This work establishes the query complexity of learning high-dimensional boxes in the exact query learning setting. Let $X \subset \mathbb{R}^d$ be a set of $n$ points, labeled by a collection of $k$ boxes: the label of each point in $X$ is determined by the unique box containing it. A learner aims to exactly recover the labels for every point in $X$ given access to a label oracle. We consider three increasingly-structured settings. In the most general setting, there are no conditions on the boxes, and they may overlap. We show that CAL (Cohn-Atlas-Ladner 1994), a classical active learning algorithm, is minimax-optimal with query complexity $\Theta(kd \log (n/kd))$. When the boxes are disjoint, we examine two regimes. In the large-$k$ regime, CAL remains minimax-optimal. For the constant-$k$ regime, an optimized variant of the Halving algorithm (Heged\"{u}s 1995) can beat CAL by a $\log(d)$ factor. Finally, in the most-structured settings, the boxes correspond to the leaves of a constant-sized decision tree. We prove a tight query complexity of $\Theta(d + \log n)$ that is additive in $d$ and $\log n$, generalizing a recent result (Black-Larsen-Mazumdar-Saha-So 2026) that establishes the query complexity of learning decision stumps.
Text-to-3D solid retrieval faces a fundamental representation gap: while natural language describes intrinsic shapes, Boundary Representation (B-rep) entangles precise geometry with arbitrary variations in pose, scale, and boundary encoding conventions. Existing methods either discretize B-reps at the cost of analytic precision, or learn features from topological graphs without explicit invariance guarantees. We propose **SpectraBRep** (*Spectral Geometry for Text-to-B-rep Retrieval*), a framework based on geometric invariance and spectral descriptors that mathematically eliminates representation ambiguities prior to cross-modal alignment. Formalizing translation, rotation, reflection, uniform scaling, and contour re-indexing via group actions, we exploit the planar-profile-and-extrusion structure of engineering solids to construct a unified spectral descriptor across cross-sectional regions, contour boundaries, and extrusion depths. On public benchmarks, our method achieves state-of-the-art recall performance across all evaluation metrics.
LLMs often answer semantically equivalent queries inconsistently, even when the underlying facts are known. We formalize consistency as semantic invariance over equivalence classes of queries and show that invariance under arbitrary meaning-preserving transformations is undecidable in general. This motivates scoped semantic invariance, where model behavior is evaluated relative to bounded semantic domains. We operationalize this framework using knowledge graphs (KGs), which act as explicit semantic control structures defining local semantic constraints and grounding contexts. Across the MITRE D3FEND ontology and eight Wikidata- derived domains, we show that inconsistencies are structured rather than random, concentrating in localized hotspot subgraphs organized around recurring TREE, STAR, and CYCLE patterns that remain stable across models and domains. We further show that selective graph grounding improves correctness and cross-model consistency, while indiscriminate grounding introduces regressions. A layered grounding strategy achieves the strongest monotonicity profile, preserving correct knowledge while reducing inconsistency. Finally, we show that hotspot structures discovered from simple consistency probes transfer to more realistic compositional reasoning tasks.
We present the framework of TACS-RF - a Tool-driven Agentic Circuit Synthesis of RF and mmWave modules. In this framework, a large-language-model (LLM) coding agent (Claude Opus 4.8) directly drives industry-standard electronic-design-automation (EDA) tools such as Cadence Virtuoso/Spectre, Calibre, Cadence EMX, and Ansys HFSS to design RF and mmWave modules. We validate the framework through the agentic design of a 240-251 GHz sub-THz transmitter in a 90 nm SiGe BiCMOS process. The agent semi-autonomously designed the sub-blocks including a 60 GHz push-push Colpitts VCO with second-harmonic extraction, multistage differential cascode power drivers, a push-push frequency doubler, a differential bowtie antenna, and all the interstage matching networks. The transmitter chain with parasitic-extracted devices and EM-verified passives delivers +5.1 to +6.3 dBm across an 11 GHz varactor-only tuning range, phase noise of -80 to -88 dBc/Hz at 1 MHz offset while consuming a DC power of 361 mW. We describe the agent-driven design flow and the resulting division of labor between human and agent, taking a step toward a "text-to-ASIC" future for designing RF/mmWave hardware.
