arXiv:2604.27853v2 Announce Type: replace Abstract: An innovative path for the detectors at future colliders to achieve higher performances is to use a Particle Flow approach, which requires highly granular calorimeters to image individual showers. The silicon-tungsten electromagnetic calorimeter (SiW-ECAL) aims at fulfilling all the expected physical and technical requirements. SiW-ECAL has been developed by the CALICE and ILD collaborations for more than two decades and is now reaching maturity, for linear machines. However, with the tendency towards circular machines, the progress of electronics and the rapid advancement of machine learning (ML) techniques, the SiW-ECAL design needs to be reoptimised to enhance its performance. This study develops ML-based reconstruction approaches for SiW-ECAL, achieving an approximate 20% improvement in energy resolution in the low-energy range and effectively correcting energy leakage in the high-energy range. Subsequently, the SiW-ECAL design is reoptimized based on this method.
Science Journals
arXiv:2508.16650v3 Announce Type: replace-cross Abstract: Brain tumour MRI typically requires both pre- and post-contrast imaging, but gadolinium is not always desirable (frequent follow-up, renal impairment, allergy, paediatric patients). We developed and validated a deep learning model to predict tumour contrast enhancement from non-contrast MRI alone. We assembled 11,089 brain MRI studies (2006-2024) from 10 datasets across four countries and three continents, spanning adult and paediatric populations with glioma, meningioma, metastases, and post-resection appearances. Three architectures were trained to detect and segment enhancing tumour from T1w, T2w and FLAIR alone. Performance was assessed in a 1,109-study held-out test set (primary endpoint: patient-level enhancement detection; secondary: voxel-level Dice). Eleven expert radiologists attempted the same task on a 564-case subset (100 cases each), blinded to history, prior imaging, and referral. The best model, nnU-Net, achieved 83.0% balanced accuracy (95% CI 79.1-87.2; sensitivity 91.5%, specificity 74.4%) for detection, with R2 = 0.859 for enhancement volume. Of enhancing cases, 76.8% reached Dice >= 0.3, 67.5% >= 0.5, and 50.2% >= 0.7. Under blinded conditions, radiologists' majority vote was lower (71.7% balanced accuracy; sensitivity 77.6%, specificity 65.8%). The proportion reaching Dice >= 0.3 varied by pathology (meningioma 93%, presurgical glioma 76%, metastases 74%, postoperative glioma 74%) and was lowest for paediatric cases (45%). Deep learning can identify contrast-enhancing brain tumours from non-contrast MRI. These models show promise as a triage or decision-support adjunct, such as in flagging studies likely to enhance so that contrast can be added to a non-contrast protocol, and may reduce gadolinium dependence in neuro-oncology imaging. Future work should optimise these models with radiologists.
arXiv:2606.15460v2 Announce Type: replace Abstract: Generative artificial intelligence (AI) has begun infiltrating the most ordinary domains of romantic life -- drafting apologies, softening reproaches, and decoding a partner's ambiguous messages. While recent scholarship on AI in intimate life has concentrated on chatbot companions, this article shifts the frame to AI as an intermediary in human-to-human romantic communication. Drawing on a multi-modal corpus of vernacular discourse from 2023 to 2026, we contribute two complementary concepts. The covert triad situates a structural change -- a relationship phenomenally dyadic but operationally triadic, with the third party visible only to the partner who deploys a model. Articulation labor names the mechanism whereby the expressive component of emotional labor -- converting felt experience into language that a partner can receive -- is increasingly delegated to AI, even as feeling labor remains lodged in the user. Authenticity, under these conditions, is being reconfigured from a property of linguistic authorship to one of emotional ownership, a shift actively contested.
