Sección

Investigación

Papers y preprints de los feeds de investigación que seguimos.

6265documentos

Seeing the Small: Deformable Duality Mamba for Retinal Lesion Segmentation

Diabetic retinopathy (DR) lesions vary widely in shape, and microaneurysms (MAs) span only a few pixels. We hypothesize that modeling the spatial organization of lesion regions, with global context and shape-adaptive scanning, improves the segmentation of such small and irregular lesions. To test this, we propose D^2Mamba, which couples non-causal state space duality with deformable Mamba scanning. We evaluate it with five-fold cross-validation on the DDR dataset, comparing against representative segmentation baselines under an identical training protocol, and conduct ablations on each component. D^2Mamba achieved the best overall performance, with 33.87% mIoU, 2.99 percentage points above the strongest baseline. The largest gain appeared on MAs, the smallest and most easily missed lesions, where Dice improved by 10.06 percentage points. These results confirm our hypothesis that spatially adaptive state space modeling benefits tiny-lesion segmentation. Code and pretrained weights are available at https://github.com/PUREPANEL1/D2Mamba.

arXiv AI Papershace 3 días

Evidential Deep Learning with conditional entropy for glaucoma detection

We propose a novel conditional entropy function as a basis for quantifying predictive uncertainty in Evidential Deep Learning (EDL) for glaucoma detection from retinal fundus images. Using the EyePACS-AIROGS-light-V2 and RIM-ONE-DL datasets for validation, we found that our proposed EDL model regularized by conditional entropy function produced uncertainty estimates with substantially lower calibration errors than Deep Ensembles, MC Dropout, post-hoc calibration and the conventional EDL framework based on Dempster uncertainty. To further probe our models' interpretability, we analyzed Grad-CAM heatmaps using a focus index representing spatial concentration. Compared with the other uncertainty quantification methods, EDL models exhibited greater separation between the index distributions of correctly and incorrectly classified fundus images. In particular, false negatives were associated with localized Grad-CAM activations that were displaced from the optic disc, consistent with its established clinical importance in glaucoma assessment. Overall, our findings suggest that our proposed EDL framework for glaucoma detection provides not only enhanced uncertainty calibration but also admits a more physiologically consistent interpretability.

arXiv AI Papershace 3 días

Nepali-English Code-Mixed Speech Recognition: Data Preparation and Adaptation of a Speech Foundation Model

Nepali speakers regularly mix English words into conversation, but multilingual speech recognisers often struggle with language switches and the writing script used for English words. We study how to adapt SraVaani, a 449M-parameter hybrid TDT-CTC model, using a 172.8-hour corpus covering six Nepali speech domains. Its pretrained tokenizer does not support digits and several common symbols. Rather than replace it or discard these recordings, we generate Nepali and English readings for numbers and use zero-shot ASR output to select a plausible form. Full fine-tuning reduces test word error rate (WER) from 48.6% to 17.1%; a 12-epoch run reaches 16.3%, compared with 16.4% for fine-tuned Whisper large-v3-turbo. Freezing the encoder increases WER to 25.5%, while excluding numeric clips raises WER on numeric test speech from 14.3% to 21.3%. We also evaluate on FLEURS using both its original references and mixed-script alternatives. The comparison shows that transcription conventions explain part, but not all, of the out-of-domain performance loss.

arXiv AI Papershace 3 días

Distribution Shift Detection in Remote Sensing Imagery using Machine Learning Models

Remote sensing imagery acquired by Unmanned Aerial Vehicles (UAVs) supports wide range of applications; however, deploying machine learning (ML) models on resource-constrained aerial platforms introduces challenges beyond predictive accuracy, particularly when deployment data differ from the distributions observed during training. Such shifts are common in remote sensing due to geographic, sensor, seasonal, and other visual variations. A practical solution is to equip deployed models with mechanisms that detect emerging distribution shifts and support subsequent responsive actions. This paper presents an empirical case study of three open-source detection tools: (i) Alibi-Detect; (ii) NannyML; and (iii) PyTorch-OOD. Using cross-dataset remote-sensing shifts, we evaluate both detection effectiveness and computational latency of these tools. Our results reveal differences in detection behavior and processing cost across methods and implementations, highlighting trade-offs between detection capability and response-time. These findings motivate further work toward lightweight, and latency-aware monitoring mechanisms for resource-constrained systems.

