Sección

Investigación

Papers y preprints de los feeds de investigación que seguimos.

6265documentos

The Fast Tree Transform

The Fast Tree Transform is a locally-aggregated transform defined for arbitrary graph geometries that generalizes both the Hadamard frequency transform and the Haar wavelet transform on the circle. The pure frequency part of the transform approximately diagonalizes the graph Laplacian; this fact makes it useful as a preconditioner in geometric optimization problems. The full transform provides an only slightly-redundant representation of signals on the graph that allows sparse representation of signals that include both edges and textures.

arXiv AI Papershace 6 días

Beyond Discrete Ancestry Groups: Distribution-Aware In-Context Learning for Cancer Outcome Prediction Across the Genetic Ancestry Continuum

Machine learning models for omics-based prediction of cancer outcomes are commonly built on aggregated data without distinguishing ancestry groups, or under an ancestry-discrete design, which partitions samples into ancestry groups and fits a separate model within each group. Recent evidence shows that this approach is inherently limited: predictive accuracy declines with genetic distance from the training samples, even within a single ancestry group, because the data distribution shifts continuously rather than only between predefined categories. In this paper, we propose distribution-aware in-context learning (DA-ICL) for ancestry-continuum modeling. Our method extends conventional ancestry-discrete modeling to ancestry-continuum modeling, capturing the nonstationary omics-endpoint relationship across the genetic continuum while enabling efficient modeling through an in-context learning foundation model. We provide theoretical analysis demonstrating the superiority of the ancestry-continuum over ancestry-discrete modeling, along with empirical results supporting the proposed framework. Source code is available at https://github.com/ai4pm/DA-ICL-Continuum.

arXiv AI Papershace 6 días

LongCapHarness: Capability-Guided Auto-Harnessing for Long-Context Reasoning

Existing methods enhancing an LLM's long-context reasoning capability often rely on data synthesis and follow-up LLM post-training. However, the data synthesis strategy and the post-training recipes are empirically driven and computationally intensive. In this work, we propose a new framework, dubbed LongCapHarness, to instead harness the underlying capabilities for long-context reasoning. The harnessing process recursively revises and updates capability primitive implementation, capability state and control logic through recursive self-improvement on the development set. With neither data synthesis nor LLM post-training, LongCapHarness is applied to Llama3-8B and transferred to Qwen2.5-3B. LongCapHarness substantially outperforms recent data-synthesis-based baselines on HELMET and RULER benchmarks; its estimated development cost is less than 50% of the estimated training costs of NExtLong and PolicyLong. We hope these results motivate further research into harnessing the latent capabilities of LLMs to solve tasks beyond their explicit training.

arXiv AI Papershace 6 días

Zeroth-Order Langevin Dynamics for Stochastic Nonconvex Optimization: Curvature Regularization and Non-Asymptotic Guarantees

Zeroth-order methods provide a way to optimize stochastic nonconvex objectives using only noisy function evaluations. However, the smoothing inherent in their gradient estimators effectively modifies the objective being optimized. In particular, Gaussian smoothing with smoothing parameter η>0 induces, to leading order, an implicit Hessian-trace regularization, which motivates the study of the curvature-regularized objective of the form f(x)+(η^2/2) tr(^2 f(x)). We develop a non-asymptotic theory in the nonconvex setting for a class of algorithms called stochastic zeroth-order Langevin dynamics (ZOLD), which use only noisy function evaluations and do not have access to first- or higher-order derivative information, and derive excess-risk guarantees for the curvature-regularized objective. We first control the finite-time distribution of the ZOLD iterates in Wasserstein distance with respect to the Gibbs measure associated with the Gaussian-smoothed objective. An explicit coupling between the smoothing and inverse temperature parameters then quantifies the proximity of this measure to the Gibbs measure associated with the corresponding Hessian-trace-regularized objective. These distributional estimates in Wasserstein distance lead to excess-risk bounds for the curvature-regularized objective. Our analysis accommodates assumptions under which the stochastic function evaluations are allowed to have non-uniform dependence on the data stream. In addition, the constants in the non-asymptotic bounds do not rely on log-Sobolev or Poincaré inequalities as in prior zeroth-order Langevin analyses. To the best of our knowledge, this is the first non-asymptotic analysis of a zeroth-order Langevin method that simultaneously establishes excess-risk guarantees for a curvature-regularized objective and Wasserstein guarantees for the associated Gibbs measure in the nonconvex setting.