arXiv:2606.23719v1 Announce Type: cross Abstract: Laser powder bed fusion (LPBF) is a promising additive manufacturing technique that suffers from quality assurance concerns. Predicting melt pools from process parameters is crucial for assessing quality prior to manufacturing but remains a difficult problem because of the complex physical processes underlying LPBF. Quantum computers present a new computing paradigm, providing a new approach to information processing using quantum entanglement and superposition. This paper presents a practical demonstration of a hybrid quantum-classical model that leverages quantum computing to improve process parameter feature extraction with a quantum feature encoder. To make the quantum approach computationally feasible for large datasets, we first employ a clustering algorithm to reduce the number of expensive quantum computations. These quantum features are then processed by a classical neural network to predict the melt pool morphology, allowing for more accurate predictions of melt pools. We demonstrate the method using a quantum simulator, analyze the effect of measurement shot noise on the predictive performance of the network, and verify the results using quantum hardware. Finally, by examining which quantum features are most important, we provide insights that can inform the future design of more effective quantum encoding circuits. Ultimately, the performance improvement over purely classical networks validates the hybrid approach, demonstrating an engineering application of quantum computing using noisy and intermediate scale quantum (NISQ) devices.
arXiv:2606.23766v1 Announce Type: cross Abstract: The detection and atmospheric characterization of exoplanets have entered a new data-intensive era driven by the James Webb Space Telescope and the upcoming Ariel mission. Modern surveys produce millions of light curves and high-resolution spectra that overwhelm traditional pipelines, motivating the rapid integration of Machine Learning and Deep Learning methods into the exoplanet workflow. This review synthesizes the latest progress in applying ML/DL techniques to exoplanet detection (transit identification, candidate vetting, false-positive rejection) and atmospheric characterization (retrieval, detrending, cross-correlation, surrogate modelling) in the context of JWST and Ariel. We start with classical algorithms such as Random Forests and Convolutional Neural Networks, move through Transformers and Recurrent architectures, then survey modern simulation-based inference using Neural Posterior Estimation and Flow Matching Posterior Estimation with normalizing or continuous normalizing flows. We discuss benchmark efforts, including the Ariel Machine Learning Data Challenges (2019 to 2025) hosted with NeurIPS, and key JWST case studies such as the WASP-39b Early Release Science programme. Results indicate that DL approaches consistently match or exceed traditional pipelines in both speed and accuracy, while ML-driven retrievals reduce inference time from CPU-hours to seconds and can accelerate nested-sampling retrievals by factors of 3-8 without compromising Bayesian evidence. We identify outstanding challenges interpretability, calibration of uncertainties under noisy data, hybrid modelling, and the generalization of models across instruments and planet populations and outline a research roadmap spanning the JWST era and beyond into Ariel's launch in 2029.
arXiv:2606.21690v2 Announce Type: replace Abstract: Phishing is a multi-modal threat. We present a hybrid pipeline that scores each modality with its own engine and fuses the results. Three engines are built, deployed, and independently benchmarked: a four-stage URL stack (Domain Guard, lexical model, threat intelligence, and an asymmetric L2 fusion sidecar); a generalization-hardened DistilBERT NLP classifier whose held-out real-phishing recall rises from 0.8% to 87.3%; and a threat-intelligence synchronizer with end-to-end OpenTelemetry instrumentation confirming 1:1 message conservation. A decision-level fusion stage, characterized on a 10,677-email whole-system benchmark, reaches F1=0.914 with a calibrated probabilistic-OR over URL, header, and phishing-probability channels while reducing held-out real-spam false positives to 3.6%. Because that benchmark uses proxy URL and header channels and an operating point still needing recalibration, we present it as a preliminary integrated result. For deployable detection, the limiting factor is how well a model generalizes, not how accurately it scores data drawn from its own training distribution.
