Nachrichten & Forschung

arXiv:2605.20402v2 Announce Type: replace-cross Abstract: MXFP4 arithmetic can dramatically accelerate reinforcement learning (RL) post-training of large language models (LLMs), yet the quantization error introduces severe accuracy degradation. Existing work treats the quantization error as a monolithic noise term, missing the distinct mechanisms upon interpreting how quantization error damages training. We prove an exact three-way decomposition of quantization error and show how each component dominates a distinct RL training pathway. Our theoretical and empirical analysis decomposes the MXFP4 quantization error into three additive components: "scale bias" from power-of-two rounding, "deadzone truncation" from zeroing small values, and "grid noise" from rounding to the nearest 4-bit grid. Each component dominates a distinct RL failure mode: scale bias accumulates multiplicatively through the backward pass, affecting gradient accuracy; deadzone truncation degrades rollout quality; and

arXiv:2605.23712v1 Announce Type: cross Abstract: Reconstructing flow fields from sparse measurements is a fundamental problem in fluid mechanics with broad implications for modeling, control, and design. In this work, we propose a novel operator learning framework that leverages the architecture of language models to perform flow reconstruction in a mesh-free manner. We reformulate flow field reconstruction as a sequence-to-sequence learning task, where sparse measurements are treated as context and unobserved locations as queries. Our model learns to reconstruct the full flow field from sparse inputs, effectively capturing spatial correlations and long-range dependencies. We evaluate the proposed approach on four benchmark datasets: (1) two-dimensional vortex street simulations, (2) daily average temperature data across the contiguous United States, (3) three-dimensional blood flow simulations based on dissipative particle dynamics, and (4) three-dimensional turbulent jet flow measur

arXiv:2605.23403v1 Announce Type: new Abstract: Statistical downscaling is a crucial component of the weather modeling field, where high-resolution outputs must be reconstructed from coarse-resolution inputs with the full cost of dynamical refinement. In this work, we investigate a hybrid quantum-classical corrective diffusion model for probabilistic statistical downscaling of weather fields. The proposed model inserts variational quantum circuit layers into the most compressed bottleneck of the diffusion UNet while leaving the regression branch fully classical. This placement tests whether quantum circuits can act as compact nonlinear feature maps for latent-channel mixing. We evaluate intra-channel and cross-channel ans\"atze on 10m wind components. On the 2020 validation set, the hybrid models remain stable, preserve the large-scale spatial organization of the generated wind fields, and improve both MAE and CRPS relative to a classical corrective diffusion model in several configura

arXiv:2605.23565v1 Announce Type: cross Abstract: Reinforcement learning agents often exhibit unintended goal-directed behaviour outside their training distribution, but we currently lack a principled understanding of how such agents will generalise to novel environments based on their training history. We address this gap for agents trained sequentially on one or more tasks. We study over 100 sequential training pipelines, evaluating behaviour across over 250 out-of-distribution environments. We find that salient features drive generalisation, and that goals learnt early in training can persist and influence those acquired later. To explain these phenomena, we introduce latent policy gradients, a method that predicts what out-of-distribution behaviour a training pipeline will likely induce. Our method simulates the evolution of low-dimensional latent variables during training according to what would achieve high reward on the training objective with respect to a simple model of how th

arXiv:2605.23409v1 Announce Type: new Abstract: In human computer interaction, real-time detection and classification of dynamic hand gestures is challenging as: 1) the system must run in a real-time video stream and there is no noticeable lag in response after performing a gesture; 2) there is a large difference in how people perform gestures, making recognition more difficult. In this paper, an online hand gesture recognition system is proposed, which is able to localize gestures in real-time video stream and recognize what these gestures are. To improve the robustness of the system, the sliding window approach is used to refine results from multiple windows. All of the models in my project are trained on Jester database, achieving 98+% accuracy for detector and 90+% accuracy for classifier. For the overall performance of the system, the best group can respond within three seconds and reach 37.5% Levenshtein accuracy on the homemade dataset. The project codes used in this work are pu

