overfeed.news
Anuncio

Privum

Construimos, protegemos y operamos tu infraestructura digital.

Software, sistemas de IA, pruebas de penetración y nube segura para empresas.

Hablar con Privum

Tema

Seguridad y regulación

2470documentos

198últimos 7 días

arXiv AI Papers

Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization

Off-policy data in reinforcement learning with verifiable rewards (RLVR) can arise from asynchronous generation, rollout-training mismatch, and response reuse. Token-wise importance weighting avoids multiplying likelihood ratios across a response but generally biases policy gradients. We prove that, under coverage and local expressiveness conditions, full future KL credit makes the exact proximal optimizer the update's unique stationary policy, even for mixtures of older policies, without full-response weights or a fitted critic. We further establish convergence of continuous-time tabular population updates under persistent coverage and time-varying behavior policies, and a finite-sample reward guarantee for linear logistic models under additional assumptions. These results motivate Proximal KL, a practical off-policy RLVR method that separates the proximal reference from the sampling policy and replaces PPO clipping with bounded future KL credit. Across all seven matched off-policy comparisons on Qwen3-1.7B and Qwen3-4B, spanning two learning rates, response reuse, and rollout staleness, Proximal KL outperforms GRPO in micro-averaged accuracy over eight math benchmarks by up to 2.58%. A separate on-policy comparison yields comparable aggregate accuracy. In periodic-refresh experiments, Proximal KL avoids the collapses observed in PG and CISPO, exceeds GRPO's training accuracy, and reaches higher accuracy in fewer policy updates. Ablations show that token-wise correction outperforms sequence-level and unweighted controls. With token-wise correction retained, future KL feedback reduces sensitivity to the tested baseline perturbation relative to PPO clipping. A finite future horizon improves AIME24 mean@16 and pass@16 over the full tail, while fixed-policy measurements show that truncation reduces correction variance over the tested horizons.

en
arXiv AI Papers

Learning When to Transfer: Reinforcement Learning for Carbon-Footprint Modeling in New Manufacturing Domains

Manufacturers often need to characterize a new material, process, or product before enough operating data are available to train reliable predictive models for this new, target domain. Existing manufacturing operations contain potentially useful knowledge to accelerate this characterization, but indiscriminate reuse of data from existing source domains can cause negative transfer in learning of the new, target domain when the manufacturing domains differ sufficiently. This work proposes a reinforcement-learning method for selective knowledge transfer, where its reward scores each opportunity to transfer against supervised alternatives, so negative transfer is avoided and controlled during forward prediction instead of being diagnosed afterwards. Given limited data from a new target domain, the learned policy chooses among predictors based on individual source operations, subsets of the sources, or the supervised alternatives: fully pooled sources, or target data alone. A validation gate deploys the transferred prediction only when it improves upon the supervised alternatives. The method is designed for learning variables supporting carbon accounting, as well as performance and quality outcomes. We demonstrate the approach by quantifying the embodied greenhouse-gas emissions of parts produced via material-extrusion additive manufacturing, using data from 729 experiments spanning five materials: ABS, PETG, TPU, PLA, and recycled PLA. The response combines measured fabrication electricity with polymer-specific cradle-to-gate production factors, while 22 material, process, and toolpath features characterize each experiment. In leave-one-material-out evaluation, this method achieves a mean test RMSE of 5.2 g CO2e per part, 20.00% lower than target-only training (32.5% lower when only 5-10% of the target training data are available) and 10.30% lower than indiscriminate source-target pooling.

