Forskningsradar

Science Journals

Peer-reviewade publikationer — 56239 artiklar

arXiv (fysik & CS) Preprint 2026-06-04
InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space
arXiv:2606.05071v1 Announce Type: new Abstract: Language-guided photo retouching aims to adjust color and tone while preserving geometry and texture. Recently, diffusion-based retouching shows a superior visual quality, but often struggles with both fidelity issues due to its generative nature and efficiency because of its iterative sampling process. In this work, we propose an efficient and fidelity-preserving retouching method using bilateral space manipulation, which is both compact and content-decoupled. Specifically, instead of directly editing pixels or image latents, our model predicts a low-resolution bilateral grid of affine transforms, which are sliced using a learned guidance map and then applied to the full-resolution image. This approach yields both high fidelity and improved efficiency. To retain strong priors of a pretrained generative model, we distill a multi-step diffusion model into our bilateral grid framework using Variational Score Distillation, complemented by a prompt alignment loss to guide instruction-following behavior. Additionally, we introduce a new benchmark and evaluate our method across multiple dimensions: fidelity, instruction following, and efficiency. Compared to the latest retouch methods, like Gemini-2.5-Flash (Nano-Banana), our method can avoid content drift, significantly improve latency, and generate visually pleasing edits, while maintaining a high level of fidelity. Project page: https://openimaginglab.github.io/InstantRetouch/.
arXiv (fysik & CS) Preprint 2026-06-04
From Symbolic to Geometric: Enabling Spatial Reasoning in Large Language Models
arXiv:2606.04381v1 Announce Type: new Abstract: Recent large language models (LLMs) often appear to exhibit spatial reasoning ability; however, this capability is largely \emph{symbolic}, arising from pattern matching over spatial language rather than true \emph{geometric} reasoning over space. Because LLMs operate on discrete tokens, they lack native support for continuous spatial representations, explicit geometric computation, and structured spatial operators. To address this limitation, we introduce the \emph{Spatial Language Model (SLM)}, the first multimodal LLM that treats location information as a first-class modality and enables geometric spatial reasoning within the model's inference process. SLM directly operates on learned spatial representations rather than textual descriptions of spatial relations. To support effective training, we construct a \emph{Spatial Instruction Dataset} that aligns spatial representations, atomic geometric operations, and natural language instructions. We further propose a new benchmark named \emph{SpatialEval}, which is designed to evaluate spatial reasoning across attributes, distance, topology, and relative-position tasks. Extensive experiments show that SLM significantly outperforms existing LLM-based approaches that rely on symbolic reasoning via prompt engineering or textual abstraction, demonstrating the benefits of integrating geometric spatial representations for robust spatial reasoning. Our instruction dataset, evaluation benchmark, model training codes, and models' checkpoints can be found at: \hyperlink{https://github.com/chuchen2017/SLM}{https://github.com/chuchen2017/SLM}.
arXiv (fysik & CS) Preprint 2026-06-04
Network node immunization: improving Netshield algorithm through random rooted forests
arXiv:2606.04131v1 Announce Type: new Abstract: We are interested in the so-called multiple-node immunization problem for complex networks under attack by a viral agent. It consists in identifying and removing a set of nodes of size $k$ in a graph to maximize the impeding of virus spread. A few approaches have been proposed in the literature based on numerical and theoretical insights on how classical models for virus spread evolve on graphs. Based on the analysis of these models, the maximal eigenvalue of the adjacency matrix of the graph has become a classical measure of how resilient the network is. Thus, a clear, well-explored approach for multiple-node immunization consists of identifying a set of $k$ nodes in such a way that the reduced network, obtained by removing these nodes, has a minimal largest eigenvalue. This spectral optimization problem turns out to be a computationally hard problem for which only greedy algorithms offer good solutions at efficient computational time. Among those, the so-called Netshield algorithm represents one of the reference choices. The latter is, in fact, a clearly defined algorithm aiming at optimizing a certain sub-modular functional, called shield-value, which approximates the original optimization problem. We propose here a novel procedure, based on random walk kernels and related random spanning forests, to build a new algorithm, referred to as K-shield, which enhances Netshield searching performance at the same computational complexity. We give theoretical insights behind this novel method, which could also be used for other optimization problems, and then test it via numerical showcase experiments on various benchmarks.