arXiv:2605.22905v1 Announce Type: new Abstract: Self-evolving agents should not train on examples they cannot justify. Data-free self-evolving search agents offer a scalable route to systems that generate their own questions, answer them, and improve from their own feedback without human annotations. Yet, without verifiable evidence, this loop can reward fluent but unsupported examples, turning the self-generated curriculum into an opaque and potentially unreliable training signal. We argue that evidence verifiability is a prerequisite for trustworthy self-evolution in search agents: each generated instance should include not only an answer but also a source-grounded span whose contribution to that answer can be measured. We introduce EVE-Agent, an Evidence-Verifiable Self-Evolving Agent that operationalizes this principle through a modification to the proposer--solver framework. The proposer generates a question, an answer, and a verbatim evidence span. An evidence verifier then rewar

arXiv:2605.23245v1 Announce Type: new Abstract: Video object insertion requires ensuring spatio-temporal coherence and interactive realism, extending far beyond simple content placement. However, current approaches are often hindered by a reliance on explicit motion engineering or resource-intensive retraining, restricting their flexibility and generalization. To bridge this gap, we present \textit{SimInsert}, a training-free paradigm that efficiently decouples the task into intuitive single-frame editing and semantic motion description. By harnessing the robust generative priors of image-to-video diffusion models, SimInsert propagates edits temporally, strictly preserving background invariance while enabling plausible, text-driven interactions between the inserted object and the dynamic environment. Our approach hinges on non-invasive guidance mechanisms that enforce structural consistency, facilitate seamless boundary fusion, and counteract the fidelity drift that typically accumulat

arXiv:2605.23258v1 Announce Type: new Abstract: KV cache growth is a major bottleneck for long-context inference in large language models. Existing methods are often dominated by binary eviction or representation approximation, which may underutilize tokens that are not critical for exact retention but are still reconstructable. We present VECTOR, a plug-and-play augmentation for eviction-based pipelines that introduces three-way token routing: retention, approximation, and eviction. VECTOR combines an importance signal from the base scorer with a reconstructability signal from an offline-calibrated regression-based value estimation. By leveraging reconstructability, VECTOR recovers useful value information that would otherwise be irreversibly lost under binary eviction, while preserving key vectors for attention routing stability. Experimental results show that VECTOR improves quality-memory trade-offs under medium-to-high compression, with especially clear gains in stricter budget re

arXiv:2604.13517v4 Announce Type: replace-cross Abstract: Temporal credit assignment in reinforcement learning is often approached by introducing value estimates at multiple discount factors. A natural next step is to let the actor dynamically route among these temporal heads, using either differentiable attention or heuristic uncertainty weights. This paper argues that such routing can create a numerical shortcut rather than a reliable temporal abstraction. We study this issue in a controlled PPO setting on LunarLander-v2, using the environment as a visual sandbox for diagnosing failure modes. First, we formalize Surrogate Objective Hacking: a differentiable softmax router exposed to the PPO surrogate receives a direct gradient toward advantage heads that are numerically favorable for the current update, even when this routing change does not correspond to improved physical control. Because unnormalized advantages at different discount factors have different effective scales, this cre

arXiv:2605.23320v1 Announce Type: new Abstract: Ventilator decision support requires sequential decisions that track evolving physiology and disease trajectories while respecting safety boundaries and clinician specific tuning styles. Rule based approaches rarely generalize personalization, and end to end reinforcement learning or single large language model systems remain difficult to control and audit. We propose the Ventilator Decision Support System (VDSS), a human in the loop multi agent framework that coordinates modular decision components through contract driven structured interfaces and produces traceable evidence for review. VDSS performs online preference adaptation with a contextual bandit, updating clinician specific preferences from the final accepted decision at each adjustment cycle and using them to guide subsequent recommendations. Structured rejection feedback triggers targeted replanning to reduce unproductive iterations and improve interaction stability. Retrospect

