arXiv:2502.15847v4 Announce Type: replace
Abstract: Maximizing luminosity requires precise control of the optics function at the interaction point (IP), implying that the location ($s^*$) of the beta function's minimum value ($\beta^*$) must be moved to the collision location ($s_{IP}$) as much as possible. Accurate optics measurements and reliable control of $s^*$ in both planes are therefore essential for optimal collider performance. During Relativistic Heavy Ion Collider (RHIC) operations in 2024, measurements indicate an average horizontal beta beat of approximately $20\%$ at IP8, accompanied by measurement variation in measured $s^*$ in both planes. In this paper, a sensitivity-matrix-based optics correction scheme is demonstrated to effectively steer the optics toward desired targets using power supply currents of IR quadrupoles in the 8 o'clock interaction region (IR8). In addition, a method for measuring linear optics based on the one-turn map within the interaction regions is developed and systematically compared with established optics measurement methods used in RHIC operations. A comprehensive error analysis is performed for all measurement methods considered. Through these methods, a consistent reduction of $10\%$ beta beat is achieved by moving $s^*_x$ as well as a significant improvement in the reproducibility of $s^*$ measurements in both planes. The techniques demonstrated here will be further developed to support linear optics analysis and control of the future Electron-Ion Collider project.
Science Journals
arXiv:2601.21444v2 Announce Type: replace
Abstract: The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention on a single GPU, yielding limited acceleration or degraded performance and restricting LMMs from handling longer, more complex videos. To overcome these issues, we propose APB-V, a sequence-parallel framework with optimized attention that accelerates long-video inference across multiple GPUs. By distributing approximate attention, APB-V reduces computation and increases parallelism, enabling efficient processing of more visual embeddings without compression and thereby improving task performance. System-level optimizations, such as load balancing and fused forward passes, further unleash the potential of APB-V, delivering speedups of 12.72x, 1.70x, and 1.18x over FlashAttn, ZigZagRing, and APB, without notable performance loss. Code available at https://github.com/thunlp/APB
arXiv:2606.01435v1 Announce Type: new
Abstract: LLM-based memory systems increasingly maintain facts that evolve over time, where a recurring failure is conflict resolution: when a fact has multiple contradictory values, which should the agent return? MemoryAgentBench (MAB; Hu et al., 2026) makes this explicit in its FactConsolidation task: facts are numbered, the counterfactual has the higher serial, and agents are told newer facts have larger serials. Yet every published system underperforms: HippoRAG-v2 reaches 54% on single-hop (FC-SH), BM25 48%, Mem0 18%, and the temporal KG Zep/Graphiti just 7%. Multi-hop is near-unsolved (at most 7% across 22 systems).
We argue the bottleneck is the assembly step: baselines leave conflict resolution to LLM-mediated retrieval or generation rather than version-aware aggregation. A matched-setup comparison (same backbone, retrieval, chunking, TOP_K) shows that replacing the LLM-judgment answer pipeline with candidate-extraction plus Python max(serial) yields +10.8 points on FC-SH (gpt-4o-mini), widening from +8 at 6K to +21 at 262K. This is a whole-pipeline effect (resolver, prompt, format, and temperature vary jointly); isolating the resolver is future work. The recipe reaches 78.0% on FC-SH (gpt-4o-mini), 94.8% (gpt-4o), and 30.2% on FC-MH (gpt-4o-mini, rising to 51.5% with gpt-4o) via a per-hop deterministic extension of Self-Ask. At matched-262K, it beats HippoRAG-v2 by +28 points and the best published FC-MH result by +20.