arXiv:2606.24210v1 Announce Type: cross Abstract: A GNSS timing receiver under spoofing has no nominal-geometry fault for position-domain RAIM to bound: the threat is a slow, common-mode pull of served clock time that the receiver's own time-accuracy flag need not reveal. We make three graded contributions. First, a field measurement: solving the receiver clock trajectory from raw L1 pseudoranges and broadcast ephemeris, we show a recorded over-the-air spoof from the public JammerTest 2024 campaign pulled a u-blox ZED-F9P by about 1.01 ms of served time while it reported at most 51 ns, a gap near 20,000x. Second, an impossibility: against an adversary free to choose the ramp rate, no finite unconditional bound on undetected time error exists under a single self-referential clock-aided monitor, because a ramp slow enough to keep the disciplined reference in lock-step is never alarmed while the error grows without limit, so any finite guarantee is conditional. Third, the conditional bound: the Timing Protection Level (TPL), a model-free monitor's static detectability floor plus the oscillator's coast over the detection latency, holds given detection by an independent cross-satellite consistency check a coherent spoofer does not drive in lock-step. Each term is a closed form over a primitive verified in the open Kshana simulator, so the sum is reproducible by hand. Calibrated on the recorded attack, the budget is 114 ns at one-second recovery and 458 ns at a 60-second coast, thousands of times below the 1.01 ms accepted; a clock-aided sequential test alone gives essentially no protection on this slow ramp (it alarms only near the ~1 ms capture), while the model-free monitor alarms during the ramp. We are explicit: the bound is calibrated, not field-validated; carries no integrity-risk budget; and is reported as a band at long coast. The simulator, bound, and calibration example are open source under AGPL-3.0.
arXiv:2606.24291v1 Announce Type: cross Abstract: Hydrodynamic memory governs Brownian motion over a broad range of timescales, from acoustic wave propagation at short times to diffusive relaxation at long times. While confinement-induced corrections to Brownian diffusion are well established, how confinement modifies the full hydrodynamic response remains less explored. In this Letter, we use molecular-dynamics simulations of a neutrally buoyant colloidal particle in an explicit solvent to resolve the velocity autocorrelation function across a broad hydrodynamic spectrum. In the bulk, the simulations recover compressibility, added mass, the hydrodynamic long-time tail, and Stokes-Einstein diffusion without adjustable parameters. Near a rigid wall, the velocity correlations become anisotropic, their algebraic tails are modified, and the diffusion coefficients are reduced. Most importantly, the short-time dynamics reveals a pronounced enhancement of the effective added mass as the wall is approached. As such, the velocity autocorrelation function appears as a central quantity to bridge the zero-frequency mobility and the high-frequency inertial behaviour of a confined Brownian particle.
arXiv:2606.24703v1 Announce Type: cross Abstract: In this paper we consider a M/G/1 queue for which we want to minimize the expected response time. We show how to compute indices from $n$ samples of the job size distribution such that the corresponding index policy is asymptotically optimal as $n$ grows. This construction is based on a discretization of the bounded support of the job size distribution and a shift of the samples to their nearest discrete point to the right. We show that the Gittins index of the empirical distribution of these shifted samples is close to the Gittins index of the original distribution. This translates to the asymptotic optimality of the corresponding index policy for minimizing the expected response time. Numerical comparison with other approaches further confirm the efficiency of our approach.
arXiv:2606.24707v1 Announce Type: cross Abstract: A convexity space is an ordered pair $(V,\mathcal{C})$, where $V$ is an arbitrary set and $\mathcal{C}$ is a family of subsets of $V$, called convex, which contains $\{\emptyset,V\}$ and is closed under intersections and nested unions of its elements. For any $S\subseteq V$, the convex hull of $S$ is the inclusion-wise minimum convex set $C\in \mathcal{C}$ such that $S\subseteq C$. For a convex set $C\in \mathcal{C}$, an element $p\in C$ is an extreme of $C$ if $p$ does not belong to the convex hull of $C\setminus\{p\}$. A convexity $\mathcal{C}$ defined over $V$ is a convex geometry if any convex set $C\in \mathcal{C}$ is the convex hull of its extreme elements. Given an oriented graph $D = (V,A)$, the family $\mathcal{C}$ of subsets of $V$ is the $\overrightarrow{P_3}$-convexity defined over $D$ if $\mathcal{C}$ is formed by all (convex) sets $C\subseteq V$ such that no vertex $v\in V\setminus C$ is the central vertex of a directed path $P=(u,v,w)$ with $\{u,w\} \subseteq C$, while in the $\overrightarrow{P_3^*}$-convexity defined over $D$, we have that no vertex $v\in V\setminus C$ is the central vertex of a directed path $P=(u,v,w)$ such that $\{u,w\} \subseteq C$ and $(u,w)\notin A$. In this work, we present necessary and sufficient conditions over an oriented graph $D$ so that the $\overrightarrow{P_3}$-convexity over $D$ is geometric, or the $\overrightarrow{P_3^*}$-convexity over $D$ is geometric. While the first case implies a polynomial-time algorithm to decide whether the $\overrightarrow{P_3}$-convexity over $D$ is a geometric, we show that it is coNP-complete to decide whether the $\overrightarrow{P_3^*}$-convexity over $D$ is a convex geometry. We also present a family termed acyclic indifference oriented graphs and demonstrate that deciding whether the $\overrightarrow{P_3^*}$-convexity in this class is geometric can be solved in polynomial-time.