arXiv (fysik & CS) Preprint 2026-06-04
Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness
arXiv:2606.05073v1 Announce Type: new Abstract: Missing value imputation is a fundamental task in machine learning, with most existing methods assuming that all missing entries correspond to unobserved regular values. In many real-world datasets, however, missingness may arise from two distinct sources: some entries are meaningfully missing (intrinsically absent and semantically valid), while others are missing due to the observation process and should be imputed. We formalize this distinction as a selective imputation problem, where the goal is to jointly infer which missing entries should be preserved and which should be recovered. To address this challenge, we propose Diff-Joint, a diffusion-based framework that jointly models tabular data together with a latent missingness mask. The method alternates between conditional sampling and uncertainty-aware aggregation to iteratively refine both imputed values and missingness labels. Empirical results on synthetic and real-world datasets demonstrate that Diff-Joint effectively identifies meaningfully missing entries while achieving competitive imputation accuracy and improved downstream task performance.
arXiv (fysik & CS) Preprint 2026-06-04
Size and solvent effects on cellulose transverse anisotropy and toughening design
arXiv:2606.05074v1 Announce Type: new Abstract: Cellulose nanocrystals (CNCs) are a promising class of materials derived from the most abundant natural polymer resource on Earth. Hydroxyl-induced polarity is a crucial advantage of CNCs, making them promising for advanced design and application. Side chain hydroxyls, hydrogen bonds, and particular crystal structures of CNCs lead to unique anisotropy. However, the nuanced anisotropy in the transverse section is not sufficiently stressed, and cannot be precisely described experimentally. Although partially covered by previous studies, a quantitative explanation of size dependency and a systematic comparison of solvent influences are still lacking. The manufacturing of cellulose materials requires a better understanding of anisotropy, size dependency, and solvent influences. In this study, the anisotropic performance of CNCs in characteristic directions and a diverse array of solvent environments was carefully inspected and compared using molecular simulations. Furthermore, a data-supported explanation for the size dependency, and transverse arrangement toughness-enhanced designs were both proposed. These systematic comparisons and unique transverse arrangements could aid future applications of cellulose.
arXiv (fysik & CS) Preprint 2026-06-04
Preferential orientation of slender elastic floaters in gravity waves
arXiv:2604.08323v2 Announce Type: replace Abstract: Slender floaters drifting in propagating gravity waves slowly rotate towards a preferential state of orientation with respect to the angle of incidence. This angular drift arises from a wave-induced, second order mean yaw moment. We develop a diffractionless, hydro-elastic theory to compute this mean yaw moment for a thin, flexible structure whose width and thickness are small compared with the wavelength. For floater lengths smaller than half the wavelength, we derive a simple, predictive criterion for the preferred orientation: Soft, short and heavy floaters prefer the longitudinal state, while stiff, long and light floaters prefer the transverse state. For floaters longer than the wavelength, the orientational dynamics become more intricate and may exhibit multiple equilibrium states. We discuss the implications of the model for flexible floating structures such as pontoons and inflatable structures.
