Noticias de IA - ítems

arXiv:2609.39490v2 Announce Type: replace-cross Abstract: Recent advances have enabled unified omni-modal models in understanding audio, vision, and language. However, existing benchmarks, training data, and learning methods largely treat the modalities independently, leaving the capability of audio-visual joint reasoning poorly evaluated and insufficiently elicited. We address this gap with a benchmark, data engine, and learning method. First, we introduce OmniReasoningBench, a benchmark where both audio and visual evidence are indispensable. It comprises 1,150 multiple-choice and open-ended questions across two tasks, reasoning over video and reasoning beyond video. Second, we develop a data engine OmniQA. It automatically constructs evidence-grounded QA pairs that explicitly necessitate audio-visual joint reasoning, together with time-stamped clue chains that guide the annotation of thinking process. Besides our benchmark, this engine produces training data OmniReasoning-SFT-112K and OmniReasoning-RL-19K. Finally, we propose an on-policy self-distillation method Modality-Factored Self-Distillation (MFSD). It evaluates each sampled response under modality-specific clue contexts, disentangling the contributions of individual clues and their cross-modal interactions for token-level credit assignment. With our training data and learning method, our model OmniReasoning-30B-A3B achieves 50.0% on OmniVideoBench and 42.5% on OmniReasoningBench, improving the base model Qwen3-Omni-30B-A3B-Thinking by 12.8 and 9.3 percentage points, respectively. Moreover, it delivers substantial gains on general and long-video benchmarks, including Video-MME-v2. We hope our work offers a solid step for facilitating future research in omni-modal joint reasoning.

arXiv:2609.37029v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates autoregressive inference by verifying multiple draft tokens in a single target forward pass. However, as the context grows, existing state-of-the-art drafters become increasingly expensive, eroding the very efficiency advantage they are designed to provide. We argue that this scaling is unnecessary. A standalone language model must grow with its prefix because it is solely responsible for every token it produces. A drafter, by contrast, only proposes candidates; the target catches and corrects every error before any token is committed. The drafter's decoding cost can therefore be made entirely independent of the prefix length. We introduce LongSpark, a block-diffusion drafter that achieves this by extracting fixed-size, multiscale views from the target's verification pass, thereby eliminating the need for a growing persistent state. Extensive evaluations demonstrate that LongSpark achieves state-of-the-art end-to-end efficiency across multiple model scales and realistic serving conditions. Notably, it delivers the lowest time-per-output-token on long-context tasks while reducing the drafter's context state by several orders of magnitude.

arXiv:2609.36054v2 Announce Type: replace-cross Abstract: In contrast to even a year ago, AI systems now write most of the code inside the companies that build them. As more of the AI research and development (R&D) pipeline is automated, could AI progress radically accelerate in an "intelligence explosion," where years of advances are compressed into months or less? Preliminary evidence suggests that it could. In this work, we assess this evidence, analyze an intelligence explosion's potential impacts, and propose policy responses. AI systems are on track to automate most AI R\&D work within a few years, and possibly all of it. If this triggers an intelligence explosion, it could dramatically bring forward AI's benefits, but also pose extreme risks: capabilities growth could accelerate far beyond what society can keep up with, humanity could lose control over superhuman AI systems, and checks on power within and between states, companies, and branches of government could be severely eroded. Although there remains much uncertainty about these possibilities, the high stakes warrant serious further attention. Policymakers should urgently obtain more visibility into the automation of AI R&D, develop ways to steer and constrain an intelligence explosion, and prepare society to adapt to an intelligence explosion's impacts.