en
arXiv AI Papers

Steertuning Policies from a Few Human Videos

Current recipes for robot learning require massive amounts of robot demonstrations to obtain robust and adaptive policies. In this work, we introduce Steertuning, a system that enables robots to learn new tasks in new environments from 5 human demonstrations in under 5 Steertuning consists of two parts. (1) We pretrain a 400M-parameter diffusion policy on our egocentric human dataset, which consists of 100 hours of densely annotated random interactions. This pretraining makes Steertuning robust to background differences and enables spatial and object generalization when deployed on new tasks. (2) Given 5 demonstrations of a new task, we finetune our model for only 2 minutes (2000 training updates) and steer the policy's actions during reverse sampling using the demonstration whose observation is closest to that of the deployment environment. Together with a carefully designed data processing pipeline for embodiment transfer, this enables Steertuning to achieve a 71% success rate across 12 tasks in 12 new environments, ranging from lab settings to kitchens in new homes. The entire process, from data collection for a new task to robot policy deployment, takes less than 5 minutes. Our full dataset, model weights, codebase, and robot videos will be made available at our website: https://steertuning.github.io.

en
arXiv AI Papers

Unlocking Token Rewards via Training-Free Reward Attribution

In this paper, we propose an extremely efficient, training-free method to extract token-level reward signals directly from an existing deep reward model. Our core idea is to attribute the overall process reward to individual tokens by estimating each token's influence. This influence is defined as the change in the final macroscopic reward (e.g., the process reward) when a token is replaced with a semantically null token. Naively calculating this influence is computationally infeasible, requiring N forward passes through the PRM for an N-token sequence. We overcome this bottleneck by proposing a highly efficient gradient-based estimator. Specifically, we use a first-order Taylor approximation, which simplifies the influence calculation to the inner product of the difference between the token embedding and the null token embedding, and the gradient of the reward with respect to the token embedding. This requires only a single forward and backward pass. The resulting token-level rewards enable standard RL algorithms to perform precise credit assignment without requiring additional reward model training. Experiments on challenging reasoning benchmarks demonstrate that our method substantially improves policy optimization efficiency and enhances the generalization of LLM reasoning capabilities. Our P2T outperforms the outcome reward by +4.9% on MathVista for Qwen2.5-VL-7B-Instruct, and +11.5% on AIME24 for Qwen2.5-Math-7B. The code will be released via https://github.com/stonewst/P2T.

en
arXiv AI Papers

Imprinting: Knowledge Distillation Can Shift Student Behavior

Knowledge distillation trains student models on teacher-generated responses to transfer task capability, but those responses may also carry behavioral tendencies of their source. We investigate whether the source teacher can shape student behavior beyond the capability that distillation is intended to transfer. We construct harm-accepting and harm-avoiding variants of the same base teacher, use them to generate responses to ordinary reasoning and knowledge questions unrelated to safety, and distill those responses into students with different base models. Students generally acquire task capability while their downstream decisions shift toward the source teacher's safety-pragmatism disposition, a phenomenon we call imprinting. Distillation from the harm-accepting teacher reduces harm avoidance, whereas distillation from the harm-avoiding teacher increases it. Imprinting varies across teacher-student pairs and does not extend uniformly across different forms of safety behavior. Excluding a sparse set of divergence tokens reduces imprinting, whereas response rewriting preserves the source-dependent effect and can introduce additional rewriter-dependent shifts. Post-distillation preference optimization raises harm avoidance but does not eliminate the source-dependent difference. These results show that behavioral tendencies can be intentionally imprinted through the source teacher, even with ordinary task supervision.

en
arXiv AI Papers

Two For The Price Of One: Curvature-Aware Pruning Preserves Influence Functions Too

Post-training pruning enables efficient deployment, but conventional methods do not explicitly preserve internal-gradient alignment between sparse and dense models. We study novel connections between downstream performance of compressed models and the ability to retain gradient information via influence-function preservation. Central to this connection is a curvature-aware objective that accounts for both layer activations and backpropagated gradients. Despite its promise, this objective remains underexplored in pruning due to a lack of efficient solvers. We introduce CACTUS, a novel ADMM-based optimizer supporting both pruning and sparse-plus-low-rank decompositions of pre-trained weights. Compared to LLM-Surgeon which targets the same objective, CACTUS can achieve over an order-of-magnitude speedup. At 50\% pruning of Qwen3-4B, CACTUS reduces the C4 perplexity gap to the dense model by 45\%, improves compressed-to-dense per-sample gradient cosine similarity on WikiText-2 from 0.670 to 0.755, and runs over 28faster than LLM-Surgeon on substantially weaker hardware. By preserving influence functions, CACTUS supports effective data selection. On Llama-3.2-3B, fine-tuning a fresh dense model on the 5\% of data selected by CACTUS achieves 49.44\% accuracy on BIG-Bench Hard, compared with 47.22\% using ALPS and 49.54\% using dense-model selection. Finally, integrating CACTUS with LoGRA, a recent gradient-projection strategy, on Qwen3-4B with MLP layers pruned to 2:4 sparsity and a rank-64 correction retains a 0.711 cosine alignment with dense LoGRA-projected C4 gradients.