arXiv (fysik & CS) Preprint 2026-06-04
The Accountability Horizon: An Impossibility Theorem for Governing Human-Agent Collectives
arXiv:2604.07778v2 Announce Type: replace Abstract: Existing accountability frameworks for AI systems, legal, ethical, and regulatory, rest on a shared assumption: for any consequential outcome, at least one identifiable person had enough involvement and foresight to bear meaningful responsibility. This paper proves that agentic AI systems violate this assumption not as an engineering limitation but as a mathematical necessity once autonomy exceeds a computable threshold. We introduce Human-Agent Collectives, a formalisation of joint human-AI systems where agents are modelled as state-policy tuples within a shared structural causal model. Autonomy is characterised through a four-dimensional information-theoretic profile (epistemic, executive, evaluative, social); collective behaviour through interaction graphs and joint action spaces. We axiomatise legitimate accountability through four minimal properties: Attributability (responsibility requires causal contribution), Foreseeability Bound (responsibility cannot exceed predictive capacity), Non-Vacuity (at least one agent bears non-trivial responsibility), and Completeness (all responsibility must be fully allocated). Our central result, the Accountability Incompleteness Theorem, proves that for any collective whose compound autonomy exceeds the Accountability Horizon and whose interaction graph contains a human-AI feedback cycle, no framework can satisfy all four properties simultaneously. The impossibility is structural: transparency, audits, and oversight cannot resolve it without reducing autonomy. Below the threshold, legitimate frameworks exist, establishing a sharp phase transition. Experiments on 3,000 synthetic collectives confirm all predictions with zero violations. This is the first impossibility result in AI governance, establishing a formal boundary below which current paradigms remain valid and above which distributed accountability mechanisms become necessary.
arXiv (fysik & CS) Preprint 2026-06-04
From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data
arXiv:2604.04974v3 Announce Type: replace Abstract: Video is a scalable observation of physical dynamics: it captures how objects move, how contact unfolds, and how scenes evolve under interaction -- all without requiring robot action labels. Yet translating this temporal structure into reliable robotic control remains an open challenge, because video lacks action supervision and differs from robot experience in embodiment, viewpoint, and physical constraints. This survey reviews methods that exploit non-action-annotated temporal video to learn control interfaces for robotic manipulation. We introduce an interface-centric taxonomy organized by where the video-to-control interface is constructed and what control properties it enables, identifying three families: direct video-action policies, which keep the interface implicit; latent-action methods, which route temporal structure through a compact learned intermediate; and explicit visual interfaces, which predict interpretable targets for downstream control. For each family, we analyze control-integration properties -- how the loop is closed, what can be verified before execution, and where failures enter. A cross-family synthesis reveals that the most pressing open challenges center on the robotics integration layer -- the mechanisms that connect video-derived predictions to dependable robot behavior -- and we outline research directions toward closing this gap.
arXiv (fysik & CS) Preprint 2026-06-04
High-Temperature and High-Speed Atomic Force Microscopy Using a qPlus Sensor in Liquid via Quadpod Scanner and Hybrid-Loop Frequency Demodulation
arXiv:2604.04970v2 Announce Type: replace Abstract: Atomic-resolution imaging on molten metal/solid interfaces at temperatures above 200 {\deg}C was achieved using a high-temperature, high-speed atomic force microscope (AFM) equipped with a qPlus sensor. A tip-scanning high-speed Quadpod scanner for a large mass load of qPlus sensor (2.3 g) was developed to enhance thermal drift tolerance by high-speed scanning and thermal insulation from the heated specimen. This scanner has dominant resonant frequencies of 7.05 kHz (lateral) / 29.7 kHz (vertical) without a load. In addition, the Hybrid-loop frequency demodulation technique for low-resonant-frequency ($f_0$) sensors with a wider bandwidth than conventional phase-locked loop was also established, providing a demodulation bandwidth of $B_{\Delta f_\mathrm{inst}}\sim 0.26 f_0$ without exceeding the theoretical noise of the input deflection signal. Combining these techniques enabled atomic-resolution imaging on the molten $\mathrm{Ga/PtGa_x}$ interface at $\sim$210 {\deg}C. The topographic images obtained at $\sim$210 {\deg}C showed a relatively low-symmetry surface with an oblique lattice with a superstructure, which differed from the primitive rectangular lattice observed in the non-heated sample left at room temperature for 96 h. This demonstrates that the developed high-temperature, high-speed AFM techniques for qPlus sensors enable visualization of non-aqueous liquid/solid interfaces above 200 {\deg}C at atomic resolution, which has various potential applications, such as injection modeling, soldering, and the fabrication of liquid-metal-based catalysts.
