Forskningsradar

Science Journals

Peer-reviewade publikationer — 51233 artiklar

arXiv (fysik & CS) Preprint 2026-05-19
Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise
arXiv:2605.18022v1 Announce Type: new Abstract: Highly over-parameterized models can simultaneously memorize noisy labels and generalize well, yet how these behaviors coexist remains poorly understood. In this work, we investigate the underlying mechanisms of this coexistence using modular arithmetic tasks under heavy label noise. Through extensive experiments on two-layer neural networks, we find that larger models tend to generalize better under appropriate optimization and model configurations, while noisy labels are memorized faster than clean data. Over-parameterized models internally form a generalization structure, but its expression in the output is suppressed by the need to fit noisy labels. Remarkably, even with 80\% label noise, near-perfect test accuracy can be achieved by extracting this internal structure using frequency-based methods. We further propose a task-agnostic method to partition networks into generalization and memorization components. Although this subnetwork improves generalization, it is limited compared with frequency-based extraction, indicating that the generalization structure is distributed across neurons and motivating the development of new tools to retrieve generalizable knowledge from over-parameterized networks.
arXiv (fysik & CS) Preprint 2026-05-19
PyHealth 2.0: A Comprehensive Open-Source Toolkit for Accessible and Reproducible Clinical Deep Learning
arXiv:2601.16414v2 Announce Type: replace Abstract: Difficulty replicating baselines, high computational costs, and required domain expertise create persistent barriers to clinical AI research. To address these challenges, we introduce PyHealth 2.0, an enhanced clinical deep learning toolkit that enables predictive modeling in as few as 7 lines of code. PyHealth 2.0 offers three key contributions: (1) a comprehensive toolkit addressing reproducibility and compatibility challenges by unifying 15+ datasets, 20+ clinical tasks, 25+ models, 5+ interpretability methods, and uncertainty quantification including conformal prediction within a single framework that supports diverse clinical data modalities - signals, imaging, and electronic health records - with translation of 5+ medical coding standards; (2) accessibility-focused design accommodating multimodal data and diverse computational resources with up to 39x faster processing and 20x lower memory usage, enabling work from 16GB laptops to production systems; and (3) an active open-source community of 400+ members lowering domain expertise barriers through extensive documentation, reproducible research contributions, and collaborations with academic health systems and industry partners, including multi-language support via RHealth. PyHealth 2.0 establishes an open-source foundation and community advancing accessible, reproducible healthcare AI. Available at pip install pyhealth.
arXiv (fysik & CS) Preprint 2026-05-19
Exploring Needs and Design Opportunities for Proactive Information Support in In-Person Small-Group Conversations
arXiv:2601.17240v2 Announce Type: replace Abstract: In-person small-group conversations play a crucial role in everyday life; however, facilitating effective group interaction can be challenging, as the real-time nature demands full attention, offers no opportunity for revision, and requires interpreting non-verbal cues. Using Mixed Reality to provide proactive information support shows promise in helping individuals engage in and contribute to group conversations. We present a preliminary participatory design and qualitative study (N = 10) using focus groups and two technology probes to explore the opportunities of designing proactive information support in in-person small-group conversations. We reveal key design opportunities concerning how to maximize the benefits of proactive information support and how to effectively design such supporting information. Our study is crucial for paving the way toward designing future proactive AI agents to enable the paradigm of augmented in-person small-group conversation experience.
arXiv (fysik & CS) Preprint 2026-05-19
Physics-guided curriculum learning for the identification of reaction-diffusion dynamics from partial observations
arXiv:2601.17382v2 Announce Type: replace Abstract: Reaction-diffusion (RD) systems provide fundamental models for understanding self-organized spatiotemporal patterns across natural and engineered settings, yet reliable parameter estimation remains challenging, particularly when observations are sparse, noisy, and restricted to a subset of state variables. We introduce CLIP (Curriculum Learning Identification via PINNs), a physics-guided framework built on physics-informed neural networks for joint parameter inference and hidden-state reconstruction under partial observability. Leveraging the physical separability of RD systems, the CLIP training progresses from reaction-dominated regimes to full spatiotemporal dynamics using curriculum learning and an anchored widening transfer strategy. Across three canonical reaction-diffusion benchmarks, CLIP achieves more accurate and robust identification than baseline methods. Furthermore, the CLIP framework is successfully applied to infer the dynamics of the Min system in bacteria, where only membrane-bound species are observed and key kinetic rates span multiple orders of magnitude. Ablation experiments and loss-landscape visualizations demonstrate that both the curriculum stages and the anchored transfer are essential for stable convergence.