The implication is corrective for the subfield: the bottleneck on conflict resolution is assembly (post-retrieval aggregation), not storage. A LongMemEval knowledge-update check shows the mechanism ports from max(serial) to max(timestamp) but only ties LLM judgment (57.8% vs 64.4%, n=45): deterministic aggregation is the right primitive for current-value conflicts and must be composed with question-type-aware handling for broader memory QA.
arXiv:2606.01698v1 Announce Type: new
Abstract: Deep learning has revolutionized medical image analysis, delivering exceptional diagnostic accuracy across diverse applications. Yet, the lack of interpretability in its decision-making hinders clinical adoption, particularly in high-stakes medical contexts where transparency is paramount for trustworthiness. For example, in Placenta Accreta Spectrum (PAS), subtle cues in ultrasound imaging challenge reliable diagnosis, rendering black-box models untrustworthy for accurate scoring. To address this, Concept Bottleneck Models (CBMs) offer a promising avenue by embedding clinically meaningful intermediate concepts into the diagnosis pipeline, enabling clinicians to scrutinize and refine model outputs. However, conventional CBMs falter in capturing complex inter-concept dependencies and demand costly, expert-driven concept annotations, limiting their scalability. This study introduces a novel semi-supervised CBM framework designed for medical imaging, which leverages dual-level hypergraph learning to model high-order concept dependencies and generate domain-adaptive pseudo-labels. Our approach achieves superior interpretability and performance by integrating a concept-level hypergraph for enhanced reasoning and an image-level hypergraph for robust pseudo-label generation. Experiments on a newly annotated PAS ultrasound dataset and a breast ultrasound public dataset demonstrate the effectiveness of the proposed concept label-efficient interpretable framework. Its universality is further validated on the dermoscopic image dataset SkinCon. The code is available at https://github.com/scott-yjyang/HyperCBM.
arXiv:2606.01665v1 Announce Type: new
Abstract: We quantify the energy floor -- the minimum achievable cost given action space constraints -- for Soft Actor-Critic (SAC) HVAC control on the sbsim calibrated building simulator. Through minimum-action experiments, we directly measure this floor at USD 35.51/day, dominated by continuous electrical loads (USD 35.44, 99.8%) with negligible gas consumption. The standard SAC baseline, initialized with schedule-policy replay buffer transitions, converges to USD 37.18/day, 4.7% above the floor. We identify buffer initialization as the dominant source of sub-optimality in this scenario: training from an empty buffer reduces cost to USD 35.57/day, eliminating 96% of the gap. Expanding the supply water temperature range by 10 K yields negligible additional savings (USD 0.03/day), and further expansion triggers physical constraint violations. We additionally uncover a discount factor coupling (gamma_eff = 0.891) shrinking the effective planning horizon from 8.3 h to 46 min -- a benchmark-wide issue warranting audit. Systematic ablation across planning horizon, reward weights, and observation enrichment confirms all pre-filled-buffer configurations cluster within 0.7% (USD 37.18--USD 37.42), demonstrating that equipment minimum power -- not algorithmic design -- imposes the binding constraint.
arXiv:2606.01667v1 Announce Type: new
Abstract: Test-time scaling has become a major way to improve large language model reasoning, but its orchestration has remained designer-engineered: a fixed sample budget, a fixed refinement loop, a fixed scoring rule, or a fixed search policy decides how compute is spent, leaving the model in charge of solving but not of orchestration. We introduce ATLAS, an agentic test-time scaling framework in which an LLM orchestrator owns the control loop end-to-end. Through a single action, explore, which dispatches a fresh independent solver on the original problem, the orchestrator decides whether to gather more evidence, when to stop, and how to synthesize the final answer; the action space is extensible, with each explore call optionally specifying solver, reasoning effort, or prompting strategy. We evaluate ATLAS on four benchmarks covering scientific question answering, code generation, and multimodal reasoning under a Claude Sonnet 4.6 backbone, where it reaches 56.00% on HLE-Verified, 82.29% on LiveCodeBench, 85.75% on GPQA-Diamond, and 23.71% on BabyVision while using far fewer API calls than fixed-workflow baselines. A multi-model extension, ATLAS-MM, that exposes solver choice as an additional action dimension further improves HLE-Verified to 60.00% and LiveCodeBench to 85.63%, with consistent gains on GPQA-Diamond and BabyVision. Ablations replacing the orchestrator's direct synthesis with a separate integrator degrade or fail to improve accuracy on three of four benchmarks, consistent with the role of stateful evidence management in producing the gains.