arXiv (fysik & CS) Preprint 2026-06-04
Schedule-Level Shared-Prefix Reuse for LLM RL Training
arXiv:2606.01143v3 Announce Type: replace Abstract: GRPO-based LLM post-training commonly samples multiple trajectories from the same prompt and then trains on the resulting group. In long-context GRPO workloads, this shared prompt-side prefix can contain retrieved passages, visual tokens, tool schemas, system instructions, or task context, while the full rollout group is still too large to pack into one training microbatch. Standard dense trainers therefore recompute the same prefix forward and backward for every trajectory. We present a schedule-level reuse mechanism that decouples prefix and suffix computation. The schedule runs prefix forward once, executes suffixes as ordinary microbatches while reading prefix K/V and accumulating prefix-side gK/gV , and then runs prefix backward once on the accumulated gradient cache. This reordered schedule is equivalent to baseline training over real arithmetic and aligns numerically within finite-precision tolerance. Because only K/V and gK/gV are hot during suffix computation, the approach offloads dormant prefix activations, integrates with TP/EP/CP/PP and DP-style placement at the execution level, and preserves aux-loss-based MoE router semantics through logical prefix-token accounting. On dense Llama3-8B, Qwen3-8B, and MoE Qwen3-MoE-30B-A3B configurations, the schedule matches optimizer updates across TP/CP/PP/EP combinations, aligns on a 100-step real GRPO actor-update trace replay, reaches up to 4.395x speedup (2.930x under a conservative compile-on comparison) as prefix ratio and GRPO group size grow, and reduces Phase-B peak HBM by up to 59.1%, extending the Llama3-8B capacity frontier from 17,920 to 29,696 total tokens.
arXiv (fysik & CS) Preprint 2026-06-04
Bridging High-Level Intent and Network Execution: Detecting Violations and Intent Drift Through Low-Level Traffic Analysis
arXiv:2606.05076v1 Announce Type: new Abstract: Intent-Based Networking (IBN) structures a core management pillar for autonomous 6G networks by translating high-level administrative goals into autonomous configurations, yet a critical validation gap persists between declarative intent and data-plane execution. This paper investigates this gap by formalizing low-level flow headers into standardized 7-tuple vectors, establishing an Internal Low-Level Intent (ILI) telemetry interface. Leveraging an empirical dataset of 100.91 million flow records from a distributed honeynet, we evaluate three administrative policy regimes (Strict, Balanced, and Permissive) across two metrics: Policy Violations ($V$) and Intent Drift ($D$). Our results expose a distinct Compliance Paradox where widening policy permissiveness systematically suppresses violation counts, yet underlying operational intent drift remains mostly invariant. This demonstrates that conventional, violation-centric tracking are unreliable. Furthermore, an empirical case study show that ILI metrics structural violations can inform closed-loop orchestrators to dynamically recalculate and enforce low-level rules that maintain high-level operational intent.
arXiv (fysik & CS) Preprint 2026-06-04
Attention-Augmented LSTMs for Automatic Homophonic Ciphertext Decipherment
arXiv:2606.05078v1 Announce Type: new Abstract: Homophonic substitution ciphers replace each plaintext letter with one of several possible ciphertext codes, deliberately weakening letter-frequency patterns and making automated decipherment difficult. This paper evaluates whether an attention-augmented Long Short-Term Memory (LSTM) model can learn such mappings in a historically motivated shared-key setting: all ciphertexts draw from the same known homophonic code pool, while individual keys use different consistent subsets of that pool. Using synthetic ciphertexts generated with ChronoFidelius from historical English and Swedish texts dated 1500--1899, we test performance across ciphertext lengths, centuries, variable-length codes, and simulated transcription errors. Models are trained only on aligned ciphertext--plaintext pairs, without external language models, frequency statistics, or key-search heuristics. Results show near-perfect character-level decryption accuracy across both languages and all periods, including short and noisy ciphertexts. The model also fails predictably on ciphertexts outside the shared pool, indicating that it functions as a practical tool for decipherment and key-space verification when key reuse is suspected.