arXiv (fysik & CS) Preprint 2026-05-19
New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions
arXiv:2605.18035v1 Announce Type: new Abstract: Hard-thresholding is an important type of algorithm in machine learning that is used to solve $\ell_0$ constrained optimization problems. However, the true gradient of the objective function can be difficult to access in certain scenarios, which normally can be approximated by zeroth-order (ZO) methods. The SZOHT algorithm is the only algorithm tackling $\ell_0$ sparsity constraints with ZO gradients so far. Unfortunately, SZOHT has a notable limitation on the number of random directions % in ZO gradients due to the inherent conflict between the deviation of ZO gradients and the expansivity of the hard-thresholding operator. This paper approaches this problem by considering the role of variance and provides a new insight into variance reduction: mitigating the unique conflicts between ZO gradients and hard-thresholding. Under this perspective, we propose a generalized variance reduced ZO hard-thresholding algorithm as well as the generalized convergence analysis under standard assumptions. The theoretical results demonstrate the new algorithm eliminates the restrictions on the number of random directions, leading to improved convergence rates and broader applicability compared with SZOHT. Finally, we illustrate the utility of our method on a ridge regression problem as well as black-box adversarial attacks.
arXiv (fysik & CS) Preprint 2026-05-19
Exploring Trust Calibration in XAI - The Impact of Exposing Model Limitations to Lay Users
arXiv:2605.18036v1 Announce Type: new Abstract: Trust calibration -- aligning user trust judgment with model capability -- is crucial for safe deployment of explainable AI (XAI), yet is often evaluated via global trust ratings detached from objective performance evidence. We present a preregistered, incentivized between-subject online study (N=418 representative UK sample) on explainable skin-lesion classification that disentangles expectation-setting from experienced performance. Participants completed 15 case evaluations using a fixed XAI panel (malignancy score, reliability score, and saliency map). We systematically manipulated five experimental onboarding conditions varying example-based information and limitation disclosures with five stimulus packages naturally varying observed prediction quality. Calibration was operationalized as the deviation between trust-related judgments (TAIS and case-wise ratings) and objective performance benchmarks for the encountered cases, analysed with hierarchical mixed-effects models. Only limitation disclosure for case-wise measures reliably impacts trust calibration, and short-term experience did not yield progressive calibration. Further, the experienced package of stimuli explained substantially more variance than the experimental manipulation. However, participants were hard-pressed to differentiate between case-wise perceived trust, trustworthiness, and accuracy estimation. We discuss implications for designing limitation communication and for measuring and analysing calibration metrics in XAI evaluations. All study materials and data of this study are publicly available for replication and further academic use.
arXiv (fysik & CS) Preprint 2026-05-19
SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals
arXiv:2605.18039v1 Announce Type: new Abstract: Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, and inconsistent topology. Existing methods typically trade off generalization, geometric fidelity, and efficiency. We address this by proposing SGSoft, a unified intrinsic pipeline that (i) constructs a geodesic correspondence field on a canonical template, (ii) learns multimodal dense descriptors guided by pretrained semantic priors with this geodesic correspondence field supervision, (iii) retrieves dense correspondences in a single feed-forward pass via nearest-neighbor search in descriptor space. This formulation enables stable and topology-invariant supervision under large pose variation, structural differences, and remeshing. SGSoft achieves state-of-the-art inter-category generalization while offering the best accuracy-efficiency trade-off among prior methods. It also achieves near real-time inference without pre-alignment, pairwise optimization, or post-refinement. Learned descriptors can be transferred effectively to downstream tasks such as semantic segmentation and deformation transfer, establishing a scalable and deployment-ready paradigm for dense 3D correspondence.
