeol Choi, Daegeol Ko, Jaehyuk Hur, Taemin Choi, Minsu Kim, Hyungjoo Ahn, Wonsok Yoo, Hyeonwoo YuAbstract
Distilling vision-language features into 3D Gaussian Splatting yields a language map that can be queried with arbitrary text. In deployment, however, a small set of user-specified targets must be reliably located, which current distilled maps often miss, while open-vocabulary queryability for other words must remain intact. We propose a training-free, target-aware refinement of an already-distilled language map. Guided by a text-promptable segmenter, the visual embedding inside each detected target region is blended with the target text embedding, a convex combination whose coefficient sets the amount of injected prior, while non-target regions are left untouched. Injecting too much overwrites appearance cues and general queryability, so we seek, for each target, the smallest coefficient that still lets it win, and we obtain every coefficient in closed form, leaving no hyperparameters to tune. We further identify a failure mode of injection in language-goal localization. Text embeddings share a common component, and injecting them makes the standard cosine read-out query-agnostic, which a centering step in the read-out removes. Across three benchmarks, the refinement consistently improves open-vocabulary segmentation, roughly doubling the base mIoU on Replica, and localizes language goals more reliably than the base map. It also transfers as a plug-in to off-the-shelf field-based and object-level language maps and supports a real-world demonstration in which a legged robot navigates to natural-language goals. Project page and code: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.21619
PDF
-
Ontology Refinement with Embeddings and LLMs: A Case Study on CASTON
2026-10-15 08:10:05Hui Yang, Ziyu Li, Xuan Liu, Anders Jarfors, He Tan, Jiaoyan ChenAbstract
Ontologies are widely used to represent and organize complex knowledge in domains such as biomedicine and healthcare. However, constructing reliable ontologies remains challenging, as class hierarchies, whether manually or automatically constructed, may contain subtle subsumption errors that require careful refinement. We study this problem in CASTON, a casting-domain ontology, and present a lightweight but scalable refinement workflow that combines a fine-tuned ontology embedding model with Large Language Models (LLMs). The embedding model is used to extract a limited number of candidate axioms for refinement together with possible replacement candidates, and an LLM then returns repair suggestions. In a small expert evaluation, the default configuration using a CASTON-fine-tuned OnT embedding model and Qwen3-8B produced reliable high-confidence repairs: all six high-confidence replacements were accepted by both domain experts. The implementation is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21466
PDF
-
HyCo: Hybrid Drafting for Cost-Efficient Mobile-Cloud Speculative Decoding
2026-10-15 07:45:49Hanbin Bae, Heejin Choi, Joohyung Lee, Byoung Jin Choi, Sangjun Park, Hoon-Young ChoAbstract
Device-cloud speculative decoding reduces server computation, but growing a deep draft tree with a small language model (SLM) requires repeated passes on a mobile neural processing unit (NPU). We present HyCo, which assigns depth to the server model's native multi-token prediction (MTP) head, executed on the device, and alternative branches to one SLM pass. The server returns the hidden state, input embedding, and key-value entries needed by the head instead of executing its sequential steps. Quantization, a restricted vocabulary, and a 1K-token window fit both drafters to the NPU. An {\epsilon}-threshold rule additionally relaxes exact preservation of the verifier's sampling distribution. In single-client runs with a Galaxy S26 Ultra over LTE/5G, HyCo reduces server GPU time per output token relative to server-side MTP self-speculation by 38.6% on Spec-Bench and 29.2% on 32K-token summarization. With the same acceptance rule, three Spec-Bench runs per system show 9.0 percentage points more saving and 1.9x delivery speed than an SLM-only drafter. HyCo differs from Cloud+MTP by +0.2 judge-score points (paired 95% CI: -0.9 to +1.3); exploratory translation favors SpecEdge-{\epsilon}. Without relaxation, HyCo exact saves 27.7% and 11.9% on the two datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21436
PDF
-
Where, How, and When: Query-Guided Grounding for Video Understanding
2026-10-15 07:32:57Yogesh KumarAbstract
Understanding video content requires reasoning at multiple levels of granularity, from identifying objects to interpreting their interactions and localizing when specific actions occur. This thesis studies three query-guided grounding tasks that answer where key objects are (object-level grounding), how they interact (relationship-level grounding), and when specific moments occur (moment-level grounding). For object-level grounding, we present QDETRv, a query-guided extension of the Detection Transformer for one-shot localization of unseen objects in videos, which combines query-context fusion, a memory module for temporal consistency, and unsupervised pretraining on synthetic object trajectories. We further propose the Temporal Object-Aware Vision Transformer (TOViT) for few-shot video object detection, which builds on a language-aligned open-set vision encoder and propagates high-confidence object features across frames. For relationship-level grounding, we introduce few-shot referring relationships in videos: given a (subject, predicate, object) query and a few support videos sharing the predicate, the entities are localized by optimizing a T-partite random field using a meta-learned relation network with query-conditioned translational embeddings, Global Semantic Aggregation, Local Localization Aggregation, and belief-propagation-based message passing. For moment-level grounding, we propose the Moment Alignment Transformer (MATR) for video-to-video moment retrieval, which uses dual-stage Dynamic Time Warping for pre- and post-fusion alignment, learnable queries for boundary prediction, and self-supervised pretraining with temporal augmentations; MATR also extends to text-to-video moment retrieval with performance comparable to, or better than, the state of the art. These contributions advance query-guided video understanding across spatial, relational, and temporal grounding.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21422