arXiv (fysik & CS) Preprint 2026-06-04
Inclusion-of-Thoughts: Mitigating Preference Instability via Purifying the Decision Space
arXiv:2604.04944v2 Announce Type: replace Abstract: Multiple-choice questions (MCQs) are widely used to evaluate large language models (LLMs). However, LLMs remain vulnerable to the presence of plausible distractors. This often diverts attention toward irrelevant choices, resulting in unstable oscillation between correct and incorrect answers. In this paper, we propose Inclusion-of-Thoughts (IoT), a progressive self-filtering strategy that is designed to mitigate this cognitive load (i.e., instability of model preferences under the presence of distractors) and enable the model to focus more effectively on plausible answers. Our method operates to reconstruct the MCQ using only plausible option choices, providing a controlled setting for examining comparative judgements and therefore the stability of the model's internal reasoning under perturbation. By explicitly documenting this filtering process, IoT also enhances the transparency and interpretability of the model's decision-making. Extensive empirical evaluation demonstrates that IoT substantially boosts chain-of-thought performance across a range of arithmetic, commonsense reasoning, and educational benchmarks with minimal computational overhead.
arXiv (fysik & CS) Preprint 2026-06-04
Gradient estimators for parameter inference in discrete stochastic kinetic models
arXiv:2604.02121v2 Announce Type: replace Abstract: Stochastic kinetic models are ubiquitous in physics, yet inferring their parameters from experimental data remains challenging. For deterministic models, parameter inference often relies on gradients, which can be obtained efficiently through automatic differentiation (AD). However, AD cannot be applied directly to the Gillespie stochastic simulation algorithm (SSA), since sampling from a discrete set of reactions introduces non-differentiable operations. In this work, we adopt three gradient estimators from machine learning for the Gillespie SSA: the Gumbel-Softmax Straight-Through (GS-ST) estimator, the Score Function estimator, and the Alternative Path estimator. We use the estimators to evaluate gradients of steady-state and time-dependent observables, and compare their performance in representative biophysical systems with relaxation dynamics (bimolecular association) and oscillatory dynamics (repressilator). We find that the GS-ST estimator generally yields well-behaved gradient estimates, but exhibits diverging variance in challenging parameter regimes, which can cause parameter inference to fail. In these cases, other estimators provide more robust, lower variance gradients. Our results demonstrate that gradient-based parameter inference can be effectively combined with the Gillespie SSA, with different estimators offering complementary advantages.
arXiv (fysik & CS) Preprint 2026-06-04
Fast & Faithful Function Vectors
arXiv:2606.05079v1 Announce Type: new Abstract: Function vectors (FVs) are task representations elicited during in-context learning that can be used to steer Large Language Models (LLMs). However, design choices in their formulation remain underexplored. In this work, we study the impact of varying FV definitions for instructions along two degrees of freedom: attention head selection and steering. For head selection, using gradient-based attributions with Layer-wise Relevance Propagation (LRP) substantially improves efficiency as well as accuracy. For FV steering, applying it in a distributed manner yields a higher accuracy compared to simple aggregation. Our code is publicly available.