arXiv:2311.02960v5 Announce Type: replace Abstract: Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks perform hierarchical feature learning across layers. In this work, we attempt to unveil this mystery by investigating the structures of intermediate features. Motivated by our empirical findings that linear layers mimic the roles of deep layers in nonlinear networks for feature learning, we explore how deep linear networks transform input data into output by investigating the output (i.e., features) of each layer after training in the context of multi-class classification problems. Toward this goal, we first define metrics to measure within-class compression and between-class discrimination of intermediate features, respectively. Through theoretical analysis of these two metrics, we show that the evolution of features follows a simple and quantitative pattern from shallow to deep layers when the input data is nearly orthogonal and the network weights are minimum-norm, balanced, and approximate low-rank: Each layer of the linear network progressively compresses within-class features at a geometric rate and discriminates between-class features at a linear rate with respect to the number of layers that data have passed through. To the best of our knowledge, this is the first quantitative characterization of feature evolution in hierarchical representations of deep linear networks. Empirically, our extensive experiments not only validate our theoretical results numerically but also reveal a similar pattern in deep nonlinear networks which aligns well with recent empirical studies. Moreover, we demonstrate the practical implications of our results in transfer learning. Our code is available at https://github.com/Heimine/PNC_DLN.
arXiv:2401.14483v4 Announce Type: replace Abstract: In the current practices of machine learning, the evaluation of forecasts has become a cornerstone of scientific progress. A multitude of evaluation metrics have been suggested and used to qualify "good" forecasts. What do those metrics share? How are they related? In this work, we use a protocol borrowed from game-theoretic probability to show that a large part of evaluation metrics can be viewed as averaged outcomes of fair gambles. Intuitively, a fair gambler is one which a forecaster would expect to fail. Hence, the gambler's ability to gain disproves the quality of the forecast. Standard evaluation metrics are then variants of choices of such fair gambles. In particular, this choice is structured along two dimensions, one of which separates calibration-type and regret-type metrics. In particular, this framework sheds light on the relationship of calibration and regret showing a theoretical equivalence in their ability to evaluate when being scaled appropriately, but the incomparability of obtained scores.
arXiv:2405.19062v2 Announce Type: replace Abstract: Continuous-Time Dynamic Graphs (CTDGs) enable fine-grained modeling of evolving relational systems. However, most existing CTDG representation learning methods are tailored to in-distribution settings and exhibit limited robustness under out-of-distribution (OOD) shifts. Although recent causal approaches learn invariant representations via interventions, they are primarily designed for static or discrete-time graphs and become computationally prohibitive for CTDGs due to the combinatorial explosion of structural and temporal variations. To address these challenges, we propose CIR, a framework grounded in a novel structural causal model termed the ICCM. To avoid exhaustive interventions, we leverage the Normalized Weighted Geometric Mean (NWGM) to efficiently approximate interventional predictions. We further instantiate ICCM within a practical deep learning architecture that jointly captures invariant structural and temporal patterns through dedicated subgraph extractors, and maintains an environment memory bank to model distributional shifts across evolving contexts. Extensive experiments demonstrate that CIR consistently outperforms existing methods under diverse OOD scenarios.