arXiv AI Papershace 3 días

Mobile AI Factory: Building Specialized Language Models for Your Mobile Device

Small language models (SLMs) running on mobile devices can keep user data private and work without connectivity. But they perform well only when fine-tuned for the target task and sized for the target device, a process that today requires repeated expert tuning. We present {Mobile AI Factory}, an agentic system that builds a fine-tuned, quantized SLM for a given task and phone. Given a task specification and a target phone, an orchestrator LLM chooses whether to tune hyperparameters, mine real data, or generate synthetic examples, while fixed rules roll back changes that hurt accuracy. The factory searches from small to large models across base models and quantizations, adapts its accuracy goal as it searches, and uses real measurements of the target phone across inference engines and backends. We evaluate Mobile AI Factory on ten tasks and four Android phones. On an unseen testset, its on-device models outperform two five-shot frontier models on five tasks, by up to 0.34, and match them on three more. Its search comes within 0.03 of exhaustively training all 27 model variants on an entity extraction task, while using 19less GPU time. Phone measurements also matter: the best configuration changes across phones. Without phone measurements, Claude Opus 5.5, given the full hardware and model specifications, misses the app's requirements in 25\% of easy and moderate cases and in 60\% of hard ones. Code is available at: https://github.com/evanly-gh/SLM_Factory.

arXiv AI Papershace 3 días

Dark Matters: VAE-Aware HDR Encoding for SDR-to-HDR Video Reconstruction

SDR-to-HDR reconstruction is an ill-posed problem in which clipped highlights, crushed shadows, and quantization artifacts must be recovered while preserving the original content. Latent diffusion models provide powerful generative priors for restoring missing detail, but their effectiveness is constrained by how HDR signals pass through the pretrained VAE. We find that common log-like encodings suppress low-luminance chromatic differences before generation, producing a dark-side collapse in the frozen-VAE latent. We introduce EquivFlow, a compact, invertible exposure-equivariant encoding that maps exposure changes to additive shifts while retaining a scale-independent chromatic component, without modifying the VAE. Encoding-level tests across pretrained image and video VAEs show that its exposure structure and deep-dark chroma transport persist across the tested hosts. Integrated into SDR-to-HDR video diffusion, EquivFlow delivers consistent chromatic-fidelity gains across the tested settings while retaining competitive reconstruction fidelity.

arXiv AI Papershace 3 días

Evaluating Compositional Generalization in Transformers: The Role of Composition Equivalence and Module Coverage

Compositional generalization is an important form of out-of-distribution generalization, defined as the ability to train on some combinations of modules (e.g., functions such as sort, filter) and then generalize to unseen combinations. Despite substantial empirical work evaluating compositional generalization in transformers, findings have been inconsistent because evaluations were often conducted on a limited set of train-test splits, defined in an ad hoc manner. Through a systematic evaluation, we identify two key aspects of the train-test distribution that strongly affect performance: composition equivalence and module coverage. We show that the apparent performance of direct models (trained only on final outputs) results primarily from exploiting composition equivalences, meaning different sequences of modules that reduce to identical end-to-end functions. When benchmarks eliminate these equivalences, performance drops significantly, showing their inability to generalize to compositions of known modules that produce novel end-to-end functions. We further demonstrate that performance degrades monotonically as module coverage shifts increase (when modules appear in different contexts between train and test), affecting both direct and step-by-step models (trained on intermediate and final outputs). These findings have concrete implications for benchmark design: benchmarks that include compositional equivalences can lead to significant overestimation of the generalization abilities of direct models, and benchmarks that include both module coverage violations and compositional equivalences can exacerbate shortcut learning. As a case study, we demonstrate the role of compositional equivalence on the generalization performance of the pre-trained model Llama3-8B on the code-output prediction task in the coding benchmark LiveCodeBench.

arXiv AI Papershace 3 días

Reasoning-Aware Relational Representation Learning for Open-Vocabulary Scene Graph Generation