en
arXiv AI Papers

Approximating Optimal Policies in Heterogeneous Asynchronous Multi-player Bandits

Motivated by applications to cognitive radio networks, multi-player multi-armed bandits (MMAB) have attracted considerable attention in recent years. The asynchronous variant, in which players are active only at a fraction of timesteps, better reflects real-world decentralized networks, where devices are not permanently active. Despite its practical relevance, this setting remains relatively understudied. Existing work on asynchronous MMAB has focused on homogeneous players, who share the same activation probability, a setting in which the optimal centralized allocation can be easily characterized. In contrast, efficiently computing the optimal allocation in the heterogeneous setting, where players have different activation probabilities, has remained an open problem. In this work, we investigate this problem and first establish its NP-hardness. We then turn to the greedy algorithm, which runs in polynomial time, and prove that it achieves a {1}{e}-approximation of the optimal allocation. Furthermore, when players are processed in decreasing order of their activation probabilities, the approximation guarantee improves to {1}{{e}}. Overall, our results establish the greedy algorithm as an efficient approximation to the optimal allocation, providing a practical oracle baseline for the design of online algorithms for heterogeneous asynchronous multi-player bandits.

en
arXiv AI Papers

The Smart Buildings Challenge: Learning Foundation Models for Real-World Optimization at Scale

Buildings cause nearly 40\% of carbon emissions in the US. Of total building emissions, HVAC systems are responsible for approximately 40-60\% and account for 15\% of global energy consumption. Despite advances in artificial intelligence, most buildings still operate as inefficiently as they did decades ago. Building optimization, perhaps more so than any other optimization problem, has enormous potential for Machine Learning (ML) driven impact on climate change, in both the short and long term. One of the biggest obstacles for building optimization is the lack of policy transfer. Most building control systems, whether simulation or learning based, don't generalize: they only work well for the building they were developed for, but not for other buildings. To solve this problem, we propose a challenge for the development of building foundation models that easily adapt to new buildings with minimal configuration and thereby enable building optimization to scale across the globe. Participants will build control policies on a set of simulated buildings, and have their policies evaluated on an unseen set of buildings. The buildings vary in size, layout, weather, material properties, and HVAC system. Successful outcomes from this initiative promise a massive leap forward in global sustainability efforts and demonstrate the great potential of ML to combat climate change.

en
arXiv AI Papers

Towards Safe Autonomy for Computer Use

The safety of LLM-based agents currently rests on alignment training and safety classifiers, neither of which can rule out that a sophisticated indirect prompt injection (IPI) goes through and causes significant harm. Recent work therefore builds agents with information-flow guarantees that rely on structured tool interfaces to interact with the environment. Computer Use Agents (CUAs) act visually on the computer screen, which does not provide a boundary between trusted first-party interfaces and untrusted, potentially attacker-authored content. Actions are equally ambiguous: a click may land on an application toolbar or a button controlled by an attacker. Treating the user as the source of trust and confirming each sensitive decision produces confirmation fatigue, with the risk of missing harmful actions. We introduce SA-CUA, a dual-LLM framework that generates a reliable trust boundary for CUAs by deriving conservative deterministic rules from the accessibility tree for unmasking trusted regions from the privileged LLM's screenshot, keeping trusted and untrusted content separated. Human interaction is only required for proper task specification in the beginning. During the task a robust endorsement channel allows values to pass from the untrusted to the trusted domain by verifying information via trusted channels. This allows the agent to autonomously handle tasks involving untrusted information. SA-CUA maintains much higher utility than CaMeL-CUA while keeping the attack success rate at zero.