arXiv AI Papershace 6 días

Represented but Not Used: Value-Policy Dissociation in LLM Agents

Large language model (LLM) agents need to choose actions whose consequences unfold over multiple future steps, yet poor decisions do not reveal whether the model failed to represent those consequences or failed to use them. Mechanistic interpretability has studied internal representations of environment state and plans, but sequential decision making also requires evaluating how candidate actions change future outcomes. Reinforcement learning formalizes this as action value. We study this computation in Qwen2.5-7B-Instruct, Qwen2.5-32B-Instruct, and GPT-OSS-20B across a partially observed Grid environment and WebShop, a simulated web shopping environment. We find that the relative values of candidate actions are linearly decodable from intermediate hidden states, including at states where the policy prefers a worse action. We call this gap between value representation and policy choice value-policy dissociation. To investigate how represented value relates to action selection, we compare direct interventions along the value readout direction with Natural Value Transport (NVT), a transformation learned from hidden state changes that naturally result from differences in action value. While readout-direction interventions have limited and inconsistent effects, NVT more consistently influences action preferences, particularly at later layers. We also test a closed-loop controller that uses the value readout as a sensor and NVT as an actuator, observing improvements in task outcomes. These results suggest that LLM agents can represent useful prospective value without reliably translating it into policy choice.

arXiv AI Papershace 6 días

Bayesian Low-Rank Posteriors for Scalable Membership Inference

Membership inference attacks (MIAs) aim to determine whether a sample was used during the training of a target model. Strong MIAs rely on reference (or shadow) models to estimate target-conditional score distributions, but training such ensembles is computationally expensive for modern large-scale Vision--Language Models (VLMs). In this work, we propose a scalable alternative that replaces explicit reference-model training with a Bayesian approximation over low-rank adaptation parameters. Specifically, we model uncertainty only within the LoRA subspace and construct a posterior from a single training run, from which we sample a diverse set of virtual reference models. We instantiate this approach using Stochastic Weight Averaging Gaussian (SWAG), enabling efficient approximation of target-conditional score distributions at a fraction of the cost of conventional shadow-model ensembles. We evaluate the resulting attack on three downstream-adapted VLMs across two privacy-sensitive visual question answering tasks, namely Document VQA and Medical VQA. To isolate the effect of pretraining knowledge, we additionally introduce a controlled synthetic dataset. Our approach outperforms standard reference-based attacks while requiring only a single reference-model fine-tuning run, making membership inference more practical for large VLMs.

arXiv AI Papershace 6 días

Decentralised Drone Swarm Formation under Silent Failures with ACO Pheromone Claims and PSO Tuning

We study decentralised drone formation, without a central planner, under the conditions that make it hard: nobody knows how many drones are alive, failures are silent, radio is short-ranged and lossy, and actuation is noisy. In our controller, ant colony optimisation (ACO) allocates drones to picture positions through claims that behave as reinforced, evaporating pheromone and are gossiped between neighbours, so evaporation doubles as failure detection. A particle swarm optimisation (PSO) law flies the drones, a noise-buffered Voronoi filter keeps them apart, and PSO also tunes the controller offline. We prove that claims of destroyed drones vanish within bounded time, that conflicts between drones that exchange tables are resolved consistently, that survivors cover the picture to within a factor of two, and that drones cannot collide while their safety cells are feasible. On held-out seeds and with two tuned configurations, the controller formed the picture in 95-99% of runs in the hardest regime, restored it after a silent loss of half the swarm in 96-100% of runs at normal difficulty, transferred unchanged to eight unseen shapes and to 300 drones, and overlapped in 5 of 21,088 runs. A CBBA-style baseline that shares the evaporating claims but uses argmax without swaps was at least as reliable as ours once tuned with the same budget, and repaired faster, whereas ours generalised better to unseen shapes. The benefit thus comes from the pheromone dynamics and from tuning, not from ACO's stochastic construction or PSO's social terms. A centralised oracle is faster.