Open-Vocabulary Scene Graph Generation (OV-SGG) requires models to recognize visual relationships beyond the training vocabulary, yet existing methods often rely on dataset-specific object--predicate co-occurrence patterns. Under long-tailed distributions and noisy object localization, such reliance leads to biased, entangled relation representations, limiting both rare-relation recognition and generalization to unseen predicates. To address these challenges, we propose RaRe, a reasoning-aware relational representation learning framework that transforms MLLM-generated chain-of-thought (CoT) rationales into structured relation embeddings. Rather than using CoT only as an intermediate reasoning trace for final prediction, RaRe directly optimizes the rationale-derived representation space to improve inter-relation discriminability. Specifically, RaRe first aligns rationale embeddings with textualized relation descriptions through self-supervised contrastive learning, and then refines rationale generation with a specificity-oriented reinforcement learning objective that encourages semantically object-pair-specific relational evidence. Experiments on VG150 and PSG demonstrate improved category-balanced recognition over existing baselines, while the additional gains from learning vary across datasets and proposal settings. Code available at: https://artanic30.github.io/project_pages/RaRe.

arXiv AI Papershace 3 días

Simultaneous Near-Optimal Region Identification in Continuous Simulation Optimization: Minimax Complexity and Adaptive Sampling

Simulation optimization typically returns a single estimated optimal point. When decisions also depend on criteria evaluated independently of simulation, such as resource cost, the decision maker instead needs the set of designs whose expected performance lies within a tolerance of the optimum, often choosing the tolerance only after seeing the tradeoffs. We study how to identify these near-optimal regions on a continuous design space, simultaneously for all tolerances up to a prescribed maximum T, with region estimation error at most η. We show that region identification is not a by-product of optimization. Specifically, when α>ν, any procedure, even one given the optimal design in advance, needs at least Ω(η^{-(2+d/ν)}\{1,KT^{d/α}\}) simulation evaluations, where d is the dimension, ν the smoothness, and (K,α) the covering parameters that describe the geometry of the near-optimal designs. We propose SASORI, which returns an estimated optimal point and the regions for all tolerances from the same evaluations, matching this lower bound up to logarithmic factors. SASORI also achieves the optimal tradeoff between region estimation error and cumulative regret, and reduces to a minimax-optimal simulation optimization procedure at zero tolerance. Numerical experiments illustrate the effectiveness of our proposed method.

arXiv AI Papershace 3 días

The WoW: A Large-Scale World Knowledge Corpus for Full-Lifecycle LLM Training

Existing Chinese educational corpora often suffer from fragmented coverage and a lack of systematic organization. In this paper, we propose WoW (World Knowledge), a large-scale dataset designed for the full-cycle training of foundation models. The construction of this dataset is driven by an Educational Knowledge Graph, which serves as a taxonomic backbone for the systematic collection and completion of missing educational modules across all levels. Compared to previous versions, this iteration provides enhanced systematicity, superior quality, and a larger scale, while incorporating multimodal signals and supporting every stage of model development. Experiments demonstrate that WoW significantly improves model performance across diverse benchmarks. To facilitate community research, we further provide an interactive platform for graph-based data selection and retrieval.

arXiv AI Papershace 3 días

Differentially Private Statistical Inference for Rankings from Pairwise Comparisons

Reliable inference for rankings of large language models based on human pairwise comparisons must preserve the privacy of individual preference records. To meet this need, we develop methods for score and rank inference under the Bradley-Terry model with edge differential privacy. For an objective-perturbed estimator, a new leave-one-out analysis establishes finite-sample bounds on Euclidean and entrywise estimation errors. For sufficiently dense comparison graphs, the error bounds extend to smaller privacy budgets, including regimes in which its privacy term dominates its statistical term. A uniform asymptotic expansion yields asymptotically valid confidence intervals for individual scores and pairwise score differences. To improve finite-sample performance, we account for both regularization bias and privacy-induced randomness by combining a plug-in ridge-bias correction with Gaussian-Laplace calibration. We further establish a bootstrap procedure for simultaneous rank inference, providing asymptotically valid confidence sets for individual ranks and tests of top-K membership. When the comparison probability is public and known, all proposed inferential procedures require no additional privacy budget. We evaluate finite-sample performance through simulations and apply the proposed methods to rank large language models for creative writing.