arXiv (fysik & CS) Preprint 2026-05-19
The Powers of Precision: Structure-Informed Detection in Complex Systems -- From Customer Churn to Seizure Onset
arXiv:2601.21170v3 Announce Type: replace Abstract: Emergent phenomena -- onset of epileptic seizures, sudden customer churn, or pandemic outbreaks -- often arise from hidden causal interactions in complex systems. We propose a machine learning method for their early detection that addresses a core challenge: unveiling and harnessing a system's latent causal structure despite the data-generating process being unknown and partially observed. The method learns an optimal feature representation from a one-parameter family of estimators -- powers of the empirical covariance or precision matrix -- offering a principled way to tune in to the underlying structure driving the emergence of critical events. A supervised learning module then classifies the learned representation. We prove structural consistency of the family and demonstrate the empirical soundness of our approach on seizure detection and churn prediction, attaining competitive results in both. Beyond prediction, and toward explainability, we ascertain that the optimal covariance power exhibits evidence of good identifiability while capturing structural signatures, thus reconciling predictive performance with interpretable statistical structure.
arXiv (fysik & CS) Preprint 2026-05-19
FG-TreeSeg: Flow-Guided Tree Crown Segmentation without Instance Annotations
arXiv:2602.00470v2 Announce Type: replace Abstract: Individual tree crown segmentation is an important task in remote sensing for forest biomass estimation and ecological monitoring. However, accurate delineation in dense, overlapping canopies remains a bottleneck. While supervised deep learning methods suffer from high annotation costs and limited generalization, emerging foundation models (e.g., Segment Anything Model) often lack domain knowledge, leading to under-segmentation in dense clusters. To bridge this gap, we propose FG-TreeSeg, a training-free framework for tree crown instance segmentation that transfers flow-based delineation from biomedical imaging to remote sensing. By modeling tree crowns as star-convex objects within a topological flow field using Cellpose-SAM, the FG-TreeSeg framework forces the separation of touching tree crown instances based on vector convergence. Experiments on the NEON and BAMFOREST datasets and visual inspection demonstrate that our framework generalizes robustly across diverse sensor types and canopy densities, which can offer a training-free solution for tree crown instance segmentation and labels generation.
arXiv (fysik & CS) Preprint 2026-05-19
Supervised sparse auto-encoders for interpretable and compositional representations
arXiv:2602.00924v3 Announce Type: replace Abstract: Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack of alignment between learned features and human semantics. In this paper, we address these limitations by adapting unconstrained feature models, a mathematical framework from neural collapse theory, and by supervising the task. We supervise (decoder-only) SAEs to reconstruct feature vectors by jointly learning sparse concept embeddings and decoder weights. Validated on Stable Diffusion 3.5, our approach demonstrates compositional generalization, successfully reconstructing images with concept combinations unseen during training, and enabling feature-level intervention for semantic image editing without prompt modification.
arXiv (fysik & CS) Preprint 2026-05-19
FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression prediction
arXiv:2605.18055v1 Announce Type: new Abstract: Predicting spatial gene expression from routine H\&E enables large-scale molecular profiling, yet current models treat this as isolated pointwise tasks, thereby overlooking essential biological structures like gene coordination and spatial distribution. To preserve these relationships, we introduce \textbf{FLAG}, a diffusion-based framework that redefines this task as structured distribution modeling. At the same time, we identify the critical \textbf{Gene Dimension Curse}, where joint modeling gene expression and their spatial interactions fail in high-dimensional spaces, and FLAG solves this challenge by integrating a spatial graph encoder for topological consistency and utilizing Gene Foundation Model (GFM) alignment for gene-gene fidelity in the generation process. To rigorously assess model performance, we propose a set of novel structural evaluation metrics, including Gene Structural Correlation (\textbf{GSC}) and Spatial Structural Correlation (\textbf{SSC}). Our experiments demonstrate that FLAG is highly competitive in traditional accuracy (PCC/MSE) while achieving significantly enhanced structural fidelity in capturing both gene-gene and gene-spatial relationships. The code is available at https://github.com/darkflash03/FLAG.