arXiv (fysik & CS) Preprint 2026-06-04
Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues
arXiv:2606.04591v1 Announce Type: new Abstract: With the widespread adoption of multi-modal communication platforms, long-form dialogues interleaving text and images have become increasingly common. Users often need to retrieve coherent dialogue fragments related to specific topics, rather than isolated utterances. We propose Fine-grained Fragment Retrieval (FFR), which locates semantically relevant multi-utterance, multi-image fragments in multi-modal long-form dialogues. We explore two settings: (1) FFR within Single-Dialogue, retrieving fragments from a given dialogue; and (2) FFR within Dialogue Corpus, retrieving from a large-scale corpus for open-domain scenarios. For (1), we introduce F2RVLM, a generation-based retrieval model trained with reinforcement learning, using multi-objective rewards and difficulty-aware curriculum sampling to enhance fragment coherence. For (2), we develop FFRS, a two-stage system combining offline fragment-level indexing with online retrieval. Specifically, each dialogue is decomposed into minimal semantic fragments encoded by a Fragment Embedding Model (FEM) into a vector database; at inference, FEM rapidly recalls Top-K candidates, and F2RVLM performs fine-grained reasoning to identify the most relevant sub-content. To support FFR, we construct MLDR, the longest multi-modal dialogue retrieval dataset to date, and a WeChat-based real-world test set. Experiments on both benchmarks demonstrate that F2RVLM and FFRS consistently achieve superior performance across single-dialogue and corpus-level FFR.
arXiv (fysik & CS) Preprint 2026-06-04
Reasoning Shift: How Context Silently Shortens LLM Reasoning
arXiv:2604.01161v2 Announce Type: replace Abstract: Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these reasoning behaviors remains underexplored. To investigate this, we conduct a systematic evaluation of multiple reasoning models across three scenarios: (1) problems augmented with lengthy, irrelevant context; (2) multi-turn conversational settings with independent tasks; and (3) problems presented as a subtask within a complex task. We observe an interesting phenomenon: reasoning models tend to produce much shorter reasoning traces (up to 65%) for the same problem under different context conditions compared to the traces produced when the problem is presented in isolation. A finer-grained analysis reveals that this compression is associated with a decrease in self-verification and uncertainty management behaviors, such as double-checking. While this behavioral shift does not compromise performance on straightforward problems, it might affect performance on more challenging tasks. Additionally, we show that targeted supervised fine-tuning partially mitigates the adverse effects of irrelevant context. We hope our findings draw additional attention to both the robustness of reasoning models and the problem of context management for LLMs and LLM-based agents.
arXiv (fysik & CS) Preprint 2026-06-04
Automatic Generation of Titles for Research Papers Using Language Models
arXiv:2606.05085v1 Announce Type: new Abstract: The title of a research paper conveys its primary idea and, occasionally, its conclusions in a clear and concise manner. Choosing an appropriate title is often challenging, and automated title generation can assist authors in this task. In this work, we propose a technique to generate paper titles from abstracts using open-weight pre-trained and large language models. We use the CSPubSum and LREC-COLING-2024 datasets and introduce a new dataset, SpringerSSAT, curated from four Springer journals in the social sciences. Additionally, we use GPT-3.5-turbo in a zero-shot setting to generate titles. Model performance is evaluated with ROUGE, METEOR, MoverScore, BERTScore, and SciBERTScore metrics. Our experiments show that fine-tuned PEGASUS-large outperforms other models, including fine-tuned LLaMA-3-8B and zero-shot GPT-3.5-turbo, across most metrics. We further demonstrate that ChatGPT can generate creative paper titles. Overall, AI-generated titles are generally appropriate and reliable.
arXiv (fysik & CS) Preprint 2026-06-04
Orthogonal Learner for Estimating Heterogeneous Long-Term Treatment Effects
arXiv:2604.00915v2 Announce Type: replace Abstract: Estimation of heterogeneous long-term treatment effects (HLTEs) is relevant for personalized decision-making in marketing, economics, and medicine, where short-term observational datasets are often combined with long-term observational datasets. However, HLTE estimation is challenging due to limited overlap in treatment assignments or in long-term outcomes for certain subpopulations, which can lead to unstable HLTE estimates with large finite-sample variance. To address this challenge, we introduce the LT-O-learners (Long-Term Orthogonal Learners), a set of novel orthogonal learners for HLTE estimation in the canonical HLTE setting with surrogacy. The key idea of our LT-O-learners is to retarget the loss via custom overlap weights that downweight low-overlap samples. We show that the retargeted loss recovers the true HLTE pointwise and satisfies Neyman-orthogonality. We further prove two key theoretical results: (i) The nuisance error enters the error bound only through higher-order terms, which means our learners are robust to nuisance estimation error. (ii) Under a linear function class, the retargeting effectively controls the asymptotic variance of the HLTE estimator via the overlap weights in low-overlap regimes. We conduct experiments on synthetic and real-world datasets to confirm the theoretical properties of our LT-O-learners, particularly robustness in low-overlap regimes. To our knowledge, ours are the first orthogonal learners for HLTE estimation robust to low overlap in long-term settings.