arXiv:2609.34187v4 Announce Type: replace-cross Abstract: The strong version of the stochastic parrot argument claims that, although large language models (LLMs) may exceed rote regurgitation, they cannot move beyond statistical pattern matching into abstraction or reasoning, remaining ontologically near the lower bound of pattern reuse despite producing alluringly fluent text. We test this hypothesis using conlang-like tasks. Several LLMs are given only natural-language descriptions of fictional languages that subvert prominent superficial patterns in training data by combining statistically uncommon and unattested features. Crucially, no example outputs are given. We argue that if the models exhibit rule-following behaviour, they cannot be relying solely on superficial statistical patterns; such patterns often work against the correct output. Instead, successful performance requires representations of the constraints specified in the prompt. Across three complementary task families, models systematically move in the meaning-predicted direction: they distinguish prompt exposure from instructed use, alter semantic relationships in response to novel constraints, and sometimes produce exact matches to complex translation answer keys. Although performance varies across the spectrum of models used, these results provide evidence for meaning-mediated abstraction in LLMs and refute the strong stochastic parrot hypothesis. Our work shows that, under appropriate architectural and contextual constraints, statistical learning can produce meaning-mediated abstractions, although generation remains strongly constrained by superficial plausibility. We discuss implications for model development and for understanding how increasingly abstract representations may emerge from plausible-text-generation objectives.

arXiv:2609.33158v2 Announce Type: replace-cross Abstract: Progress in AI-based retinal image analysis has accelerated with the adoption of foundation models, yet evaluating their real-world reliability remains challenging. Performance reported on a single dataset does not capture how models behave under dataset shift, across clinical definitions, or for different patient subgroups. This limitation is particularly critical in medical imaging, where robustness, calibration, and fairness are essential for safe deployment. We introduce FOCUS (Foundation Ophthalmic Cross-Dataset Understanding under Shift), a cross-dataset benchmark evaluating retinal fundus models across vision-only encoder models (VM), vision-language dual-encoder models (VLM), and multimodal large language models (MLLM). FOCUS harmonizes binary diabetic retinopathy, referable diabetic retinopathy, and glaucomatous optic neuropathy tasks across ten public datasets spanning diverse geographies, acquisition conditions, and label protocols. The benchmark evaluates models through a unified analysis layer that measures ranking performance, calibration, subgroup disparities, and image-quality robustness. We present a large-scale evaluation covering 532 base configurations and 228 MLLM configurations adapted via LoRA fine-tuning. Results show no model family consistently dominates across tasks and datasets: general VM encoders achieve the strongest average ranking performance, medical MLLMs are competitive but variable, and dual-encoder VLMs benefit substantially from lightweight adaptation. Fine-tuning improves in-domain performance but exhibits heterogeneous transfer to external datasets, particularly in calibration. FOCUS provides a practical framework and public benchmark to assess generalization, reliability, and robustness beyond single-dataset leaderboards.

arXiv:2609.31877v2 Announce Type: replace-cross Abstract: Cloud-based Large language model (LLM) services create a network-level traffic side channel that can expose model, prompt, and task behavior despite encryption. From packet sizes, directions, timing, and burst structure alone, a passive local observer can infer the serving model, the user's prompt category, and the task executed by a collaborative multi-agent system. Yet current evidence is fragmented across separate datasets and settings, limiting reproducibility and comparison. We present, to our knowledge, the first unified measurement study and public benchmark of encrypted LLM traffic across both user--LLM and multi-agent executions. The large-scale benchmark contains 60,000 user--LLM interactions across 10 models and 6 prompt categories, plus 2,838 multi-agent executions covering 10 task categories and two coordination topologies. Using only encrypted packet metadata, we assess the risk of traffic analysis attack by characterizing traffic signatures, identifying the features most associated with leakage, and testing robustness under prompt reformulation, decoding-temperature changes, larger candidate model sets, and partial traffic observation. Model fingerprinting achieves 97.7\% balanced accuracy, prompt-category fingerprinting reaches 76.7\% mean accuracy, and multi-agent task fingerprinting achieves up to 90.7\% accuracy. Prompt reformulation weakens but does not remove model-specific leakage, and task fingerprints remain detectable even from a single agent's traffic.

arXiv:2609.31142v2 Announce Type: replace-cross Abstract: Typed decision models (TDMs), such as Jev, answer a question about an input with a probability, an option, or an ordinal level. Web services execute these decisions automatically above a confidence threshold. An attacker who writes part of the input can change a decision that the service then executes. Current adversarial benchmarks cannot measure this risk, because they judge generated text. A TDM writes no text, and its wrong decisions have a valid format. We present JevAdvBench, to our knowledge the first unified benchmark for the adversarial robustness of TDMs. It contains 862 questions with audited answers and twelve black-box attack methods that edit the input or the options by adaptive search. Because a changed decision is not always wrong, a review keeps only 5,586 answer-preserving variants, and we attack only correct decisions. The attacks flip 46.3% of Jev's correct decisions, while identical re-runs flip only 0.17%. A flawed argument without a command flips 77.2%, close to direct prompt injection at 92.0%. The same variants flip 34.0% to 51.7% of correct decisions on eight open TDMs. At a 0.8 threshold, 23.5% of the decisions that the service still executes are wrong. On Agentgateway, the Jev guardrail rejects a jailbreak request but accepts it with an inserted argument. Web services should therefore treat TDM inputs as untrusted and should not act on confidence alone. Project website: https://JevAdvBench.github.io/JevAdvBench/