arXiv:2406.13041v3 Announce Type: replace Abstract: Lower-bound analyses for nonconvex strongly-concave minimax optimization problems have shown that stochastic first-order algorithms require at least $\mathcal{O}(\varepsilon^{-4})$ sample complexity to find an $\varepsilon$-stationary point. Some works indicate that this complexity can be improved to $\mathcal{O}(\varepsilon^{-3})$ when the stochastic loss gradient is Lipschitz continuous. The question of achieving enhanced convergence rates under distinct conditions, remains open. In this work, we address this question for optimization problems that are nonconvex in the minimization variable and strongly concave or Polyak-Lojasiewicz (PL) in the maximization variable. We introduce novel bias-corrected momentum algorithms utilizing efficient Hessian-vector products. We establish convergence conditions and demonstrate a lower iteration complexity of $\mathcal{O}(\varepsilon^{-3})$ for the proposed algorithms. The effectiveness of the proposed method is validated through applications to robust logistic regression and robust adaptive cruise control.
arXiv:2605.12234v2 Announce Type: replace-cross Abstract: We present novel, ultra-thin, large-diameter silicon nitride windows for various soft X-ray applications. Together with the company NORCADA, we developed windows with 200 nm and 300 nm thickness withstanding pressure differences above 1 bar. The windows have an open diameter of 14 mm. They were intensively vacuum- and overpressure-tested, showing very good results. At a measurement campaign at the synchrotron radiation source SOLEIL in France, the transparency of the windows was measured over a range from 50 eV to 15 keV, giving results comparable with the expected transparencies.
arXiv:2501.03695v2 Announce Type: replace Abstract: With the advancement of blockchain technology, chained Byzantine Fault Tolerant (BFT) protocols have been increasingly adopted in practical systems, making their performance a crucial aspect of the study. In this paper, we introduce a unified framework utilizing Markov Decision Processes (MDP) to model and assess the performance of three prominent chained BFT protocols. Our framework effectively captures complex adversarial behaviors, focusing on two key performance metrics: chain growth and commitment rate. We implement the optimal attack strategies obtained from MDP analysis on an existing evaluation platform for chained BFT protocols and conduct extensive experiments under various settings to validate our theoretical results. Through rigorous theoretical analysis and thorough practical experiments, we provide an in-depth evaluation of chained BFT protocols under diverse attack scenarios, uncovering optimal attack strategies. Contrary to conventional belief, our findings reveal that while responsiveness can enhance performance, it is not universally beneficial across all scenarios. This work not only deepens our understanding of chained BFT protocols, but also offers valuable insights and analytical tools that can inform the design of more robust and efficient protocols.
arXiv:2501.07761v2 Announce Type: replace Abstract: Increasingly, recommender systems are tasked with improving users' long-term satisfaction. In this context, we study a content exploration task, which we formalize as a bandit problem with delayed rewards. There is an apparent trade-off in choosing the learning signal: waiting for the full reward to become available might take several weeks, slowing the rate of learning, whereas using short-term proxy rewards reflects the actual long-term goal only imperfectly. First, we develop a predictive model of delayed rewards that incorporates all information obtained to date. Rewards as well as shorter-term surrogate outcomes are combined through a Bayesian filter to obtain a probabilistic belief. Second, we devise a bandit algorithm that quickly learns to identify content aligned with long-term success using this new predictive model. We prove a regret bound for our algorithm that depends on the Value of Progressive Feedback, an information-theoretic metric that captures the quality of short-term leading indicators that are observed prior to the long-term reward. We apply our approach to a podcast recommendation problem, where we seek to recommend shows that users engage with repeatedly over two months. We empirically validate that our approach significantly outperforms methods that optimize for short-term proxies or rely solely on delayed rewards, as demonstrated by an A/B test in a recommendation system that serves hundreds of millions of users.