arXiv (fysik & CS) Preprint 2026-06-04
Light or Full Verb? A Minimal-Pair Dataset for Probing Phraseological Competence in Language Models
arXiv:2606.05087v1 Announce Type: new Abstract: Frequent English verbs such as 'have' and 'make' can function either as collocates in light-verb constructions or as full lexical predicates, as in 'make a decision' vs. 'make a cake'. Whether language models represent this distinction remains unclear. We introduce a large-scale controlled dataset of minimally varying English sentence series in which the same context contains the same verb in light-verb and full-verb uses. Two probing experiments show that language models differentiate between these uses even in minimal contexts and exhibit separable patterns across object types. We release the dataset, generation code, and materials as a reusable resource. The framework supports extensions to broader contexts, additional verbs, and other languages.
arXiv (fysik & CS) Preprint 2026-06-04
Pinpoint: Grounded Worldwide Image Geolocation via Cross-Source Retrieval and Reranking
arXiv:2606.04133v1 Announce Type: new Abstract: Image geolocation aims to estimate where a photograph was taken from its visual content. At worldwide scale, this remains challenging because visual evidence is often ambiguous, diverse, and unevenly distributed. Prior work has typically treated geolocation of ordinary internet photos and street-view imagery as separate tasks, despite their complementary strengths: internet photos better match the appearance distribution of user-captured queries, while street-view imagery provides denser, geographically grounded coverage. We present Pinpoint, a retrieve-and-rerank architecture that combines both sources in a coarse-to-fine pipeline. A contrastive image-GPS embedder is trained on both user-uploaded Flickr photos and street-view imagery, learning a shared image-GPS embedding space that is used to retrieve candidate locations. An attention-based reranker then rescores retrieved candidates by combining candidate-level visual and GPS features with cross-source evidence from nearby locations to ground the prediction. Unlike recent prior work, Pinpoint does not rely on multimodal large-language models, making inference faster and more reproducible. Pinpoint achieves state-of-the-art results across all metrics on standard benchmarks for internet photos (IM2GPS3k and YFCC4k) and street-view imagery (OSV-5M).
arXiv (fysik & CS) Preprint 2026-06-04
The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents
arXiv:2606.04296v1 Announce Type: new Abstract: As autonomous AI agents move from conversational systems to long-horizon software execution, runtime safety layers that decide when to interrupt an agent have become essential. We study this timing problem using a continuous 18-dimensional affective-dynamics engine (HEART) as a diagnostic probe, evaluating four intervention trigger families - absolute state thresholds, composite state-action patterns, regex reasoning-feature extraction, and zero-shot LLM-as-judge - against human-annotated intervention points on SWE-bench-Verified debugging traces. We report three findings. First, a State Saturation Trap: agents show no recovery signal under sustained difficulty, so modeled frustration quickly crosses the threshold and stays at its maximum, converting threshold-on-state triggers from moment detectors into near-constant indicators that fire on 39-83% of actions across five trajectories. Second, a capability-and-context floor for LLM judges: a small model (gpt-5.4-mini) never fires, while frontier and cross-vendor models escape the zero-firing floor only with full-trajectory context, and even then reach only F1 0.17-0.40 at up to 90x the cost. Third, and most importantly, the supervised target is not reproducible among humans: three trained annotators using one rubric on a 56-action trajectory agree on where to intervene only slightly above chance (location Krippendorff's alpha = +0.047; best pairwise Cohen's kappa = +0.349) and not at all on intervention type (pause degenerate; clarify below chance; reflect only alpha = +0.226). We conclude that intervention timing is a low-reliability construct, making single-annotator F1 an unsuitable optimization target. Our contribution is the joint mapping of this problem across human inter-rater reliability, four detector architectures, a cross-model LLM-judge sweep, and a reproduced saturation effect, rather than any single detector's accuracy.