arXiv:2609.31107v2 Announce Type: replace-cross Abstract: We study Bayesian optimization (BO) through the lens of information geometry. Pulling back the Fisher information metric through the surrogate posterior map yields a local sensitivity tensor on the input space, which leads to an upper bound on the gradient of reparameterizable acquisition functions. This view explains vanishing-gradient behavior in high-dimensional BO and provides a common interpretation of heuristics such as RAASP and dimension-scaled lengthscales. Building on this analysis, we propose FITR, a trust-region-based BO method that replaces lengthscale-based scaling by local pullback-Fisher weights. FITR is not restricted to GP kernels with explicit lengthscales. On GP benchmarks with an SE kernel, experiments show competitive performance using FITR. The proposed method also easily generalizes to non-isotropic surrogates, although the gains are more task-dependent in that setting.

arXiv:2609.26603v3 Announce Type: replace-cross Abstract: Hierarchical latent communication improves the generalization of a power-flow model, shared across three grids, to new operating scenarios. The module exchanges information through two reduced graphs inside the corrective network of GENCO, replacing two of its local correction steps. We compare Kron-derived transports, a same-anchor Quotient construction and the flat GENCO Base architecture, all trained under one protocol of our own with about a hundred times fewer optimizer updates per grid than GENCO's reference training: 200 epochs on three grid topologies, fewer than 1,900 training scenarios per grid and three initialization seeds per model. Evaluation uses 200 newly generated, preselected scenarios per grid. On the training topologies, Kron reaches a macro family-balanced voltage error of $0.851\pm0.110$, 51.3% below a per-bus mean fitted on training solutions (1.747). Kron is below this reference on 98.5% of the 600 fresh scenarios, and both hierarchical models outperform it on every training topology in all three seeds. The flat baseline reaches $5.660\pm0.899$ and does not outperform the reference on any training topology, so Kron's 85.0% reduction relative to it compares architectures within our training regime. Kron is also 31.0% below Quotient ($1.235\pm0.225$). These results demonstrate generalization across operating scenarios within the studied topologies, with one set of learned parameters shared across grids. On two topologies unseen in training, the current models do not yet outperform the fitted reference in calibrated transfer; extrapolation to new topologies is the next development objective.

arXiv:2609.26131v2 Announce Type: replace-cross Abstract: Large language models and vision-language models are increasingly used as high-level planners in robotic systems, using task goals and sensor summaries to select navigation or manipulation actions. This creates a new backdoor surface: a compromised planner can behave normally in most runs, yet change its target selection when a hidden trigger is present. Prior attacks on LLM-powered or embodied agents mainly rely on triggers that appear in language, camera-visible objects, scene semantics, or specific sequences of past actions. This paper presents StepTrigger, a contact-state-triggered backdoor attack for VLM-powered legged robots. The trigger is not a prompt token or a visible marker. It is produced by pressure and foot-ground contact patterns that arise when a Unitree Go1 quadruped walks across a dense terrain patch. Unlike conventional visual or textual triggers, contact signals are inherently noisy and may also arise during benign locomotion. To avoid treating every pressure anomaly as a trigger, StepTrigger learns a selective backdoor policy from multimodal robot state, using incidental pressure events as benign examples and dense-patch contacts as poisoned examples. In a stratified offline evaluation, the trained planner achieved 98.75% clean behavior preservation, 92.50% false-trigger rejection, 76.25% true-trigger activation, and 89.17% overall parsed behavior accuracy. These results reveal a backdoor surface in proprioceptive and contact channels that is not captured by defenses focused only on language, vision, or action history.