arXiv (fysik & CS) Preprint 2026-05-19
LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning
arXiv:2602.01705v3 Announce Type: replace Abstract: Reinforcement learning has become a central paradigm for improving LLM reasoning, but most existing methods optimize policies over discrete token sequences. This creates a mismatch between the optimization space and the structure of reasoning: many important decisions are semantic, global, and trajectory-level rather than local token choices. Continuous latent-space RL offers a promising alternative by allowing policies to explore higher-level reasoning representations. However, simply moving to latent space is not sufficient. The resulting policy must model a complex, multi-modal distribution over valid reasoning trajectories. We therefore propose Latent Diffusion Reasoning with Reinforcement Learning (LaDi-RL), where a diffusion model generates latent reasoning trajectories through iterative denoising. This formulation enables structured exploration and expressive distribution modeling, but also introduces a fundamental credit-assignment challenge: the policy acts in latent space, while rewards are observed only after the latent is decoded into text. A naive rollout strategy therefore entangles latent reasoning quality with text decoding quality, making it unclear whether an incorrect answer results from a poor latent trajectory or from an imperfect textual realization. To address this, we introduce hierarchical latent-text rollouts. We sample multiple text completions for each latent trajectory and aggregate their rewards to obtain a decoder-marginalized estimate of latent utility. This provides a cleaner and lower-variance reward signal for optimizing the diffusion policy. Empirically, LaDi-RL outperforms token-level RL by 9.4% on code generation and 5.7% on math reasoning in pass@1, and even surpasses the base model's pass@k performance.
arXiv (fysik & CS) Preprint 2026-05-19
Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models
arXiv:2602.02039v2 Announce Type: replace Abstract: The agency expected of Agentic Large Language Models goes beyond answering correctly, requiring autonomy to set goals and decide what to explore. We term this investigatory intelligence, distinguishing it from executional intelligence, which merely completes assigned tasks. Data Science provides a natural testbed, as real-world analysis starts from raw data rather than explicit queries, yet few benchmarks focus on it. To address this, we introduce Deep Data Research (DDR), an open-ended task where LLMs autonomously extract key insights from databases, and DDR-Bench, a large-scale, checklist-based benchmark that enables verifiable evaluation. Results show that while frontier models display emerging agency, long-horizon exploration remains challenging. Our analysis highlights that effective investigatory intelligence depends not only on agent scaffolding or merely scaling, but also on intrinsic strategies of agentic models.
arXiv (fysik & CS) Preprint 2026-05-19
Adaptive Control in Autonomous Driving via Real-Time Recurrent RL
arXiv:2602.02236v4 Announce Type: replace Abstract: We study online fine-tuning of pretrained control policies for autonomous driving using Real-Time Recurrent Reinforcement Learning (RTRRL), a memory-efficient algorithm that updates policy parameters at every time step without backpropagation through time. We extend RTRRL to support LrcSSM, a recently proposed nonlinear diagonal state-space model, and combine offline behavioral cloning with online RTRRL fine-tuning to adapt policies to distribution shifts at deployment. We validate the approach in the CarRacing simulation and on a 1:10-scale RoboRacer platform equipped with an event camera, where a pretrained policy is fine-tuned online during real-world line-following. To our knowledge, this is the first demonstration of online RL fine-tuning with event-camera observations on standard (non-spiking) hardware in closed-loop control. LrcSSM-based policies improve fastest and most consistently across both settings.
arXiv (fysik & CS) Preprint 2026-05-19
Contextual MetaML: Syntax and Full Abstraction
arXiv:2602.03033v2 Announce Type: replace Abstract: MetaML-style metaprogramming languages allow programmers to construct, manipulate and run code. In the presence of higher-order references for code, ensuring type safety is challenging, as free variables can escape their binders. In this paper, we present Contextual MetaML, \textit{the first metaprogramming language that supports storing and running open code under a strong type safety guarantee}. The type system utilises contextual modal types to track and reason about free variables in code explicitly. A crucial concern in metaprogramming-based program optimisations is whether the optimised program preserves the meaning of the original program. Addressing this question requires a notion of program equivalence and techniques to reason about it. In this paper, we provide a semantic model that captures contextual equivalence for Contextual MetaML, establishing \textit{the first full abstraction result for an imperative MetaML-style language}. Our model is based on traces derived via operational game semantics, where the meaning of a program is modelled by its possible interactions with the environment. We also establish a novel closed instances of use theorem that accounts for both call-by-value and call-by-name closing substitutions.