Language agents carry information from past experience into future tasks whose demands may be unknown or change over time. We develop a decision-theoretic account of the capability available in history, retained in storage and realized through use, together with the costs of recovery and revision. Drawing on comparison of statistical experiments, information acquisition and the value of computation, we express these values in units of avoided task loss. Recovery and revision define attainable risk-cost profiles and preservation across uses. A cost-aware simulation condition and five minimal counterexamples establish how information timing, access, computation, feedback and demand shape these comparisons; a pointer with zero answer mutual information can reduce the cost of exact recovery. Allocation and recovery criteria identify when gains pay for estimation, selection and evidence access. Complete-split studies on LoCoMo, LongMemEval-S and PersonaMem cover 3,075 questions and two readers. They show complementary value from saved state and recovered evidence, task-dependent performance orderings, and the role of reuse in amortizing construction costs. Multi-project workflows connect correction to preservation and validation costs. Together, the theory and studies support decisions about what to retain, which recovery options to preserve, and how to adapt memory as evidence and objectives evolve.
Scientific discovery requires more than generating hypotheses: ideas must be grounded in prior work, translated into executable methods, experimentally validated, challenged by counterevidence, and communicated through reproducible findings. Despite recent advances in autonomous research agents, closing this entire loop remains challenging in rapidly evolving computer-vision fields with complex training pipelines and expensive evaluations. We introduce SplatLab, an autonomous scientific discovery system for 3D Gaussian Splatting (3DGS) that integrates literature understanding, hypothesis generation, implementation, experimental refinement, falsification, and manuscript writing into a unified research pipeline. Given a research prompt, a target-paper URL, or no input at all, SplatLab identifies research opportunities, proposes novel methods, trains and ablates candidates across Mip-NeRF 360 and LLFF, and produces manuscripts grounded in verifiable experimental evidence. Unlike prior systems, SplatLab performs discovery over verified baseline implementations using domain-aligned modification scaffolds. A cascade-weighted Elo tournament evolves candidate methods using measured GPU performance and verbal-gradient feedback, while a standing falsifier incorporates adversarial stress testing directly into selection. An integrity audit binds reported claims to logged experiments, and reviewer-driven feedback can initiate further experimentation rather than merely revising text. SplatLab discovers methods achieving PSNR improvements of +0.18 to +3.78 dB over matched baselines, including +3.78 dB on astrophotographic nebula rendering, a previously unexplored setting for 3DGS. By closing the loop between scientific reasoning, executable experimentation, and evidence-backed communication, SplatLab compresses months of researcher effort into days of mostly autonomous compute.
Parameter configurations control presolving, cut generation and branching strategies in mixed-integer programming (MIP) solvers, directly affecting solving efficiency. Effective configurations vary across instances, while searching for them online requires additional solver runs. We propose Nominate-then-Adjudicate: an empirical performance model (EPM) shortlists candidates from a fixed portfolio, and one large language model (LLM) call selects using static features, compressed formulation text and memory distilled from offline solver measurements. Text exposes distinctions omitted by the chosen aggregate features; selection requires no online candidate solves or foundation-model weight updates. Across sixteen synthetic families, adjudication improves on the EPM's top-ranked candidate (top-1), raising mean normalized performance score from 0.377 to 0.426 and the win rate against SCIP's default from 84.9% to 90.2%; all ten sequential batches show positive mean-score gains. On 400 Ecole instances, it outperforms the per-instance baseline ISAC+ in mean runtime-based score, with gains concentrated in facility location. Total solver time falls by 69.6% versus default, excluding LLM latency. Ablations support text and memory; a second LLM improves over top-1.
Few-shot image classification (FSIC) frequently suffers from visual ambiguity, where background clutter and RGB appearance similarities hinder discriminative feature matching in data-scarce settings. To mitigate this, we propose DAFIC, a geometry-guided framework that incorporates monocular depth into representation learning, episodic adaptation, and dense support-query matching. DAFIC first learns geometry-aware token representations through RGB-D self-supervised pre-training. Subsequently, the Depth-guided Geometric Adaptation (DGA) module uses depth-derived geometry to refine patch representations with geometry-enriched class context while suppressing background interference. Spatial Bidirectional Patch Matching (SBiM) then performs bidirectional dense matching on the refined features, reducing sensitivity to spurious correspondences and background clutter. Extensive experiments on four benchmarks show that DAFIC achieves strong performance against existing methods, with ablation and robustness analyses supporting the effectiveness of coupling geometry-conditioned episodic adaptation with bidirectional matching for few-shot visual recognition.