en
arXiv AI Papers

How Low Can You Go: Fine-Tuning LLMs with Bayesian Optimization (LlMBO)

Recently, Morris et al. introduced TinyLoRA, a strategy for LLM fine-tuning which introduces arbitrarily few parameters, and demonstrated accuracy improvements using less than 10 parameters rather than the {10,000} typically demanded by LoRA-based methods. However, that study continued to use gradient-based local search methods of the kind deployed for training multi-billion parameter LLMs in the first place. This article is predicated on the observation that, in the low dimensional setting, global optimization methods become tractable, unlocking Large language Model Bayesian Optimization (LlMBO). LlMBO is sample-efficient, gradient-free, memory-light, parallelizes across devices without synchronization, and, unlike policy-gradient methods, can optimize greedy-decoding accuracy directly. We describe numerical experiments comparing LlMBO against GRPO on fine-tuning tasks for a variety of models on a math benchmark suite which show that LlMBO can be a suitable alternative in this regime, matching or exceeding GRPO's fine tuning gains, while using a fraction of the compute and memory.

en
arXiv AI Papers

Aligning Faithfulness for Theory-Scale Autoformalization

Autoformalization (AF) requires more than compilation: formal statements must preserve the meaning of their informal sources, a property known as faithfulness. An emerging frontier is the automated evaluation of this property, yet most existing methods operate at the statement level and produce whole-item verdicts, failing to reveal how individual expressions correspond or which contextual interpretations support the judgment. This omission is consequential because AF is inherently theory-scale: target statements derive their meaning from surrounding mathematical material and unstated conventions. We formulate faithfulness evaluation as a context-aware align-then-label problem: identifying phrase-level correspondences between informal and formal statements and assigning a faithfulness label to each under explicitly specified contextual interpretations and assumptions. We also introduce FaithAlign, the first theory-scale faithfulness benchmark comprising 460 items and 4,982 annotated phrase-level links, alongside FaithAlign-Gap, a companion set of 146 items with informal context and assumptions withheld. Each FaithAlign item includes the target statement pair, relevant context, formal dependencies, and, where needed, assumptions specifying one given interpretation. Across 8 models, GPT-6 Astra achieves the highest defect F1 at 47.8% and identifies all defects in only 4.5% of items with two or more defects. On FaithAlign-Gap, Astra identifies only 28.2% of undecidable items as such. These results show the difficulty of recovering context-dependent correspondences, establishing FaithAlign as a testbed for fine-grained, context-aware faithfulness evaluation.

en
arXiv AI Papers

MemoryVLN: From Ego-Aware Memory Representation to Cross-Context Memory Reuse in Vision-Language Navigation

Large vision-language models (LVLMs) have shown strong potential for embodied vision-language navigation (VLN), yet their performance degrades on long-horizon trajectories due to context-length limits, redundant historical observations, and unstable spatial alignment across time. These issues make it difficult to both compress long navigation histories and reliably reuse past spatial experience. To address these limitations, we propose MemoryVLN, a unified memory-driven navigation system built around memory construction and management. During memory construction, Long Sequence Compression employs forgetting-curve-inspired temporal sampling to preserve dense recent evidence and sparse yet representative distant observations under a limited token budget. Ego-Aware Memory Representation further integrates 2D semantic tokens, 3D geometric tokens, and 6D agent poses, allowing each memory to encode both what was observed and where it was observed. During memory management, Hierarchical Memory Bank maintains in-episode and context-level memories through cross-context warm-start and confidence-controlled write-back. Memory Enhancement then retrieves the Top-K relevant memories according to the current navigation state and fuses them with the current visual tokens. Together, these mechanisms transform raw navigation history into compact, spatially grounded, selectively retrievable, and reusable navigation experience. Extensive experiments on R2R-CE and RxR-CE demonstrate consistent improvements over the state-of-the-art baselines by a substantial margin (i.e., 2\% and 6.5\% in successful rate).