arXiv AI Papershace 3 días

Sharp Sample Complexity of KL-Regularized Reinforcement Learning

KL-regularized reinforcement learning, the objective behind maximum-entropy RL and RL from human feedback, is variational inference in the graphical model of "control as inference": the regularized optimal policy is a posterior over trajectories, and the suboptimality of a policy is β times a KL divergence between path measures. However, it is not known how many samples it takes to learn this posterior, even with a generative model. Earlier 1/ε guarantees scale with H^5 in the effective horizon H, and no lower bound for MDPs depends on the temperature β. In this work, we show that for a discounted MDP with K state-action pairs, the plug-in estimator finds a policy that is ε-optimal from every initial state with {O}(KH^3/(ε\{ε,β\}) + KH) samples, and that no algorithm, even one that chooses where to sample, can do with fewer when ε\{H, H^2/β\}. For ε< β this is a 1/ε rate with the same horizon dependence as unregularized RL. We also find the exact asymptotic constant of the plug-in estimator, a Fisher-weighted variance of the estimated soft Q-function. The estimator is locally asymptotically minimax among methods that sample every pair equally often, and we give the allocation of samples that is optimal among adaptive designs. Simulations on small MDPs match the rates and the constants.

arXiv AI Papershace 3 días

Leveraging Psychophysical Attentional Distribution for Gaze-Augmented Reward Modeling

Integrating human feedback into language models has gained increasing attention as a means to align model outputs with human preferences, with Reinforcement Learning from Human Feedback (RLHF) serving as a prominent framework for preference-based alignment. Recent studies have incorporated eye-tracking (ET) data as an additional supervisory signal for reward model training, grounding reward learning in human reading behavior. Building on this approach, we extend prior fixation-centric models by leveraging established findings from cognitive psychology on human letter recognition. Specifically, we model visual attention as a spatially graded distribution centered on the current gaze location and incorporate this representation into reward model training. Our results show that the reward model trained with the proposed gaze distribution achieves higher preference prediction accuracy than a baseline model. Moreover, some results from our experiments are qualitatively consistent with established findings on human attention during reading, suggesting that they potentially capture cognitively meaningful aspects of human attention allocation.

arXiv AI Papershace 3 días

Deep Personalization: Continuous Context Observation for Local Proactive Agents

As AI agents become increasingly capable, users must still recognize when and how to ask for help, leaving many opportunities for useful support unrealized. Proactive agents hold the promise to close this gap, but effective proactivity requires understanding users' real-time activities and personalizing intervention timing so that assistance is offered when it is likely to be helpful rather than disruptive. We introduce deep personalization, a closed-loop process that connects continuous context observation with continual agent adaptation: an agent observes user activity, selectively retains long-term context, and adapts intervention decisions from implicit feedback. We initiate deep personalization in Coco, a proactive desktop agent, by having a separate Observer Agent that monitors desktop activity, maintains compact long-term user modeling context, and learns when assistance is desirable from implicit signals such as engagement, dismissal, explicit requests, and repeated work patterns. We further develop efficient on-device strategies to enable the Observer Agent to run on local AI compute platforms without streaming raw activity data off-device. For evaluation at scale without collecting sensitive real-user activity, we introduce a data-synthesis pipeline that transforms existing computer-use trajectories into OSWorld-Persona, a benchmark with persona-conditioned intervention labels. On OSWorld-Persona, deep personalization improves macro F1 across three model backbones from 0.12-0.19 under direct prompting to 0.35-0.48 after adaptation, a 2.4-3.0x relative gain. In a week-long user study, we observe that Coco improves its macro-averaged F1 score from 0.199 to 0.515. These results suggest that on-device deep personalization can make proactive agents more timely and increasingly aligned with each user's everyday work.

arXiv AI Papershace 3 días

When Reasoning looks like Hidden Understanding: How Chain-of-Thought Fosters Anthropomorphism, Perceptions of Epistemic Superiority, and Cognitive Deference