arXiv AI Papershace 6 días

BunshinRL: Splitting Live Agent Workspaces for Memory-Efficient Agentic RL

Agentic reinforcement learning (RL) rollouts interleave model reasoning with tool calls in persistent workspaces. Scaling these rollouts incurs substantial memory costs for concurrent environments, while slow tool calls delay entire rollout batches. We present BunshinRL, an agentic RL rollout system that exploits shared environment state and recurring tool calls through three techniques: memory sharing across environments, tool-prefix caching, and speculative tool execution. These techniques build on BunshinFork, a novel live whole-workspace forking mechanism for containers. BunshinFork reconstructs process trees, shares memory copy-on-write, and preserves file, communication, and GUI state, enabling cached-state reuse and rollback after incorrect speculation. We implement BunshinRL and BunshinFork through Linux kernel module and CRIU modifications. BunshinRL reduces peak memory by up to 43%, total memory consumption by up to 51%, and end-to-end rollout latency by 23%.

arXiv AI Papershace 6 días

The Truth Beneath the Tokens: Prompt-Space Recovery of Knowledge Edits in Language Models

Model editing provides an efficient way to update factual knowledge in transformer models. Recent approaches reverse edits by modifying, masking, or decomposing model weights, but make recovery dependent on weight-space interventions. We instead show that pre-edit knowledge can be recovered through input-space interventions alone, without modifying the edited model's weights. We introduce Memento, a prompt-space mechanism for auditing residual knowledge that learns a reusable recovery signal to steer an edited model toward its pre-edit response. Memento supports both continuous recovery prefixes and discrete textual prompts for standard text interfaces. Across three LLMs and five editing techniques, Memento recovers 80.07% of held-out edited facts, achieving a 9.58% relative improvement over baselines, suggesting that editing may suppress the facts without fully eliminating their recoverability. We further investigate whether prompt-space recovery extends beyond model editing. On pristine, unedited LLMs, Memento improves average factual recall by 53.9% relative to standard inference. These results demonstrate the potential of prompt-space recovery for auditing residual knowledge in edited models and investigating the gap between factual knowledge and its accessibility during inference. We will release our source code.

arXiv AI Papershace 6 días

DiSARM: Diverse and Surprising Association Rule Mining with Large Language Models

Exploratory Data Analysis (EDA) aims to discover informative patterns in large datasets. For transactional data, Association Rule Mining (ARM) is an established approach that facilitates EDA by efficiently generating candidate patterns. Beyond efficient mining, identifying informative rules has also been extensively studied through both objective and subjective interestingness measures. Recent advances in Large Language Models (LLMs) offer new opportunities for assessing subjective interestingness using world knowledge. Nevertheless, relying solely on LLMs raises concerns about scalability and statistical reliability. Building on prior ARM research, we propose a hybrid framework, DiSARM, that leverages the world knowledge of LLMs to assess the subjective interestingness of rules, while maintaining statistical reliability and promoting diversity among the selected rules. Across three transactional datasets, experiments demonstrate that DiSARM effectively combines statistical reliability with surprise and diversity, offering a promising approach to ADE from transactional data.

arXiv AI Papershace 6 días

Split and Bridge: Multimodal Generation via Diffusion Bridging

Visual data are often expressed through multiple complementary modalities (e.g., images and segmentation masks), each capturing different aspects of the same underlying structure. Most existing multimodal methods adopt a top-down paradigm, learning a shared latent variable through joint training from scratch, which limits scalability. We propose Split and Bridge (SnB), a bottom-up framework for multimodal generation that couples pretrained unimodal diffusion models at sampling time. Rather than learning a unified latent space, SnB generates coherent multimodal samples by following a shared diffusion trajectory up to a split point and then branching into modality-specific trajectories guided by a bridge module. This design enables plug-and-play reuse of powerful pretrained models without joint training, making it scalable and easily adaptable. Across standard benchmarks (PolyMNIST, CelebAMask-HQ) and more complex settings (PIE-Bench++, ROCO), SnB achieves a strong balance between sample quality and coherence. We show that SnB naturally extends to downstream zero-shot tasks such as interleaved co-generation, image editing, and style coupling/decoupling. Our results demonstrate that bottom-up generation provides a practical framework that complements existing top-down multimodal approaches. Code is available at https://github.com/AhmadArrabi/SnB