PDF
-
Memorilla: Latent Semantic Memory for LLMs
2026-10-15 06:55:55Adibvafa Fallahpour, Parsa Idehpour, Vignesh Kothapalli, Nikita Mounier, Shirley Wu, Shayan Pardis, Jure LeskovecAbstract
Memory enables large language models (LLMs) to use information beyond their parameters, such as past user conversations, long documents, or an agent's earlier actions. For a frozen LLM, access to this accumulated knowledge is limited to what a memory system places in its context window. However, gathering and combining relevant information needed for each query while keeping the model's context short remains challenging for existing systems. Here we introduce Memorilla, a memory system that gathers information from an entire document collection into a fixed number of query-dependent 'memory tokens' for a frozen LLM. Memorilla encodes documents (such as user chats, book chapters) once into reusable embeddings, then learns to retrieve and place query-specific information in the LLM's input embedding space. Using only 16 memory tokens, Memorilla achieves the best performance against baselines including Mem0 and MemoRAG on five of eight benchmarks spanning personalization, long-document and knowledge-intensive question answering. Notably, on FactKG, it reaches 84.33% accuracy versus 80.43% with full-context inference, while using 108x fewer tokens to represent the source documents. Furthermore, Memorilla can facilitate continual learning in agentic systems where the document count (the agent's past turns) increases throughout the trajectory. In a TextWorld environment, we show that Memorilla reduces the agent's tendency to wander between rooms it has already explored, and improves its average success rate from 18.6% with full-history in-context learning to 24.2%. Overall, Memorilla aids frozen LLMs in accumulating and using knowledge effectively across long-context interactions and takes a step towards building continually learning AI systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21375
PDF
-
CoDeFont: One-Shot Font Generation via Multi-Scale Factor-Specific Representation Learning
2026-10-15 06:42:20Rejoy Chakraborty, Prasun Roy, Saumik Bhattacharya, Umapada PalAbstract
One-shot Font Generation (OFG) aims to synthesize a target glyph by transferring the stylistic characteristics of a single reference glyph while preserving the structure of the target character. However, accurately capturing font style from a single reference image remains challenging due to the limited stylistic information available in a single glyph, and this challenge is further amplified for complex scripts. We propose CoDeFont, a script-agnostic OFG framework that addresses this challenge through multi-level style-content factorization and progressive style-content reconciliation. CoDeFont independently aggregates complementary style and structural information across multiple spatial levels to obtain factor-specific representations, while a contrastive objective explicitly encourages separation between style and content embeddings. During reconstruction, the disentangled representations are progressively injected through multi-level style conditioning, enabling stylistic information to be incorporated at different decoding resolutions while preserving the underlying glyph structure. We evaluate CoDeFont on structurally distinct Bengali and Latin scripts across seen and unseen font styles. Extensive quantitative and qualitative analyses demonstrate consistent improvements over existing state-of-the-art methods, highlighting the effectiveness of the proposed framework for OFG across diverse writing systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21364
PDF
-
Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models
Abstract
In a small language model the vocabulary is the single largest part. In Gemma 3 270M the embedding table holds 168M of 268M parameters, and because quantisation methods leave the embedding in 16-bit, it is also most of the file once the rest of the model is compressed. We ask what that table actually buys. We replace it with one frozen table of 512-bit codes, 16 MB, with no trainable parameters, derived once from a pretrained embedding by principal-component projection and sign binarisation, and we train the same Gemma-shaped body from scratch on the same 2.05B tokens with and without it. The learned table buys 0.20 nats of validation loss for 2.6 times the trainable parameters, but on LAMBADA, HellaSwag and PIQA the frozen-table model is better or tied; only ARC-Easy favours the learned table. With a ternary BitNet b1.58 body the whole model is a 46 MB file, still ties the float model on LAMBADA and PIQA, and on a laptop CPU generates 615 to 740 tokens per second in 62 MB of memory, five to six times the speed of the float model's 8-bit GGUF in this http URL at a seventh of the memory. The frozen table wins by 1.7 to 2.3 nats on rare words, accepts 10,000 new words after training with a 3% cost where the learned table collapses by 43%, and all of it is released with the weights, the data and every evaluation answer.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22428