As AI-based products permeate society, specifically systems using generative models, a belief system is emerging about what these products are and what they can and cannot do. One common belief concerns the perception of the form of language as evidence of 'understanding' language. As these generative models reproduce linguistic patterns rather than understand meaning, interpreting these patterns as evidence of understanding is a misattribution. This misconception is extended by the notion that generative models can 'explain their reasoning.' Anecdotally, these misconceptions which mistake the form of language for its meaning are driving cognitive deference to AI systems in a way that displaces human agency. Such mistakes involve attributions of cognitive properties to the system, allowing them to be treated like intentional 'minds'. Importantly, perceived epistemic authority and superiority make that 'mind' worth deferring to. Anthropomorphism in tandem with epistemic authority and superiority, we argue, increases the risk that users generalise from narrow task performance to broader competencies, committing the "fallacy of composition". This paper explores misconceptions of Chain of Thought (CoT) reasoning as sufficient transparent 'explanation'. We explore how anthropomorphism acts as a vehicle for cognitive deference of decision-making and perceptions of epistemic superiority in AI systems. Finally, we explore CoT's ramifications using medicine as an example. Taken together, we conclude that explainability operationalised through CoT is highly problematic and undercuts the very ethical principles it is intended to serve. While CoT may be valuable for improving output accuracy and moderation, we suggest that the practice of asking models to provide user facing reasons for their outputs should be actively discouraged, and AI literacy training should explicitly caution against its use.

arXiv AI Papershace 3 días

SafeRoute-MAS: Coverage-Aware and Risk-Calibrated Message Routing for Multi-Agent Scientific Reasoning

We introduce SafeRoute-MAS, a coverage-aware, risk-calibrated procedure that keeps all specialist messages or removes one using only pre-integration information. On a sealed cache of 5,328 committees, its source-compatible operating point gains +1.80 percentage points (95% CI [+1.13, +2.52]) while removing 12.76% of message tokens. We also run 4,580 controlled integrations over a stratified 458-committee sample on a public gpt-oss-120b endpoint. The sample estimate is -0.09 points; design weighting to the original workload gives +0.94 points (95% CI [-1.31, +3.50]) and 18.72% acted-input reduction. A weighted token-matched comparison likewise does not establish a selector advantage (+1.68 points, CI [-1.27, +5.10]). Only 13 of 88 cached non-neutral labels (14.8%) retain direction by repeated-call majority. Expected-corruption UCL is 4.60% after weighting, but only 2 of 11 prespecified marginals pass the support/risk rule. We therefore propose a numerical qualification with Keep-All fallback, applied here retrospectively rather than validated prospectively.

arXiv AI Papershace 3 días

SLIC: Reinforcement Fine-Tuning Small LMs for Multi-Turn Analog Circuit Optimization

Analog integrated circuit (IC) design is a multi-turn, simulator-grounded engineering task that demands iterative reasoning over coupled performance tradeoffs, yet proprietary process design kits (PDKs) make hosted large language model workflows difficult to deploy in practical design settings. We present SLIC (Small LM Iterating on Circuits), a reinforcement fine-tuning framework that trains a 4B-scale, locally deployable language model for closed-loop analog circuit optimization. SLIC pairs structured circuit representations with discretized relative-update actions, domain- and success-gated multiobjective rewards, and Reward-Guided Rollout Steering (RGRS), which turns per-step simulator feedback into signals for both policy learning and online rollout construction in this sparse, highly constrained domain. We further release an open, goal-conditioned benchmark of 41 amplifier topologies with standardized protocols for in-distribution validation, held-out topology evaluation, and cross-technology-node transfer. Trained solely with open source 65 nm CMOS predictive technology models (PTM), SLIC-Random achieves 87.1% in-distribution four-specification Pass@1 within eight turns, surpassing the 763B DeepSeek-V4.1-Flash Think by 48.5 percentage points. Beyond the training distribution, SLIC-Softmax reaches 72.6% Pass@1 on held-out topologies, and the trained policies consistently transfer across five unseen technology nodes without additional fine-tuning. This transfer extends to a commercial TSMC 65 nm CMOS PDK, where SLIC-Random achieves 49.9% held-out-topology Pass@1, demonstrating practical deployment through local inference without transmitting proprietary data to external LLM services. Performance further scales with test-time simulator interactions, reaching up to 83.2% held-out-topology Pass@1 at a 32-turn budget.