arXiv (fysik & CS) Preprint 2026-05-19
TIDAL: Recovering Temporal Phase for Cloud Block Storage Placement from LLM-Derived Semantics
arXiv:2605.18066v1 Announce Type: new Abstract: Cloud Virtual Disk (CVD) placement in Cloud Block Storage (CBS) is critical for resource efficiency and performance isolation. Existing schemes prioritize spatial load balancing by dispersing disks across pods based on configuration-derived load estimates. However, overload risk in CBS is fundamentally temporal. Even when average load is balanced, pods can still suffer transient congestion when the peaks of co-located disks align in time. Achieving complementary placement, which co-locates CVDs with offset peaks, is hard at provisioning time because new disks have no history from which to infer temporal phase. We present TIDAL, a CVD placement framework that recovers phase-aware signals for cold-start placement from an underused source: tenant-provided names and identifiers in provisioning metadata. TIDAL first uses LLMs to recover application semantics from noisy metadata such as project, VM, and disk names. It then translates these semantics into phase-aware temporal signals to guide complementary placement. To satisfy control-plane constraints, TIDAL adopts an offline-to-online design with teacher-student distillation, regex-based filtering, and prefix-aware caching, enabling CPU-only inference with millisecond-level latency. Evaluations driven by production traces show that TIDAL reduces overload frequency by 79.1% and P95 overload duration by 73.7% compared with the strongest baselines.
arXiv (fysik & CS) Preprint 2026-05-19
Balancing FP8 Computation Accuracy and Efficiency on Digital CIM via Shift-Aware On-the-fly Aligned-Mantissa Bitwidth Prediction
arXiv:2602.05743v2 Announce Type: replace Abstract: FP8 low-precision formats have gained significant adoption in Transformer inference and training. However, existing digital compute-in-memory (DCIM) architectures face challenges in supporting variable FP8 aligned-mantissa bitwidths, as unified alignment strategies and fixed-precision multiply-accumulate (MAC) units struggle to handle input data with diverse distributions. This work presents a flexible FP8 DCIM accelerator with three innovations: (1) a dynamic shift-aware bitwidth prediction (DSBP) with on-the-fly input prediction that adaptively adjusts weight (2/4/6/8b) and input (2$\sim$12b) aligned-mantissa precision; (2) a FIFO-based input alignment unit (FIAU) replacing complex barrel shifters with pointer-based control; and (3) a precision-scalable INT MAC array achieving flexible weight precision with minimal overhead. Implemented in 28nm CMOS with a 64$\times$96 CIM array, the design achieves 20.4 TFLOPS/W for fixed E5M7, demonstrating 2.8$\times$ higher FP8 efficiency than previous work while supporting all FP8 formats. Results on Llama-7b show that the DSBP achieves higher efficiency than fixed bitwidth mode at the same accuracy level on both BoolQ and Winogrande datasets, with configurable parameters enabling flexible accuracy-efficiency trade-offs.
arXiv (fysik & CS) Preprint 2026-05-19
Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers
arXiv:2602.05813v2 Announce Type: replace Abstract: We study adaptive learning rate scheduling for norm-constrained optimizers (e.g., Muon and Lion). We introduce a generalized smoothness assumption under which local curvature decreases with the suboptimality gap and empirically verify that this behavior holds along optimization trajectories. Under this assumption, we establish convergence guarantees under an appropriate choice of learning rate, for which warm-up followed by decay arises naturally from the proof rather than being imposed heuristically. Building on this theory, we develop a practical learning rate scheduler that relies only on standard hyperparameters and adapts the warm-up duration automatically at the beginning of training. We evaluate this method on large language model pretraining with LLaMA architectures and show that our adaptive warm-up selection consistently outperforms or at least matches the best manually tuned warm-up schedules across all considered setups, without additional hyperparameter search. Our source code is available at https://github.com/brain-lab-research/llm-baselines/tree/warmup
arXiv (fysik & CS) Preprint 2026-05-19
Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps
arXiv:2602.05993v3 Announce Type: replace Abstract: Flow and diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and brittle, a challenge commonly called reward alignment. We argue that efficient reward alignment should be a property of the generative model itself, not an afterthought, and redesign the model for adaptability. We propose "Diamond Maps", stochastic flow map models that enable efficient and accurate alignment to arbitrary rewards at inference time. Diamond Maps amortize many simulation steps into a single-step sampler, like flow maps, while preserving the stochasticity required for optimal reward alignment. This design makes search, Sequential Monte Carlo, and guidance scalable by enabling efficient and consistent estimation of the value function. Our experiments show that Diamond Maps can be learned efficiently via distillation from GLASS Flows, achieve stronger reward alignment performance, and scale better than existing methods. Our results point toward a practical route to generative models that can be rapidly adapted to arbitrary preferences and constraints at inference time.