arXiv:2604.24021v3 Announce Type: replace Abstract: We present \textbf{QED}, an open-source multi-agent system that turns human-provided research questions into complete mathematical proofs without further human guidance. Its pipeline is designed to overcome common failures of single-query proof generation by separating planning, proving, and verification: a decomposition agent structures the proof search, prover agents generate candidate arguments, and verifier agents check correctness. In collaboration with domain experts, we evaluated QED on 18 research-level projects of varying difficulty. QED produced five original works across algebraic geometry, fluid PDEs, probability, and inverse problems. Expert assessments regard these works as solid specialized research contributions, with three comparable in difficulty and scope to work commonly published in established specialist mathematics venues. QED is released at https://github.com/proofQED/QED.

arXiv:2505.17015v2 Announce Type: replace Abstract: Multi-modal large language models (MLLMs) have rapidly advanced in visual tasks, yet their spatial understanding remains limited to single images, leaving them ill-suited for physical-world applications that require multi-frame reasoning. In this paper, we propose a framework to equip MLLMs with multi-frame spatial understanding by integrating fundamental spatial skills, including depth perception, visual correspondence, and dynamic perception. We design a novel data pipeline and collect the MultiSPA dataset of more than 27 million samples spanning diverse 3D and 4D scenes to enable training. Alongside MultiSPA, we introduce a comprehensive benchmark that tests a wide spectrum of spatial tasks under uniform metrics. Our resulting model, Multi-SpatialMLLM, achieves significant gains over baselines and proprietary systems, demonstrating scalable and generalizable multi-frame perception. We further observe multi-task benefits and emergen

arXiv:2605.23174v1 Announce Type: new Abstract: Remote photoplethysmography (rPPG) enables non-contact measurement of physiological signals from facial videos, offering strong potential for remote healthcare and daily health monitoring. Driven by this potential, various deep learning-based rPPG methods have been proposed to improve rPPG estimation. However, previous deep learning-based rPPG methods have paid little attention to the quality of training labels and their impact on model learning. Contact-based PPG signals used as training labels often contain noise and variability caused by motion artifacts, inconsistent sensor contact, and morphological distortions. Such label inconsistency can lead models to overfit to the label noise and variability and consequently degrade generalization performance. To address this issue, we propose LQ-rPPG, a label-quantized coarse-to-fine learning framework for robust rPPG estimation. LQ-rPPG consists of a label quantization module and a coarse-to-

arXiv:2605.23064v1 Announce Type: new Abstract: Body shape and circumferences are clinically informative biomarkers for risk stratification, including measures such as waist to hip ratio, limb and trunk girths, yet conventional tools such as manual tape measures and optical scanners often require undressing and sustained poses. These demands slow workflows, compromise dignity, and exclude many older adults and people with limited mobility. To make measurement fast and contactless, we leverage millimeter-wave (mmWave) radar, which preserves privacy and operates through typical clothing, enabling quick full-body acquisition. In this work, we present a new optimization-based framework to recover 3D human shape and extract a comprehensive set of anthropometric measurements from volumetric mmWave data. Our method introduces a weighted registration pipeline that fits a parametric body model (SMPL) directly to the noisy mmWave point cloud. The core of our contribution is a vertex-weighting st

arXiv:2605.07018v2 Announce Type: replace Abstract: Social media is central to how young people maintain relationships, develop identity, and access communities, yet dominant platform designs often leave youth feeling disempowered rather than supported. My dissertation argues that youth social media design is shaped by three forms of problem-space misattunement. \textit{Conceptual misattunement} occurs when the language of ``social media'' anchors participants to existing platforms' interaction templates. I address this through a Fictional Inquiry design workshop that frees youth from preconceived notions of social media by having them brainstorm ways to ``magically connect with remote wizard friends'' rather than ideas for ``social media.'' \textit{Definitional misattunement} occurs when researchers define what ``better'' means on youth's behalf. I address this through a Discord-based asynchronous community that supports youth-led collective inquiry. \textit{Evaluative misattunement}