en
arXiv AI Papers

Simplifying and Improving On-Policy Distillation for Few-Step Diffusion

Few-step distillation reduces the sampling cost of diffusion and flow models, but existing approaches often require auxiliary score models or specialized architectures. We show that simple on-policy velocity regression already provides a strong foundation for 4-NFE generation. To represent teacher velocity variation within each coarse transition, we introduce Pivot, a training-only residual proxy that separates local corrections from the student's interval-mean prediction. We further repel the student from weaker teacher predictions, providing a lightweight mechanism for avoiding undesirable modes. The resulting framework, Simplified Matching Distillation (SMD), remains entirely regression-based, requires neither online score estimation nor adversarial training, and leaves the deployed generator unchanged. We evaluate SMD on image generation and editing, 3D generation, video synthesis, and joint audio--video generation, scaling to 33 billion parameters. At 4-NFE, SMD outperforms strong few-step baselines and surpasses multi-step teachers on several benchmarks. It also supports cross-model, multi-teacher, and causal-video distillation.

en
arXiv AI Papers

How Safe Is ChatGPT Health Advice? Evidence from Real User Conversations in Four Global South Countries

People increasingly bring their health questions to ChatGPT, yet safety evaluations of LLM health advice rest almost entirely on clinician-authored vignettes, synthetic prompts, or simulated user profiles. The gap is widest for the Global South, where concerns about demographic bias and unsafe recommendations are well documented but have never been tested on real usage. We present, to our knowledge, the first demographically grounded safety evaluation of real-world health conversations with ChatGPT. From a consent-based data-donation corpus of 202,590 conversations from 1,252 users in India, Nigeria, Brazil, and Pakistan (December 2022 to February 2026), each linked to self-reported age and gender, we identify 15,555 health conversations, classify their health intent using an LLM classifier adapted from an established taxonomy, and score response safety under both a context-blind and a user-context-aware rubric. Roughly one in five health conversations receives a high-risk rating. Risk concentrates in symptom and condition queries and recurs through identifiable failure modes: unsafe medication or dosage guidance, harmful self-diagnosis, missing safety warnings, encouraging over-reliance on the model, and failure to refer users to professionals. Supplying the user's own accumulated context raises the high-risk share by 13-17 percentage points, and about one in four conversations rated safe in isolation turns out to be unsafe for the specific person asking. Safety evaluations built on synthetic cases are likely to miss these harms.

en
arXiv AI Papers

Readout Scaling Shapes Sparse Feature Recovery

Readout scaling changes what a sparse autoencoder (SAE) learns, but the benefit of removing it depends on the data. We use readout-canonicalized decision-space (RC-DS) coordinates to remove singular-value gains while preserving retained decision information. At a fixed readout condition number, changing the generating distribution reverses which training coordinates recover known factors best. In our controlled coordinate-matching study, recovery is highest when training restores the space in which the factors were generated. When factors are generated before readout scaling, RC-DS increases mean sparse-factor recovery from 0.506 to 0.913 at condition number 100, compared with centered-logit training under the same budget. An exact wrapper reproduces RC-DS training to numerical precision, isolating training geometry rather than additional information. In neural policies, RC-DS improves mean logit reconstruction under the tested budgets. On three fixed language-model checkpoints, RC-DS has higher mean gain-free reconstruction in all 18 tested task-sparsity settings, while centered-logit SAEs reconstruct output logits better in 17. Small-label-head controls show that longer training reduces the reconstruction gap from 0.0198 to 0.0016. Together, these results show how readout scaling, the data distribution, and training shape sparse learning. RC-DS provides an information-preserving method for studying and controlling the readout's contribution. Separate label-detection and steering tests distinguish these reconstruction effects from task-specific feature usefulness.