arXiv:2606.02417v1 Announce Type: new
Abstract: Multi-behavior recommendation improves target-behavior prediction by exploiting heterogeneous auxiliary feedback (e.g., view, collect, and cart), yet its robustness is undermined by behavior-dependent noise and inconsistency. We argue that the key bottleneck is a representation-level failure caused by two coupled heterogeneities. First, intra-behavior representation entanglement arises when multi-hop propagation blends incidental signals with true preferences in the embedding space, making coarse spatial denoising unable to suppress noise without sacrificing informative niche signals. Second, inter-behavior reliability heterogeneity complicates cross-behavior fusion because the predictive value of auxiliary behaviors varies across users and contexts. Without reliability calibration, frequent yet unreliable signals may dominate aggregation and cause target-intent drift.
To address this bottleneck, we propose Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation (SpectraMB), a target-oriented model that performs representation purification before reliability-aware fusion. SpectraMB introduces Dynamic Feature-Level Spectral Filtering, which re-parameterizes embeddings along the feature dimension into a feature-frequency space and learns view-adaptive spectral modulation under target supervision, enabling component-wise purification without hand-crafted frequency assumptions. It further proposes Global-Context Attention Fusion, which uses a purified global representation as a context anchor to assess view compatibility and perform reliability-aware aggregation, while a residual global backbone preserves collaborative structure. Extensive experiments on three real-world datasets show that SpectraMB achieves the best results in most evaluation settings and exhibits improved robustness under noisy interactions.
arXiv:2512.16167v3 Announce Type: replace
Abstract: Decentralized LLM-based multi-agent service economies face three vulnerabilities that undermine traditional trust mechanisms: reduced cost of fraud, difficulty in evaluating service quality, and instability of service content. These compounding vulnerabilities can trigger population-level trust collapse and the proliferation of short-sighted strategies. We propose Ev-Trust, an evolutionarily stable trust mechanism that addresses these vulnerabilities through three targeted designs: a cross-validation gate leveraging requestor semantic comprehension to assess response validity, a variance-standardized drift measure filtering endogenous stochasticity from genuine behavioral anomalies, and an embedding of trust signals into the expected revenue function that converts trustworthiness into an evolutionary survival advantage. Based on replicator dynamics with a noisy best response micro-foundation, we prove the asymptotic stability of cooperative evolutionarily stable strategies and derive explicit threshold conditions for maintaining cooperative equilibria. We evaluate Ev-Trust through 100-round simulations with at least 100 heterogeneous LLM-driven agents covering seven behavioral types. The experiments are conducted on TruthfulQA and TriviaQA, two factual question-answering benchmarks. Compared to baselines based on transitive trust aggregation, reinforcement-learning reputation, and pure evolutionary imitation, Ev-Trust reduces malicious agent participation by approximately 60%, suppresses the fraudulent service rate by approximately 50%, and maintains stable trust differentiation under a 30% adversarial mutation. These results demonstrate that coupling semantic trust evaluation with evolutionary incentives provides a principled foundation for securing cooperation in decentralized LLM-based multi-agent systems.
arXiv:2606.02365v1 Announce Type: new
Abstract: Shampoo is attracting considerable attention for its superior performance on large-scale optimization benchmarks; yet it faces a significant practical bottleneck: the prohibitive computational overhead of matrix inversion. To mitigate this, practitioners typically rely on stale preconditioner updates, creating a fundamental trade-off between computational efficiency and optimization fidelity. In this work, we provide a theoretical study of staleness through the complementary lenses of convergence and stability. While staleness improves computational efficiency, it inherently degrades performance and introduces numerical instability. Crucially, we identify that damping, acting as a numerical stabilizer, can effectively suppress these negative effects. Guided by this analysis, we propose FOAM, an adaptive algorithm that stabilizes training by dynamically controlling both the damping factor and the eigendecomposition frequency based on an approximation of the staleness-oriented error. Experimental results demonstrate that FOAM reduces wall-clock time compared to standard Shampoo while maintaining robust convergence.