arXiv (fysik & CS) Preprint 2026-05-19
A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback
arXiv:2605.18073v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate strong potential for automated code generation, yet their ability to iteratively refine solutions using execution feedback remains underexplored. Competitive programming offers an ideal testbed for this investigation, as it demands end-to-end algorithmic reasoning, precise implementation under strict computational constraints, and complete functional correctness with rigorous evaluation. In this paper, we present A-ProS, an autonomous AI agent that solves competitive programming problems through a hybrid multi-model feedback framework separating solution generation from specialized debugging. A-ProS combines ChatGPT-based generators (GPT-4 and GPT-5) with three debugging critics: Codestral-2508, Llama-3.3-70B, and DeepSeek-R1, under a 2 x 3 factorial design. We evaluate six workflows on 367 problems from ICPC World Finals (2011-2024) and Codeforces (rated 1200-1800). The results show that GPT-5 workflows improve from 39 initial accepted solutions to 85-90 after three refinement rounds, while GPT-4 improves from 15 to 31-38. A controlled ablation on 47 problems shows that stateful refinement outperforms stateless approaches by 8.5-10.6 percentage points and reduces repeated failures by up to 3.5x. Compared to baseline agent loops, A-ProS achieves over 2x greater gains, highlighting the importance of persistent context and multi-model feedback for reliable autonomous program synthesis.
arXiv (fysik & CS) Preprint 2026-05-19
4DLidarOpen: An Open 4D FMCW Lidar Dataset for Motion-Aware Autonomous Driving
arXiv:2605.18074v1 Announce Type: new Abstract: We present 4DLidarOpen, a large-scale open multi-modal dataset for autonomous driving, centered on 4D frequency-modulated continuous-wave (FMCW) Lidar sensing. Unlike conventional time-of-flight Lidar datasets that mainly provide geometric measurements, 4DLidarOpen includes point-wise radial velocity measurements from a forward-facing 4D FMCW Lidar, together with multiple Lidars of different types, including rotating, solid-state, and blind-spot variants, surround-view cameras, and 6-DOF ego-vehicle poses. The dataset was collected in complex urban environments in Beijing and covers dense pedestrian interactions, congested traffic, high-speed driving, and unprotected maneuvers. 4DLidarOpen provides synchronized multi-sensor data and 3D bounding-box annotations with persistent track IDs across five object categories. A hybrid annotation strategy is adopted, where large-scale auto-labeled data support scalable training and human experts refine annotations for the human-annotated training and validation sets. Based on this dataset, we establish benchmarks for 3D object detection, birds-eye view (BEV) segmentation and flow prediction, and motion forecasting with planning. Extensive experiments show that direct velocity measurements from 4D FMCW Lidar provide complementary motion cues for dynamic-scene understanding. Compared with geometric-only sensing, the velocity-aware representation improves motion-related perception and downstream forecasting and planning, especially in scenarios involving vulnerable road users and fast-moving objects. These results indicate that 4D FMCW Lidar is a promising sensing modality for motion-aware autonomous driving. The dataset and evaluation toolkit are publicly released to support research on 4D scene understanding, multi-Lidar fusion, and velocity-aware perception and planning.
arXiv (fysik & CS) Preprint 2026-05-19
Thinking with Geometry: Active Geometry Integration for Spatial Reasoning
arXiv:2602.06037v5 Announce Type: replace Abstract: Recent progress in spatial reasoning with Multimodal Large Language Models (MLLMs) increasingly leverages geometric priors from 3D encoders. However, most existing integration strategies remain passive: geometry is exposed as a global stream and fused in an indiscriminate manner, which often induces semantic-geometry misalignment and redundant signals. We propose GeoThinker, a framework that shifts the paradigm from passive fusion to active perception. Instead of feature mixing, GeoThinker enables the model to selectively retrieve geometric evidence conditioned on its internal reasoning demands. GeoThinker achieves this through Spatial-Grounded Fusion applied at carefully selected VLM layers, where semantic visual priors selectively query and integrate task-relevant geometry via frame-strict cross-attention, further calibrated by Importance Gating that biases per-frame attention toward task-relevant structures. Comprehensive evaluation results show that GeoThinker sets a new state-of-the-art in spatial intelligence, achieving a peak score of 72.6 on the VSI-Bench. Furthermore, GeoThinker demonstrates robust generalization and significantly improved spatial perception across complex downstream scenarios, including embodied referring and autonomous driving. Our results indicate that the ability to actively integrate spatial structures is essential for next-generation spatial intelligence. Code can be found at https://github.com/Li-Hao-yuan/GeoThinker.