arXiv:2502.06707v2 Announce Type: replace Abstract: Recently, combining stock features with inter-stock correlations has become a common and effective approach for stock movement prediction. However, financial data presents significant challenges due to its low signal-to-noise ratio and the dynamic complexity of the market, which give rise to two key limitations in existing methods. First, the relationships between stocks are highly influenced by multifaceted factors including macroeconomic market dynamics, and current models fail to adaptively capture these evolving interactions under specific market conditions. Second, for the accuracy and timeliness required by real-world trading, existing financial data mining methods struggle to extract beneficial pattern-oriented dependencies from long historical data while maintaining high efficiency and low memory consumption. To address the limitations, we propose FinMamba, a Mamba-GNN-based framework for market-aware and multi-level hybrid stock movement prediction. Specifically, we devise a dynamic graph to learn the changing representations of inter-stock relationships by integrating a pruning module that adapts to market trends. Afterward, with a selective mechanism, the multi-level Mamba discards irrelevant information and resets states to skillfully recall historical patterns across multiple time scales with linear time costs, which are then jointly optimized for reliable prediction. Extensive experiments on U.S. and Chinese stock markets demonstrate the effectiveness of our proposed FinMamba, achieving state-of-the-art prediction accuracy and trading profitability, while maintaining low computational complexity. The code is available at https://github.com/TROUBADOUR000/FinMamba.
arXiv:2505.14251v2 Announce Type: replace Abstract: We study the problem of differentially private second moment estimation and present a new algorithm that achieve strong privacy-utility trade-offs even for worst-case inputs under subsamplability assumptions on the data. We call an input $(m,\alpha,\beta)$-subsamplable if a random subsample of size $m$ (or larger) preserves w.p $\geq 1-\beta$ the spectral structure of the original second moment matrix up to a multiplicative factor of $1\pm \alpha$. Building upon subsamplability, we give a recursive algorithmic framework similar to Kamath et al 2019, that abides zero-Concentrated Differential Privacy (zCDP) while preserving w.h.p. the accuracy of the second moment estimation upto an arbitrary factor of $(1\pm\gamma)$. We then show how to apply our algorithm to approximate the second moment matrix of a distribution $\mathcal{D}$, even when a noticeable fraction of the input are outliers.
arXiv:2506.14293v4 Announce Type: replace Abstract: We present Sleeping-DISCO 9M, a large-scale pre-training dataset for music and song. To the best of our knowledge, there are no open-source high-quality dataset representing popular and well-known songs for generative music modeling tasks such as text-music, music-captioning, singing-voice synthesis, melody reconstruction and cross-model retrieval. Past contributions focused on isolated and constrained factors whose core perspective was to create synthetic or re-recorded music corpus (e.g. GTSinger, M4Singer) and arbitrarily large-scale audio datasets (e.g. DISCO-10M and LAIONDISCO-12M) had been another focus for the community. Unfortunately, adoption of these datasets has been below substantial in the generative music community as these datasets fail to reflect real-world music and its flavour. Our dataset changes this narrative and provides a dataset that is constructed using actual popular music and world-renowned artists.
arXiv:2510.00814v2 Announce Type: replace Abstract: Robotic fabric manipulation remains challenging due to fabric deformability and occlusions from wrinkles and the manipulator. This paper defines Random-to-Target Fabric Flattening (RTFF) as the task of bringing a randomly wrinkled fabric to an arbitrary user-specified wrinkle-free target pose. RTFF requires simultaneous flattening and pose alignment, where the two objectives are inherently coupled since flattening the fabric displaces its pose, while realigning it tends to introduce wrinkles. To solve this task, this paper anchors both the current and target fabric states to the same template mesh, enabling direct vertex-level wrinkle and pose assessment without registration. Building on this representation, a hybrid Imitation Learning--Visual Servoing (IL--VS) RTFF policy is proposed. A novel Mesh Action Chunking Transformer (MACT) leverages structured mesh observations to achieve goal-conditioned coarse alignment from a compact demonstration set, after which VS ensures precise convergence to the target. The policy is validated on a real dual-arm teleoperation system, demonstrating precise alignment to unseen target poses, fabric types, and scales. Code and videos: https://kaitang98.github.io/RTFF_Policy/
arXiv:2510.04767v2 Announce Type: replace Abstract: While most autoregressive LLMs are constrained to one-by-one decoding, diffusion LLMs (dLLMs) have attracted growing interest for their potential to dramatically accelerate inference through parallel decoding. Despite this promise, the conditional independence assumption in dLLMs causes parallel decoding to ignore token dependencies, inevitably degrading generation quality when these dependencies are strong. However, existing works largely overlook these inherent challenges, and evaluations on standard benchmarks (e.g., math and coding) are not sufficient to capture the quality degradation caused by parallel decoding. To address this gap, we first provide an information-theoretic analysis of parallel decoding. We then conduct case studies on analytically tractable synthetic list operations from both data distribution and decoding strategy perspectives, offering quantitative insights that highlight the fundamental limitations of parallel decoding. Building on these insights, we propose ParallelBench, the first benchmark specifically designed for dLLMs, featuring realistic tasks that are trivial for humans and autoregressive LLMs yet exceptionally challenging for dLLMs under parallel decoding. Using ParallelBench, we systematically analyze both dLLMs and autoregressive LLMs, revealing that: (i) dLLMs under parallel decoding can suffer dramatic quality degradation in real-world scenarios, and (ii) current parallel decoding strategies struggle to adapt their degree of parallelism based on task difficulty, thus failing to achieve meaningful speedup without compromising quality. Our findings underscore the pressing need for innovative decoding methods that can overcome the current speed-quality trade-off. We release our benchmark to help accelerate the development of truly efficient dLLMs.