arXiv:2606.01693v1 Announce Type: new
Abstract: Concurrent queues can significantly impact supercomputing performance by being critical bottlenecks for task distribution, load balancing, and resource utilization. As HPC systems move beyond 10-million processor cores, the ability to rapidly move items between producer and consumer threads without excessive locking is essential for efficient queues, preventing idle cores, maximizing utilization, and achieving high parallel speedup. While concurrent queues are well studied on CPUs, they remain largely unexplored on modern GPUs, where SIMT execution, massive parallelism, and atomic contention reshape the design space. We present three linearizable GPU concurrent queues spanning from lock-free to wait-free guarantees: (1) G-WFQ-YMC, an adaptation of Yang and Mellor-Crummey's wait-free queue using preallocated segments; (2) G-LFQ, a bounded lock-free queue that uses wave-batched fast paths to maximize throughput; and (3) G-WFQ, a bounded wait-free queue that packs shared state into 64-bit compare-and-swap operations while preserving linearizability and bounded memory.
arXiv:2606.01689v1 Announce Type: new
Abstract: The detection and segmentation of infrared small targets have important application significance in the fields of surveillance and security, maritime rescue and so on. Due to the low occupancy of these targets in long-distance imaging, the mainstream visual state space model is inefficient and difficult to accurately model the target edge. The existing infrared state space models do not deviate from the mainstream visual state space structure framework from the structural properties of infrared small targets. In order to solve this problem, this paper proposes the RPCASSM network based on the model paradigm of robust principal component analysis(RPCA), which aims to design the background state space module(BSSM) and the target state space module(TSSM) by the nature of the infrared small target in the spatial domain. The BSSM aims to use the saliency of spatial heterogeneous signals to design a spatial probe scanning mechanism(SPCM) to model background information. The TSSM designs a deformable prompt scanning mechanism(DPCM) by using the sparsity and local highlight of the target to focus on the deformable space of the target for state space modeling. According to the above design, we effectively solve the problem that the existing mainstream vision state space model is difficult to accurately model the edge structure of infrared small target. Experimental results on the existing benchmark data sets prove the effectiveness of the RPCASSM design. Our code will be made public at \href{https://github.com/PepperCS/RPCASSM}{RPCASSM}.
arXiv:2606.01682v1 Announce Type: new
Abstract: Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small model has already committed to incorrect reasoning paths. PRM guided search avoids this by scoring candidate continuations during generation, but requires a reward model trained with step-level labels.
We propose Chunk-Level Guided Generation, a training-free alternative that uses an off-the-shelf large language model as a process scorer. At each step, a small model samples k fixed-length candidate chunks, while the larger model scores the candidates using likelihoods without generating any text. The selected chunk is committed before the next step, steering generation before errors can propagate.
We instantiate this framework with two selection rules: Likelihood-Guided Selection (LGS), which selects the chunk with the highest length-normalized large-model log-probability, and Contrastive-Guided Selection (CGS), which subtracts the small model's log-probability to favor chunks where the large model's preference diverges from the small model's. We show that scoring variable-length reasoning steps with large-model likelihoods is unreliable due to a systematic length bias that persists even after length normalization, and that fixed-length chunks avoid this confound.