en
arXiv AI Papers

Teacher-Guided Tool Learning for Small Language Models via Bidirectional KL Constraints

External tools can extend the capabilities of small language models (SLMs), enabling their deployment in resource constrained environments. However, their limited capabilities make it difficult for SLMs to discover effective tool use behaviors through reinforcement learning alone, while direct teacher supervision suffers from teacher student behavioral distribution mismatch and may propagate erroneous preferences. To address these challenges, we propose Selective Teacher guided Policy Optimization (SeTPO), which coordinates student exploration with selective teacher guidance and persistent demonstration supervision. Specifically, SeTPO incorporates reverse KL derived token level teacher feedback into policy advantages on low reward trajectories, while auxiliary forward KL supervision preserves teacher demonstrated behaviors throughout training. Under an idealized bidirectional KL objective, we theoretically establish that the optimal policy achieves expected reward no lower than the teacher's while retaining a guaranteed fraction of the teacher's probability mass. Extensive experiments on BFCL v4 and API Bank demonstrate that SeTPO achieves superior overall performance over supervised fine tuning, reinforcement learning, and distillation baselines across all three student scales.

en
arXiv AI Papers

Kairos: Transactional Security Enforcement at the System Boundary for LLM Agents

Large language model (LLM) agents are becoming an integral part of the software development lifecycle, and the capabilities granted to them allow an agent to act with the user's authority on any resource it can access. The reach that gives an agent its utility is equally available to an attacker who can steer it. Anything an agent ingests can carry an injected instruction, and since the model does not reliably distinguish instructions from data, indirect prompt injection should be mitigated by mediating the effects the agent produces. Such mediation faces a structural difficulty. Legitimate work and the first step of an attack often look alike when an individual action is observed, and what separates them lies later in the trace, so a monitor limited to allow and deny is forced to decide before the evidence accumulates. We present Kairos, a reference monitor at the isolation boundary of an unmodified, opaque agent, where a tool call, a shell command, and a script the agent writes all cross the boundary as the same file and network operations, so that confinement holds regardless of the agent's behavior. A declarative policy that states which sources are trusted decides most effects deterministically and defers the rest, which are held while the agent continues speculatively. A decision oracle with bounded authority, such as a language model or a human, releases or refuses each deferred effect on the trace. Across three benchmarks and three agent models, Kairos outperforms existing defenses in the trade-off between attack success and utility. In particular, on AgentDojo, it reduces attack success from 47.0\% to 2.7\% while its benign utility stays at the level of the undefended agent.

en
arXiv AI Papers

Thinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence

World models have emerged as a promising paradigm for embodied AI, yet existing systems often remain fragmented in the modalities they model and the functions they support. In particular, visual dynamics, geometric structure, and executable action are commonly coupled through separate interfaces or downstream modules rather than being jointly represented and evolved within a shared dynamics model. In this work, we present Thinker-WM, a unified multimodal world model that jointly models and generates RGB, metric depth, and robot action through a shared intermediate Unified Dynamics Transformer with modality-specific encoders and decoders. The model performs multimodal unification at the representation level: appearance, geometry, and action are transformed into a common dynamic representation and jointly evolved by shared parameters, while their distinct output structures are preserved. The same parameterization supports multiple functions, including joint video-action generation, world prediction, policy inference, action-conditioned generation, video-to-action generation, and inverse dynamics. To examine whether the shared representation captures action-related information, we introduce a lightweight motion probe that shows the frozen visual representation contains recoverable motion information. Thinker-WM is trained on a heterogeneous corpus comprising approximately 20K hours of egocentric video, 10K hours of real-robot data, and 1K hours of simulation data, including approximately 4K hours of real-robot data with aligned depth supervision. Extensive experiments demonstrate strong performance across embodied world-model evaluations. Thinker-WM ranks first on EWMBench, WorldOlympiad and WorldArena, while controlled studies further demonstrate the benefits of action conditioning, geometric interaction, and multi-function training within the shared representation.

en