arXiv:2511.01489v2 Announce Type: replace Abstract: This work presents a requirement analysis for collaborative dialogues among medical experts and an inquiry dialogue game based on this analysis for incorporating explainability into multiagent system design. The game allows experts with different knowledge bases to collaboratively make recommendations while generating rich traces of the reasoning process through combining explanation-based illocutionary forces in an inquiry dialogue. The dialogue game was implemented as a prototype web-application and evaluated against the specification through a formative user study. The user study confirms that the dialogue game meets the needs for collaboration among medical experts. It also provides insights on the real-life value of dialogue-based communication tools for the medical community.
arXiv:2511.21945v3 Announce Type: replace Abstract: Generating complete 3D objects under partial occlusions (i.e., amodal scenarios) is a practically important yet challenging problem, as large portions of object geometry are unobserved in real-world scenarios. Existing approaches either operate directly in 3D, which ensures geometric consistency but often lacks generative expressiveness, or rely on 2D amodal completion, which provides strong appearance priors but does not guarantee reliable 3D structure. This raises a key question: how can we achieve both generative plausibility and geometric coherence in amodal 3D modeling? To answer this question, we introduce GENA3D (GENarative Amodal 3D), a framework that integrates learned 2D generative priors with explicit 3D geometric reasoning within a conditional 3D generation paradigm. The 2D priors enable the model to plausibly infer diverse occluded content, while the 3D representation enforces multi-view consistency and spatial validity. Our design incorporates a novel View-Wise Cross-Attention for multi-view alignment and a Stereo-Conditioned Cross-Attention to anchor generative predictions in 3D relationships. By combining generative imagination with structural constraints, GENA3D generates complete and coherent 3D objects from limited observations without sacrificing geometric fidelity. Experiments demonstrate that our method outperforms existing approaches in both synthetic and real-world amodal scenarios, highlighting the effectiveness of bridging 2D priors and 3D coherence in generating plausible and geometrically consistent 3D structures in complex environments.
arXiv:2512.24731v2 Announce Type: replace Abstract: Sound effects build an essential layer of multimodal storytelling, shaping the emotional atmosphere and the narrative semantics of videos. Despite recent advancement in video-text-to-audio (VT2A), the current formulation faces three key limitations: First, an imbalance between visual and textual conditioning that leads to visual dominance; Second, the absence of a concrete definition for fine-grained controllable generation; Third, weak instruction understanding and following, as existing datasets rely on brief categorical tags. To address these limitations, we introduce EchoFoley, a new task designed for video-grounded sound generation with both event level local control and hierarchical semantic control. Our symbolic representation for sounding events specifies when, what, and how each sound is produced within a video or instruction, enabling fine-grained controls like sound generation, insertion, and editing. To support this task, we construct EchoFoley-6k, a large-scale, expert-curated benchmark containing over 6,000 video-instruction-annotation triplets. Building upon this foundation, we propose EchoVidia a sounding-event-centric agentic generation framework with slow-fast thinking strategy. Experiments show that EchoVidia surpasses recent VT2A models by 40.7% in controllability and 12.5% in perceptual quality.