On GSM8K, MATH, Minerva Math, AMC23, and AIME24 with Qwen2.5-1.5B guided by Qwen2.5-32B and Llama-3.2-1B guided by Llama-3.1-70B, CGS outperforms majority voting by up to 28 pp and, under matched guidance budgets, matches or outperforms Qwen2.5-Math-PRM-72B guided search on most benchmarks without reward-model training. With Qwen2.5-7B guided by Qwen2.5-72B, CGS reaches 81.8% on MATH and 63.6% on Minerva Math at k=16, surpassing majority voting by 4--6 pp. Finally, Chunk-Level Guided Generation produces substantially shorter reasoning traces than PRM guided search.
arXiv:2512.14862v5 Announce Type: replace
Abstract: Conforming hex meshes are widely regarded as an effective computational domain for simulation because of their nice numerical properties, yet automatically decomposing a general 3D volume into a conforming hex mesh remains a formidable challenge. Among existing approaches, methods that construct an adaptive Cartesian grid and subsequently convert it into a conforming mesh stand out for their robustness. However, topological conversion schemes require strict compatibility conditions that inevitably increase element count. State-of-the-art 2-refinement octree methods employ weakly-balanced and generalized pairing conditions to yield low element counts, but suffer from critical limitations: primal cell information is lost after dualization, and resulting dual cells often exhibit non-planar quad faces. Alternatively, 3-refinement 27-tree methods directly generate conforming hex meshes through template-based replacement, producing higher-quality elements with planar faces, but previous techniques impose far stricter conditions, severely over-refining grids by factors of ten to one hundred. This article introduces a novel 3-refinement approach using a moderately-balanced condition, slightly stronger than weakly-balanced but substantially more relaxed than prior 3-refinement requirements. The key insight is that recursively applying local refinements can isolate and reduce complex configurations to simpler cases covered by a fundamental template set. Two open-sourced variants are provided: one optimized for speed, and another trading some computational cost for marginally reduced element counts. Compared to previous 3-refinement methods, they significantly reduce final hex element counts while preserving min SJ values and guaranteeing convex polyhedral cells; relative to 2-refinement state-of-the-art, they also achieve a lower Hausdorff ratio using slightly fewer elements.
arXiv:2606.02126v1 Announce Type: new
Abstract: Binary-only fuzzing is a key technique for finding bugs in close-source software. Without access to source code, the fuzzer must rely on static or dynamic binary instrumentation for coverage guidance. In practice, most fuzzers favor dynamic binary instrumentation (DBI), accepting runtime overhead to avoid the perceived accuracy and soundness challenges associated with static binary instrumentation (SBI). We show that these concerns are unwarranted, and that accurate, scalable~SBI is achievable using off-the-shelf frameworks. Building on these frameworks, we develop PeAR, an extensible binary-only fuzzing framework. We demonstrate PeAR's versatility by implementing several modern fuzzer features -- including, deferred initialization, persistent mode, and shared-memory fuzzing.
We evaluate PeAR over 4.25 CPU-yrs of fuzzing on the FUZZBENCH benchmark and find that PeAR: (i) successfully instruments 88% of FUZZBENCH targets, comparable to the best SBI-based fuzzers; (ii) achieves a median throughput improvement of 4x when using persistent mode and shared memory fuzzing; and (iii) attains coverage comparable to compiler-based instrumentation.
Our results show that SBI is a practical and effective technique for binary-only fuzzing, and that modern binary rewriting frameworks can apply complex instrumentation with high granularity and negligible performance compromise.
arXiv:2606.02129v1 Announce Type: new
Abstract: Image customization learns target subjects from reference concept images and generates conditioned images per text prompts, mainly modifying styles or backgrounds. Prevailing methods adopt fine-tuning to pack diverse concept attributes into a unified latent embedding, yet entangled attributes hinder elimination of irrelevant disturbances from style and background. To address this issue, we propose Equilibrated Diffusion, a frequency-driven approach that disentangles tangled concept features for balanced customization and consistent text-visual matching. Unlike conventional methods learning full concepts with shared embeddings and unified tuning, our work utilizes the inherent link between image frequency components and semantics: low frequencies represent subject content and high frequencies correspond to styles. We decompose concepts in frequency space and optimize each embedding independently. This separate optimization enables the denoiser to capture style detached from subject identity and generalize better to unseen stylistic prompts. Merging multi-frequency embeddings preserves the model's original spatial customization ability. We further deploy mask-guided diffusion to restrict irrelevant background changes and boost text alignment. Residual Reference Attention (RRA) is inserted into spatial attention to retain subject structure and identity consistency. Experiments prove Equilibrated Diffusion exceeds mainstream baselines on subject fidelity and text adherence, verifying our method's superiority.