arXiv (fysik & CS) Preprint 2026-05-19
Equilibrium Selection in Multi-Agent Policy Gradients via Opponent-Aware Basin Entry
arXiv:2605.18078v1 Announce Type: new Abstract: Multi-agent policy-gradient methods have been shown to converge locally near stable Nash equilibria. Local convergence, however, does not determine which equilibrium is reached. We study this question through basin-entry probability with respect to a target set of equilibria selected by an external criterion, such as payoff dominance. For finite-unroll Meta-MAPG, we show that the update decomposes into ordinary policy gradient plus own-learning and peer-learning corrections, with controlled sampling noise and finite-unroll bias. We identify the peer-learning correction as the main equilibrium-selection mechanism: under a local alignment condition, the probability of entering the certified attraction region of the target stable-Nash set increases, relative to ordinary policy gradient. Because persistent correction may shift zero-update points of the original game, annealing the correction after entering the basin recovers ordinary policy-gradient dynamics and inherits local stable-Nash convergence guarantees. Experiments in Stag Hunt, iterated Prisoner's Dilemma, and preliminary neural-policy coordination environments support this basin-entry view, showing increased entry into cooperative basins under peer-aware updates.
arXiv (fysik & CS) Preprint 2026-05-19
The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-Thought
arXiv:2605.18079v1 Announce Type: new Abstract: Existing expressivity results for transformers typically rely on hardmax attention, high precision, and other architectural modifications that disconnect them from the models used in practice. We bridge this gap by analyzing standard transformer decoders with softmax attention and rounding of activations and attention weights, while allowing depth and width to grow logarithmically with the context length. As an intermediate step, we construct hardmax transformers with ternary activations and well-separated attention scores that simulate Turing machines using Chain-of-Thought (CoT). This lets us convert the constructions to equivalent softmax transformers without the unrealistic parameter magnitudes or activation precision that prior approaches would require. Using the same technique, we analyze a recently proposed summarized CoT paradigm and show that it simulates Turing machines more efficiently, with model size scaling logarithmically in a space bound rather than a time bound. We empirically test predictions made by our results on a Sudoku reasoning task and find better alignment with learnability than for prior high-precision results. Our code is available at https://github.com/moritzbroe/transformer-expressivity.
arXiv (fysik & CS) Preprint 2026-05-19
Wonderboom -- Efficient, and Censorship-Resilient Signature Aggregation for Million Scale Consensus
arXiv:2602.06655v2 Announce Type: replace Abstract: Over the last years, Ethereum has evolved into a public platform that safeguards the savings of hundreds of millions of people and secures more than $650 billion in assets, placing it among the top 25 stock exchanges worldwide in market capitalization, ahead of Singapore, Mexico, and Thailand. As such, the performance and security of the Ethereum blockchain are not only of theoretical interest, but also carry significant global economic implications. At the time of writing, the Ethereum platform is collectively secured by almost one million validators highlighting its decentralized nature and underlining its economic security guarantees. However, due to this large validator set, the protocol takes around 15 minutes to finalize a block which is prohibitively slow for many real world applications. This delay is largely driven by the cost of aggregating and disseminating signatures across a validator set of this scale. Furthermore, as we show in this paper, the existing protocol that is used to aggregate and disseminate the signatures has several shortcomings that can be exploited by adversaries to shift stake proportion from honest to adversarial nodes. In this paper, we introduce Wonderboom, the first million scale aggregation protocol that can efficiently aggregate the signatures of millions of validators in a single Ethereum slot (x32 faster) while offering higher security guarantees than the state of the art protocol used in Ethereum. Furthermore, to evaluate Wonderboom, we implement the first simulation tool that can simulate such a protocol on the million scale and show that even in the worst case Wonderboom can aggregate and verify more than 2 million signatures within a single Ethereum slot.