arXiv AI Papershace 6 días

Who Remembers What? Multi-Granularity Memory Extraction for Multi-User, Multi-Agent Interaction

Self-evolving agents improve their own skills, memory, and harness code from experience without retraining the base LLM, and group-evolving agents go further by sharing these lessons across agents. Yet most such systems overlook that sharing across users and heterogeneous agents requires deciding who can benefit from each lesson and what information must remain private. We present MixUA, a memory system that distills independent user-agent trajectories into lessons and assigns each lesson to a user-agent pair, user, agent, or global scope according to whom it benefits and what it may disclose. For evaluation, we introduce CrossLearnBench, a mixed-user-agent benchmark that pairs established agent tasks with user preferences and privacy probes that test whether private facts leak into memory other users can read. With five users and seven agents, MixUA raises pass rates by up to 16 points over no memory and 5 over a single global memory, even on tasks previously tried only by other users on other agents. It retains up to 90% of previously stated preferences, and at most 0.02% of privacy probes find a planted private fact in a forbidden scope. We hope MixUA offers a scalable path toward a global system where users and agents co-evolve.

arXiv AI Papershace 6 días

HexIt: Learning Hexahedral Block Decomposition with Expert Iteration on Combinatorial Maps

Decomposing a polyhedral solid into a few well-shaped hexahedral blocks is a long-standing open problem in mesh generation. We cast it as a sequential decision problem on a 3-dimensional generalised map: an agent splits edges, faces and volumes with three insert operations until every cell is a hexahedron and the mesh passes a quality threshold, and a policy that convolves over the map's involutions chooses each insert. A successful decomposition takes over a hundred decisions, and a uniformly random policy never finds one. We clone a policy from constructed decompositions and improve it by expert iteration. On held-out chamfered solids that share no boundary topology with the cloning data, the final policy solves an expected 94.4\% in 20 samples, and expert iteration raises the best-of-20 solve rate on large chamfered solids from 0.203 to 0.355. At matched compute, PPO, GRPO and VinePPO updates all make the cloned policy worse.

arXiv AI Papershace 6 días

D-REAL: Acceptance-Length Optimization with Unbiased Gradients for Speculative Decoding

Speculative decoding efficiency depends on the number of consecutively accepted draft tokens, yet token-level training objectives do not directly optimize this quantity. We introduce D-REAL (Drafter Reinforcement of Expected Acceptance Length), a post-training method that directly optimizes expected acceptance length for a fixed decoding context. D-REAL weights position-wise draft-target distributional overlap by prefix survival probabilities along a draft-sampled prefix, faithfully capturing the sequential dependence of verification on earlier proposals. By accounting for the parameter dependence of the proposal distribution, we derive an unbiased gradient estimator for this single-round objective under stochastic verification. We evaluate D-REAL on DSpark and DFlash2 with Qwen3-8B as the target model across ten benchmarks. Starting from baselines whose mean acceptance length has plateaued, one epoch of D-REAL post-training consistently improves the benchmark-averaged mean acceptance length by up to 0.23 tokens across both architectures under greedy (T = 0.0) and stochastic (T = 1.0) sampling, translating into up to a 9.4% end-to-end serving throughput improvement.

arXiv AI Papershace 6 días

Deploying Physically and Epistemically Compliant Agents by Distilling Belief-Space Task and Motion Planners