arXiv (fysik & CS) Preprint 2026-06-04
Low Distortion Fusion Bonding using Pneumatically Warped Wafers
arXiv:2606.04625v1 Announce Type: new Abstract: Backside power-delivery-network (BSPDN) schemes require wafer-to-wafer bonding steps that do not leave high order shape changes or localized stresses in the bonded stack to ensure that these don't get transferred to the thinned wafer for further lithographic exposure. However, bonding mechanics involve strong adhesive forces which can inherently create localized distortions that lithography tools must eventually compensate. Some contributors to grid distortion of the target wafer are, method of bond initiation, bond front velocity variations, and lack of symmetry between the wafers. In this work, we evaluate a low-distortion bonding approach in the SUSS XBA tool, where some of these contributors are tackled at the source, namely by initiating the bond without a localized external force, and keeping the wafers compliant & symmetric during bonding. Wafers are bonded with a slight pre-stress due to controlled gas pressure applied over the whole backside of the wafers throughout bonding. Wafer-shape measurements of the bonded stacks are used to perform gradient-based in-plane-displacements (IPD) modelling to estimate bonding-induced grid distortion. Dense scanner metrology is used on patterned-bonded wafers to confirm the location and severity of distortion predictions from patterned wafer geometry (PWG) measurements. On the PWG distortion maps and scanner grid readouts, we perform alignment and CPE modelling with different field layouts. Sub-10 nm levels of residual grid distortion are achievable with relatively low-order correction models, and less than or equal to 3 nm by using advanced CPE models. These results demonstrate that pneumatically warped bonding yields low-distortion bonded stacks, and that simple process tuning can decouple the dominant distortion source from edge-related variability.
arXiv (fysik & CS) Preprint 2026-06-04
Bregman divergences and error control via convex duality
arXiv:2606.05088v1 Announce Type: new Abstract: Convex duality relations are a useful tool for deriving error estimates for challenging nonlinear and non-smooth variational problems. Applied at the continuous level they can deliver nonlinear analogues of the Prager-Synge a posteriori error identity, while at the discrete level they allow the derivation of minimal regularity a priori estimates. By leveraging elementary properties of Bregman divergences, we obtain three results on the error control via convex duality for a general class of problems: first, we prove a local efficiency bound for the duality gap error estimator, secondly, we derive a guaranteed a posteriori bound for non-conforming fields, and finally, we prove a minimal-regularity quasioptimal estimate for a Crouzeix-Raviart discretisation of the $\varphi$-Laplace problem.
arXiv (fysik & CS) Preprint 2026-06-04
Emotion Entanglement and Bayesian Inference for Multi-Dimensional Emotion Understanding
arXiv:2604.00819v2 Announce Type: replace Abstract: Understanding emotions in natural language is inherently a multi-dimensional reasoning problem, where multiple affective signals interact through context, interpersonal relations, and situational cues. However, most existing emotion understanding benchmarks rely on short texts and predefined emotion labels, reducing this process to independent label prediction and ignoring the structured dependencies among emotions. To address this limitation, we introduce Emotional Scenarios (EmoScene), a theory-grounded benchmark of 4,731 contextrich scenarios annotated with an 8-dimensional emotion vector derived from Plutchik's basic emotions. Motivated by the observation that emotions rarely occur independently, we further propose an entanglement-aware Bayesian inference framework that incorporates emotion co-occurrence statistics to perform joint posterior inference over the emotion vector. This lightweight post-processing does not require any parameter updates and improves the structural consistency of predictions, and yields overall gains of 2.24% Lexical Accuracy without any additional cost. EmoScene therefore provides a challenging benchmark for studying multi-dimensional emotion understanding and the limitations of current language models.