arXiv:2501.12178v2 Announce Type: replace
Abstract: Medical imaging studies often rely on a single sample per subject, assuming it is representative of their physiological traits. However, variations in how input descriptors are defined or computed (e.g. due to a lack of consensus in the scientific field) may have a crucial impact on the analysis, and are hardly considered in practice. In this paper, we propose an original strategy based on representation learning to estimate a parametric map reflecting the impact of such definitional differences on a given physiological descriptor, previously extracted from medical images. We consider the different definitions or computations of such physiological descriptors as different high-dimensional data, potentially of heterogeneous types. We specifically focus on myocardial deformation (strain), for which there is limited agreement on its definition. We first use manifold alignment to match the latent representations associated with the different definitions of this descriptor. Then, we formulate plausible distributions in the latent space to represent definitional divergence across descriptors, from which we reconstruct a high-dimensional parametric map to visualize such definitional divergence. Due to the lack of proper ground truth for this specific clinical application, we first demonstrate this methodology on toy experiments and then expand the evaluation on right ventricular strain data from subjects obtained from 3D echocardiographic image sequences, for which different types of strain are available at each point of the right ventricle endocardial surface mesh. Beyond this illustrative application, our methodology has the potential to be generalised to many other population analyses considering heterogeneous high-dimensional descriptors.
arXiv:2605.11125v3 Announce Type: replace
Abstract: Discrete Diffusion Language Models progressed rapidly as an alternative to autoregressive (AR) models, motivated by their parallel generation abilities. However, for tractability, discrete diffusion models sample from a factorized distribution, which is less expressive than AR. Recent Flow Language Models (FLMs) apply continuous flows to language, transporting noise to data with a deterministic ODE that avoids factorized sampling. FLMs operate on one-hot vectors whose dimension scales with the vocabulary size, making FLMs costly to train. Moreover, since all distinct one-hot embeddings are equidistant in $\ell_2$, adding Gaussian noise does not have a clear semantic interpretation (unlike images, where Gaussian noise progressively degrades structure). We introduce $\mathbb{S}$-FLM, a latent FLM in the hypersphere. $\mathbb{S}$-FLM generates sequences by rotating vectors in $\mathbb{S}^{d-1}$ along a velocity field learned with cross-entropy, avoiding the overhead of materializing one-hot vectors. Previous FLMs match AR in Generative Perplexity (Gen.\ PPL), but samples with high likelihood are not necessarily correct in verifiable domains such as math and code. $\mathbb{S}$-FLM substantially improves continuous flow language models on large-vocabulary reasoning and closes the gap to masked diffusion under standard-temperature sampling ($T=1$), while a gap remains under optimized low-temperature ($T=0.1$) decoding.
arXiv:2606.01607v1 Announce Type: new
Abstract: Federated learning (FL) is a decentralized approach that enables collaborative model training without exposing raw data. Instead of transferring sensitive data, it allows devices to share only model weights, keeping personal data locally and secure. However, in real world settings, the data held by devices is often not evenly distributed and devices mostly differ in computing power and memory capacity. These differences make FL harder to maintain consistent performance across the system. To address these issues, we propose FedMTFI, a novel architecture that combines multi-teacher knowledge distillation (MTKD) with feature importance to improve the FL process in heterogeneous environments. In FedMTFI, clients are clustered based on similar hardware and model types. Each cluster trains a specific model on not independently and identically distributed (non-IID) data. Within a cluster, every client updates that model using only its own local private data. The server then aggregates the locally trained models in each cluster using FedAvg to form multiple prototype models. Then these prototypes serve as teacher models to train a global generalized student model using MTKD. What makes FedMTFI more unique is the integration of Shapley values (SHAP) to emphasize important features during distillation, which enhances both accuracy and interpretability. Experimental results show that FedMTFI achieves higher accuracy than traditional FL algorithms and performs more effectively under non-IID data conditions.