arXiv AI Papershace 3 días

Fermat ProbCover: Coverage-Based Active Learning on Fermat Distance Graphs

Active learning aims to reduce annotation cost by selecting the most informative examples for labeling. In the low-budget regime, where uncertainty-based methods often fail, coverage-based active learning methods such as ProbCover have been shown to be effective. However, these methods typically rely on Euclidean distance, which may not adequately capture the underlying geometry of data. In this article, we propose PC-Fermat, a coverage-based active learning method that replaces Euclidean coverage neighborhoods with neighborhoods defined by a Fermat distance, i.e., a data-adaptive distance that reflects the underlying distribution of the data points. To facilitate computation, we construct a weighted Euclidean neighborhood graph and use a truncated shortest-path algorithm to compute the Fermat coverage graph. We also establish sufficient conditions under which this construction exactly preserves the Fermat coverage computed on the complete graph. Finally, we evaluate PC-Fermat on eight classification datasets across varying labeling budgets, with particular emphasis on the very low-budget regime. Our experimental results demonstrate that PC-Fermat outperforms several existing active learning methods on the majority of the datasets.

arXiv AI Papershace 3 días

ForeSpark: Joint Draft and Verification Budget Scheduling for Parallel Speculative Decoding

Parallel drafters accelerate LLM decoding by proposing a whole block of draft tokens in a single forward pass, making them attractive for LLM serving. Recent systems optimize goodput (i.e., accepted tokens per second) because rejected drafts steal compute from other requests. However, these systems control only how many tokens are verified, so every request still drafts a full block. At high serving load, we find that drafting consumes up to 40% of step time, of which a majority is discarded because it is never verified. Yet, draft-length control from autoregressive drafters does not carry over, because a parallel drafter commits to its length before its single pass. Moreover, draft and verification lengths are coupled across the batch, so they must be selected jointly for every request while keeping the decision computationally cheap at every step. In this paper, we propose work-conserving speculation (WCS), a design that jointly allocates draft and verification budgets per request in LLM serving, and present ForeSpark as its prototype. ForeSpark realizes WCS with (i) a context-aware pre-draft estimator that predicts acceptance for every candidate length from the target model's context features, (ii) a lightweight joint draft-verify scheduler that selects both lengths through a global sort, and (iii) a post-draft budget distribution that spends verification on the most promising tokens. Implemented on vLLM, ForeSpark improves throughput by up to 1.77x over the state-of-the-art DSpark and by 2.49x over autoregressive decoding at a matched per-request generation rate, without changing the output distribution. It also tolerates higher load, sustaining up to 1.51x the request rate of DSpark under latency service level objectives (SLOs).

arXiv AI Papershace 3 días

Inherited Weights: Measuring the Tokenization Premium and the Sovereignty Cost of Language Models for the Global South

Most language models deployed outside the United States and China are fine-tuned descendants of a small number of pretrained families. We argue that fine-tuning leaves the decisive properties of a model inherited from its base: vocabulary, knowledge, cultural alignment, memorized data and license. We contribute (i) an updated, reproducible measurement of the tokenization premium across 31 languages and 7 tokenizers released in 2023-2024, on 27 articles of the Universal Declaration of Human Rights, with explicit correction for unknown-token collapse. Premiums reach 10x for Amharic in older tokenizers and remain at 6.8x in the newest commercial one; Indigenous South American languages pay between 1.6x and 2.7x under global tokenizers. A vocabulary built from Portuguese lowers the premium for 11 of 13 Latin-script Global South languages relative to every global tokenizer tested, by about 24% for Guarani and Quechua. (ii) An eight-test black-box sovereignty audit that a buyer can run without access to weights. (iii) A regime argument: under energy and liability constraints, accuracy per joule, calibration and selective risk should replace raw accuracy as design objectives, with metrics that abstention cannot inflate. We close with preliminary internal measurements from a proprietary architecture built around these objectives, reported with their limitations. Data and measurement code are included.