In this work, we train agents to act under uncertainty according to specified, belief-dependent rules. Deep reinforcement learning (RL) can in theory train agents to follow rules if encoded into well-designed rewards, but in practice, RL fails to perfectly optimize these rewards, leading to ineffective or noncompliant agent behavior. Belief-space planners by construction produce behavior in line with developer specification, but require hand-programming online planners and belief-state estimators, adding significant engineering complexity at scale. We combine the two: we plan offline to generate a dataset of sample trajectories and then distill the plans into a policy that acts on raw observations. We propose two changes to planner distillation that address problems specific to history-based policies: Dual Averaging, a loss that combines per-timestep predictive loss and average loss on task changes, and ρ-Optimal Reinforcement, a feedback mechanism that reinforces the policy's own successful rollouts when these are near-optimal. We provide a sufficient condition under which static search problems with noiseless observation models is complete, and show that maximum-likelihood-observation planning implies this condition in static search with continuous beliefs. We create a challenging new domain, Scavenger, where an agent needs to gain information in order to succeed. We evaluate our distilled policy in two versions of Scavenger, one where information is provided visually and one where it is provided as a command in natural language. In either case, the learned policy attains a success rate above 90% in Scavenger, compared with at most 5% for RL. We also find that distilled planners transfer with greater than 60% success to following unseen and intentionally vague commands and greater than 75% success to following floorplans larger than those seen in training.

arXiv AI Papershace 6 días

Applied bifidelity material response model construction and uncertainty quantification with a sampling hypernetwork

Multifidelity modeling offers a practical route to accurate prediction and uncertainty quantification when high-fidelity data are scarce but lower-fidelity data are comparatively abundant. This work develops a bifidelity Langevin sampling hypernetwork framework that constructs probabilistic neu- ral response models by learning a posterior distribution over model parameters rather than a single deterministic fit. The method combines a flexible shared-latent data representation for low- and high-fidelity responses, enabling parameter sharing and transfer learning between the fidelities. We introduce several methodological enhancements to improve the robustness and efficiency of this ap- proach, including stability-promoting drift models, staged and conditional training strategies, adap- tive initialization of Langevin trajectories, and training procedures designed to better exploit corre- lations between fidelity levels. These additions improve convergence behavior, reduce the sampling effort required to obtain representative posterior ensembles, and provide more reliable predictive uncertainty in data-limited regimes. The resulting framework makes more effective use of available multifidelity data while preserving interpretability through the learned posterior structure, yielding improved predictive performance, better uncertainty characterization, and a more stable workflow for constructing uncertainty-aware surrogate models. The method is demonstrated on experimental, high-fidelity simulation and illustrative synthetic data.

arXiv AI Papershace 6 días

Mental Imagery That Matters: Curing Latent Collapse in Multimodal Reasoning

Mental simulation, the ability to reason by constructing and updating internal visual states, is central to flexible human cognition, but remains elusive in current multimodal large language models. Latent multimodal reasoning offers a promising route toward this capability by interleaving text with continuous visual latent blocks, allowing models to maintain internal visual workspaces without decoding them into pixels. In this paper, we ask whether these latent visual states actually matter. Through a direct perturbation analysis across representative latent-reasoning MLLMs, we find that they often do not: dropping, replacing, or shuffling generated visual latents has only minor effects on the model's own final-answer probability, while equivalent perturbations to the linguistic reasoning trace are substantially more damaging. We call this failure mode Mental Simulation Collapse (MSC): the model appears to perform interleaved visual reasoning, but routes most answer-relevant computation through text. We further diagnose that MSC follows naturally from existing training objectives: visual alignment can make generated latents resemble helper-image embeddings, but it does not require the decoder to rely on them; subsequent text-only supervision further leaves the semantic role of the latent pathway unidentifiable. To address this, we introduce AnchorSim (Anchored Mental Simulation), a contrastive distillation framework that trains models to make their generated visual latents consequential. Across multiple visual reasoning benchmarks, AnchorSim improves performance, while diagnostic re-evaluation shows that visual perturbations now meaningfully affect predictions. Our results expose a fundamental failure mode of latent multimodal reasoning and demonstrate that mental simulation must be anchored to model behavior in order to matter.