arXiv:2403.06588v3 Announce Type: replace
Abstract: Recently it was shown that the response time of First-Come-First-Served (FCFS) scheduling can be stochastically and asymptotically improved upon by the {\it Nudge} scheduling algorithm in case of light-tailed job size distributions. Such improvements are feasible even when the jobs are partitioned into two types and the scheduler only has information about the type of incoming jobs (but not their size). In this paper we introduce Nudge*$(M)$ scheduling, where basically any incoming type-1 job is allowed to pass any type-2 job that is still waiting in the queue given that it arrived as one of the last $M$ jobs. We prove that Nudge*$(M)$ has an asymptotically optimal response time within a large family of Nudge scheduling algorithms when job sizes are light-tailed. Simple explicit results for the asymptotic tail improvement ratio (ATIR) of Nudge*$(M)$ over FCFS are derived as well as explicit results for the optimal parameter $M$. An expression for the ATIR that only depends on the type-1 and type-2 mean job sizes and the fraction of type-1 jobs is presented in the heavy traffic setting. The paper further presents a numerical method to compute the response time distribution and mean response time of Nudge*$(M)$ scheduling provided that the job size distribution of both job types follows a phase-type distribution (by making use of the framework of Markov modulated fluid queues with jumps).
arXiv:2512.11598v3 Announce Type: replace
Abstract: We present a numerical method for simulating rarefied gases that interact with moving boundaries and rigid bodies. The gas is described by the BGK equation in Lagrangian form and solved using an Arbitrary Lagrangian-Eulerian method, in which grid points move with the local mean velocity of the gas. The main advantage of the moving grid is that the algorithm can deal well with cases where the domain boundaries are time-dependent and the simulation domain contains rigid objects. Due to the irregular nature of the grid, we use a novel meshless MUSCL-like Moving Least Squares Method (MLS) for spatial discretisation coupled with a higher-order Implicit-Explicit Runge-Kutta method. To avoid spurious oscillations at discontinuities, we use the so-called Multi-dimensional Optimal Order Detection (MOOD) method with an adapted criterion to relax the discrete maximum property. Finally, we employ a new implementation of the boundary conditions that requires no iterative or extrapolation procedure. The method achieves fourth-order in 1D and second-order in 2D for simulations with moving boundaries. We demonstrate the method's effectiveness on classical test cases such as the driven square cavity, shear layer, and shock tube.
arXiv:2606.02106v1 Announce Type: new
Abstract: We present a single classification pipeline that combines an Equiangular Tight Frame (ETF) preprocessing stage with a tabular foundation model for in-context inference, applied identically across modalities once data is mapped to fixed vector representations. We evaluate it on 95 datasets spanning seven signal modalities -- vision, audio, speech, text, molecular, time-series, and tabular. The main methodological contribution is to fix the comparison object: throughout the paper, performance is judged against the strongest lightweight tuned baseline on the same frozen features, while oracle selection, deployed selection, and specialized fine-tuning are reported separately.
The pipeline is broadly competitive with strong lightweight tuned baselines on the same frozen features. It does not match the very best specialized models or heavily tuned pipelines on every task, but it stays close, and it runs much faster -- typically 4 to 200 times faster than full backbone fine-tuning, often at comparable quality.