PDF
-
CertEx: Exact Visual Retrieval at Scale by Certified Exclusion
Abstract
Exact $k$-nearest-neighbor (kNN) search over image descriptors and embeddings underlies visual retrieval, near-duplicate detection, the evaluation of learned representations, and increasingly the memory of LLM agents. However, exhaustive search computes every distance at full precision, whereas approximate indexes return recall below one. We observe that exact search only needs a proof that each excluded vector cannot be a neighbor. Because such a proof only has to be conservative, it can be checked in low precision, much as the retina examines the whole scene at low resolution. We call this principle certified exclusion and realize it in an exact kNN method for GPUs, which we call \certex. Specifically, \certex\ stores a lower-bounding projection of each vector in half precision and folds a rounding certificate into the same tensor-core dot product, so that only the few vectors that the test keeps need exact distances. We prove that \certex\ returns the exact kNN of every query. On sixteen datasets with up to 100M vectors, \certex\ is exact for every query at 7.1$\times$ to 18.0$\times$ the throughput of the fastest cuVS search on one H100 and outperforms quantized and graph indexes whenever every query must be exact.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21325
PDF
-
PocketTSLM: Deploying an On-Device Soft-Prompt Time-Series Language Model for Privacy-Preserving Smartphone Reasoning
2026-10-15 05:56:53Max Rosenblattl, Nikhil Krishnaswamy, Leon Nissen, Manuel Milling, Nicolas Zumarraga, Ning Wang, Thomas Kaar, Robert Jakob, Bj\"orn W. Schuller, Elgar Fleisch, Patrick Langer, Paul SchmiedmayerAbstract
Consumer phones and wearables increasingly collect physiological time-series data, yet most mobile systems treat these streams as summaries or text rather than as temporal evidence. This representation is poorly matched to personal health systems that need to retrieve, route, or summarize sensor evidence while preserving temporal structure. Cloud-hosted time-series language models avoid smartphone limits, but they repeatedly move sensitive physiology off the device and add latency and per-query compute cost. Mobile model alternatives that aggregate time-series data into statistical features or serialize raw samples as text either compress temporal structure or exhaust the context and memory budgets of small on-device models. We present PocketTSLM, a mobile-native deployment of OpenTSLM SoftPrompt, the soft-prompt variant of the OpenTSLM time-series language model. PocketTSLM runs fully on a consumer smartphone by injecting encoded time-series windows as embeddings instead of tokenizing time series as text. A numerical parity protocol verifies identical greedy-decoded token sequences between the Swift port and a Python reference using Apple's MLX machine-learning framework. Answers also match the PyTorch reference, although rationale wording can differ. An on-device context-economics benchmark compares the soft-prompt path with a text-serialized baseline on the same backbone. In our benchmark format, soft-prompting uses approximately 12 times fewer time-series tokens and reduces prompt-prefill cost. PocketTSLM processes 30-second Sleep-EDF electroencephalography clips for sleep staging and a 1,000-sample (10 s) 12-lead electrocardiogram clip from ECG-QA. In comparison, text-serialized baselines exceed the phone's context or memory budget at longer time-series windows. All inference runs entirely on the device, with no health data transmitted during inference.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21308
PDF
-
Making every stage of medical device document assessment with large language models deterministic
2026-10-15 05:45:20Ryosuke SuzukiAbstract
To show that a medical device complies with regulation, experts judge whether documents and records meet each requirement and record the judgment for others to verify. For each assessment item that experts define, large language models could prepare a preliminary assessment: a label such as Satisfied or Not satisfied, a reason and quoted evidence. We sent fourteen commercial deployments of such models (seven models from three providers, through six routes) the same request repeatedly, with the deterministic sampling settings each accepted; every deployment returned differing assessments for at least one request, and in twelve the label changed. Reducing reasoning where the interface allows it did not reduce the variation, and prompts of retrieved passages removed it only for the smallest models. The same open-weight model was reproducible or not depending only on how it was served. A pipeline we built to be deterministic at every stage -- text extraction and optical character recognition (OCR), chunking, embedding, indexing, retrieval and inference -- returned byte-identical output at each stage across reruns, interruptions, edits, machines of one graphics processing unit (GPU) model and days, for blood glucose meter and infusion pump documents. OCR, embedding and approximate retrieval varied when their own serving was not made invariant, and outputs changed with the GPU model and with the inference engine's scheduling settings, which therefore belong in the recorded configuration. End-to-end determinism is achievable and gives a testable basis for audit and change control.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21300
PDF