arXiv AI Papershace 6 días

Beyond Query Similarity: Safety-Conditioned Cache Routing for LLM Response Reuse

Semantic response caching reuses a cached response for a semantically similar query to improve LLM inference efficiency. However, query similarity alone can lead to unsafe reuse when safety conditions change. Existing approaches improve cache safety through stricter similarity checks, context-aware validation, or response verification, yet they may still miss safety conflicts between the cached response and the new request or introduce unnecessary verification overhead. We argue that safe and efficient semantic caching requires a reuse policy that makes the cached response's safety conditions explicit and uses them to guide the reuse decision with a balance between safety and utility. In this paper, we propose SafeCache, a safety-aware framework that separates candidate retrieval from safety approval and formulates semantic response reuse as a safety-conditioned routing problem. SafeCache matches each cached-response condition against the new request and aggregates the per-condition mismatches into an overall risk score. A separate contradiction guard prevents explicit conflicts from being diluted by strong matches. It further estimates matching uncertainty and calibrates the routing policy under a required unsafe-reuse target and a verifier-call budget to choose among direct reuse, selective verification, or regeneration. Experiments show that SafeCache achieves the better safety-utility trade-off among the evaluated baselines, enabling safer response reuse at comparable cache utility.

arXiv AI Papershace 6 días

Track or Follow? A Jev-Compatible Multi-Agent Trading System When Web News Lags the Market

LLM agents increasingly trade on the Web news they read, yet much Web news about listed firms is published after, and about, the price move it reports, so a reader can agree with the market by following it instead of reading the event. We ask whether LLM judgments of Web news track the market's reaction to the reported event or follow it. To answer, we built a multi-agent trading system whose agents share only point-in-time stores and answer typed questions through the interface of Jev, a hosted typed decision model; code sets every position under a proved bound on how far text can move it. In a hash-committed test of a Jev-compatible reader built from a pinned LLM's option probabilities, item judgments track announcement-window abnormal returns (weekly Spearman 0.119), also after the LLM's release, and event types agree with the issuers' 8-K filings (AUC 0.833); Jev's judgments of news published after its own release track the reaction as well (descriptive). Exploratory analyses show where the association comes from: 72% of earnings news items appear after the issuer's filing, contributor-written items often report the price move, and from the first trade after publication the association falls to 0.023. At a weekly horizon, the confirmatory test detects no rank information over code-only features. Under attack, decision cards traced 88% of successful attacks to the planted item. We propose that market-graded tests of Web-text readers report the criterion from publication, not only from the event.

arXiv AI Papershace 6 días

Frequency-Structure Complementary Modeling for Hyperspectral Image Fusion

Existing methods mainly rely on convolutional aggregation or attention-based spatial-spectral interaction. However, conventional feature-domain attention does not explicitly characterize variation patterns along spatial-token and learned latent-channel coordinates, while spatially shared local operators lack the flexibility to adapt neighborhood aggregation to heterogeneous structures. To address these limitations, we propose a Frequency-Structure Complementary Modeling Network (FSCM-Net), which couples frequency-aware dependency learning with structure-adaptive local refinement. Specifically, a Spatial-Spectral Frequency Calibration Attention (SSFCA) module constructs spatial-token affinities from Fourier-interacted query-key representations and builds latent-channel affinities after input-conditioned frequency filtering along learned channel coordinates. The latent-channel response is then calibrated by a learned shared gain and combined with the spatial-token response. Complementarily, a Structure-Coherent Dynamic Feature Fusion (SC-DFF) module combines regularized structure-tensor cues from MSI features with context-modulated HSI detail representations to generate channel- and position-dependent aggregation kernels. This design makes local HSI refinement responsive to smooth regions, edges, and textures while maintaining spectral fidelity. The two modules are progressively integrated within a multiscale encoder-decoder to coordinate representation-level interaction and structure-adaptive reconstruction. Experiments on two simulated benchmarks and one real remote-sensing dataset demonstrate favorable performance against representative fusion methods in spatial detail reconstruction and spectral preservation.