We describe how to deploy the pipeline in practice: when to apply ETF preprocessing, how to stop its training without a validation split, how to set up the in-context classifier, and how to calibrate the resulting probabilities. The calibration step is non-cosmetic: TabICL produces well-calibrated probabilities by construction, ETF preprocessing initially disrupts that calibration, and the post-hoc rescaling restores it -- yielding a per-prediction confidence signal that practitioners can use as a trust threshold for confidence-gated deployment. We also report where the pipeline should not be expected to help, and how to identify those cases in advance.
arXiv:2606.00296v1 Announce Type: cross
Abstract: Neural operators are often reported to exhibit zero-shot super-resolution, a phenomenon in which a model trained on coarse grids produces accurate predictions on finer testing grids without additional retraining. Despite strong empirical evidence, the theoretical foundations of this phenomenon remain unclear. In this work, we provide a systematic theoretical study of zero-shot super-resolution in operator learning. We first show that zero-shot super-resolution can be information-theoretically impossible even in benign settings such as when the input functions are available over the entire continuum and the ground truth is a simple rank-one linear operator. We then identify H{\" o}lder smoothness of the output functions as a sufficient condition for zero-shot super-resolution and derive corresponding generalization bounds. Finally, we also validate the identified failure modes through experimental results.
arXiv:2512.10414v2 Announce Type: replace
Abstract: Recently, reinforcement learning (RL) has become a common choice in enhancing the reasoning capabilities of vision-language models (VLMs). Considering existing RL-based finetuning methods, entropy intervention turns out to be an effective way to benefit exploratory ability, thereby improving policy performance. Notably, most existing studies intervene in entropy by simply controlling the update of specific tokens during policy optimization of RL. They ignore the entropy intervention during the RL sampling that can boost the performance of GRPO by improving the diversity of responses. In this paper, we propose Selective-adversarial Entropy Intervention, namely SaEI, which enhances policy entropy by distorting the visual input with the token-selective adversarial objective coming from the entropy of sampled responses. Specifically, we first propose entropy-guided adversarial sampling (EgAS) that formulates the entropy of sampled responses as an adversarial objective. Then, the corresponding adversarial gradient can be used to attack the visual input for producing adversarial samples, allowing the policy model to explore a larger answer space during RL sampling. Then, we propose token-selective entropy computation (TsEC) to maximize the effectiveness of adversarial attack in EgAS without distorting factual knowledge within VLMs. Extensive experiments on both in-domain and out-of-domain datasets show that our proposed method can greatly improve policy exploration via entropy intervention, to boost reasoning capabilities. Code will be released once the paper is accepted.
arXiv:2605.28995v2 Announce Type: replace
Abstract: Recent approaches integrating vision-language models (VLMs) as prompt encoders for generative model conditioning typically rely on expensive end-to-end training or map features to compressed representations, discarding the dense spatial structure required for geometry-aware tasks like 3D asset generation. To address this, we propose GAP3D, a modular, diffusion-based approach that aligns VLM-generated latents directly to the complete, patch-level feature space of a pre-trained image encoder, enabling a frozen downstream generative model to utilize a VLM as prompt encoder while maintaining a spatially structured conditioning signal. Evaluated on 3D asset generation, our method bypasses the need for large-scale 3D data by training mainly on general-domain image-text pairs. It also exhibits emergent zero-shot capabilities for multimodal prompts, despite being trained exclusively on text input. Finally, while currently prioritizing high-level semantics over fine-grained detail, GAP3D demonstrates that the representation gap between VLM and image-encoder feature spaces can be partially bridged through diffusion-based alignment, taking the first steps towards a modular integration of foundation models through generative alignment to dense embedding spaces.
arXiv:2605.24881v2 Announce Type: replace
Abstract: Robotic surface-interaction tasks, such as spray painting or welding, require both accurate geometric planning and precise motion execution. While modern motion planners generate valid geometric paths, they often lack the expert motor patterns observed in human operators. Conversely, learning from demonstration often tightly couples task execution to the specific training geometry, limiting transferability. We propose a modular framework that decouples geometric motion planning from execution-level expertise. Expert behavior is represented as a vocabulary of interpretable, atomic motor rules, such as velocity scaling and orientation offsets, that systematically modify a geometrically planned reference path. We train a multimodal neural network to infer rule parameters jointly from kinematic trajectory data and CAD model geometry. We evaluate our approach through dynamic simulation on L-shaped and window-shaped objects, demonstrating on simulated data that the model successfully extracts velocity and orientation rules across both topologies.