Social media sentiment is increasingly used to predict stock returns. Its reliability depends on the composition of the crowd generating the feed. For foreign firms, the home-market investors who know them best are underrepresented on English-language Twitter. Hence, their feed should carry a less precise signal. Reduced-form analysis of firm-level Twitter sentiment shows that sentiment noise predicts next-quarter losses less consistently for foreign stocks than for domestic stocks. The loss-on-noise slope is negative in 78 percent of quarters for domestic stocks but in only 48 percent for foreign stocks, with a significant mean difference in slopes. We interpret this difference through a noisy rational expectations model in which the feed carries a public signal produced by three types of contributors. Specialists post repeatedly with information about the firm, attention-driven contributors post once with information about the firm and a transient fad, and automated accounts post repeatedly with no information about the firm. The share of each contributor type and the size of the fad determine the precision of the signal, which, in turn, determines how much of the feed's noise reaches prices. The model gives repeat-author share, fad and precision from the vendor's aggregate metrics, without account-level data, whereas prior work backs out precision from price informativeness. The structural estimates show that feeds for foreign stocks have a higher share of repeat authors, a larger fad component and a less precise signal. Thus, the foreign signal did not disappear but got diluted.
Electrocardiography (ECG) is a cornerstone of cardiac diagnosis, yet most machine learning methods for ECG analysis lack interpretability, limiting their clinical adoption. We present IECG, a weakly-supervised ECG foundation model that jointly performs diagnostic classification and abnormality localization without requiring manual abnormal region annotations, overcoming a long-standing bottleneck in interpretable ECG learning. Central to IECG is a weakly-supervised attention strategy that explicitly incorporates clinical priors by deriving abnormality heatmap pseudo-labels from established ECG clinical knowledge. These pseudo-labels guide the model's CLS-token attention through a KL-divergence loss, encouraging it to focus on diagnostically relevant waveform regions. During pretraining, IECG is jointly optimized with clinically guided attention supervision, ECG-text contrastive alignment, and report captioning objectives, enabling it to learn rich multimodal representations while producing localized waveform evidence. By explicitly aggregating features from clinically guided attention regions, IECG grounds its diagnostic predictions in interpretable waveform evidence without sacrificing classification performance. Extensive experiments demonstrate that IECG achieves state-of-the-art abnormal region localization while maintaining strong classification performance, advancing trustworthy foundation models for ECG analysis.
Human-centric audio-visual editing requires precise alignment of lip movements, gestures, and expressions with speech. Existing methods process inputs through independent video and audio pipelines, preventing cross-modal interaction between visual editing and audio dubbing. Many of these pipelines further rely on mask-based inpainting. As a result, they suffer from poor lip-audio synchronization, cumulative pipeline errors, and an inherent mask-size dilemma. We present AVE, the first unified end-to-end framework that jointly performs reference-guided person swapping, insertion, and deletion across both audio and video modalities without requiring spatial masks. To overcome data scarcity, we design a synthesis pipeline and introduce AVE-Dataset, the first audio-visual editing dataset to provide 100K pairs with appearance and voice references. By combining Synthetic-to-Real reconstruction with preliminary audio warm-up, our framework transcends synthetic pipeline limits and mitigates audio-video token imbalance. AVE outperforms modality-separate audio-visual editing pipelines in editing realism, temporal consistency, and audio-visual alignment.
We measure LLM probability updates on $\delta$-SNLI premise-hypothesis pairs across the Multi-Candidate Verbalization (MCV) family. Separate calls elicit priors and posteriors; directional movement s signs changes by the annotated direction. We cross stated vs. reported wording with Direct single estimates (D0) vs. Multi-Candidate Weighted elicitation (MCW; five weighted estimates, V0, weighted mean M_W). Frozen formal tests cover 15 configurations (23,400 planned units): 3 primary (Qwen3-8B thinking off, OLMo-2-7B, gpt-6.1-sol via codex; 6,600), 4 CLI-harnessed configurations (gpt-oss-120b, claude-sonnet-5.5, gemini-3.8-flash low/high; dnli-agy; 5,600), and 8 un-harnessed REST API configurations (dnli-api; 11,200). We add a 20-configuration, 8-provider dev ladder (3B-550B; 6,000 units) and a 2-model OpenAI 1+1+4 ablation of D0, Direct-CoT (D_CoT), MCW (V0), and Multi-Candidate Unweighted (MCU; V2 / M_U; 1,800 calls). All 15 reject H1 (s = +16.1 to +28.9 points) and H4a (endpoint reduction +0.065 to +0.391); 13 reject H2 (+2.0 to +8.9 points), except gpt-oss-120b (+0.9) and sf:qwen3.5-4b (-0.64). In 14 of 15 formal configurations, readouts obey Top-1 > MCW (M_W) > MCU (M_U). On 120 common pairs, API Qwen3 tracks local Qwen3 (H1 +18.72 vs. +18.90; H4a +0.265 vs. +0.254; H2 +3.78 vs. +1.67; H4b -9.03 vs. -6.70); local H2 rejects on all 240 pairs (+1.97), not this subset. API Gemma 31B (formal H4b -2.85, Top-1 +0.64; spread -13.3% / +7.6%) and Groq gpt-oss-120b (dev -4.15, +0.40; -18.4% / +12.2%) show small MCW costs and stated narrowing/reported widening without CLI harnesses. In OpenAI ablations, D_CoT keeps numeric-token entropy <1 bit; MCU (V2) shows smaller movement loss but halves spread and $\Delta H_2$ vs. MCW (V0). Because $\delta$-NLI annotates only direction, we make no claim about appropriate update magnitude. Code/data: https://github.com/asj252/llm-judgment-studies
Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluation benchmarks. Existing general-purpose benchmarks (e.g., MMLU and HELM) primarily assess broad knowledge and reasoning capabilities, but fail to capture critical domain requirements such as exercise safety, physiological appropriateness, personalization, and actionable coaching quality. This gap is particularly concerning in fitness and health applications, where incorrect or unsafe recommendations can lead to physical harm. To address this limitation, we introduce MoveBench, the first comprehensive benchmarking framework specifically designed for evaluating LLMs in sports and health coaching. The proposed benchmark integrates heterogeneous task formats, including multiple-choice questions (MCQs) and open-ended question answering (OpenQA), grounded in real-world user scenarios and paired with structured rubrics emphasizing safety compliance, scientific validity, and training logic. Through large-scale evaluation of 15 diverse LLMs on 809 questions with 5,012 rubric-level criteria, our results reveal substantial performance variability, particularly in safety awareness, structured program design, and personalization capability, highlighting a critical gap between knowing and doing. Our work establishes a foundational evaluation standard for sports and health LLM applications and provides a reproducible framework for advancing safe, reliable, and context-aware AI-driven coaching systems. Open resources are available at https://github.com/SatoSakula/MoveBench.
In multimodal learning, modality imbalance often lets one modality dominate optimization and keeps the model from fully exploiting cross-modal interactions. Balance-oriented methods such as the Multimodal Competition Regularizer (MCR) perform well by alleviating this imbalance during training. These dynamic balancing methods, however, mainly adjust modality contributions and do not consider how imbalance affects the formation of synergistic information during fusion. Synergy is a major source of multimodal advantage, because it is predictive gain that cannot be recovered from unimodal evidence alone. We propose the Multimodal Synergistic Competition Regularizer (MSCR), a fusion method that jointly promotes balanced modality utilization and the discovery of synergistic information. MSCR has two complementary objectives. An anti-dominance objective suppresses excessive unimodal influence and leaves room for synergistic information, and a synergy objective encourages the fused predictor to outperform a non-synergistic unimodal reference. An adaptive gate further concentrates the regularization on samples that need stronger collaborative modeling. Experiments on five benchmarks show that MSCR consistently improves performance over MCR and strengthens synergistic capability. It raises conditional recovery, the accuracy of the fused prediction on samples that the unimodal predictors misclassify, as well as the share of the model's output that InterSHAP attributes to cross-modal interactions. Its gain in conditional recovery persists when the fusion module is Transformer-based. Code is available at https://github.com/chenxinyu991-collab/MSCR.
Fetal brain biometry provides a quantitative basis for assessing prenatal growth and identifying congenital brain abnormalities. However, comprehensive assessment remains limited by labor-intensive manual measurements and automated models that lose accuracy across imaging sequences and institutions. We introduce BioTTA, an anatomically guided test-time adaptation framework that measures 11 fetal brain biometrics from reconstructed three-dimensional magnetic resonance images. BioTTA adapts pretrained models to individual unlabeled volumes using geometric consistency and atlas priors, without access to source images. In a retrospective study across five centers in China and Switzerland, BioTTA improved measurement accuracy across three out-of-distribution datasets and two network architectures. It reduced mean absolute measurement errors by 46-82% relative to the corresponding models without adaptation, achieving errors similar to those of supervised fine-tuning. Its measurements were mapped onto normative growth trajectories derived from expert annotations, enabling gestational-age-specific assessment through a web-based reporting platform. Across four disease cohorts, the platform achieved 82.1-95.0% accuracy in binary detection of ventriculomegaly or cerebellar abnormalities, with performance similar to that of a senior radiologist. BioTTA provides a practical foundation for standardized fetal brain biometry across heterogeneous imaging settings, supporting scalable prenatal growth assessment and quantitative evaluation of brain abnormalities.
Current scaling law formulations suggest that increasing the number of unique samples in a dataset consistently improves model performance, while repeated exposure to the same samples provides diminishing value. In this work, we challenge this assumption for image self-distillation models. We train iBOT models on random subsets of seven datasets spanning satellite imagery, driving scenes, egocentric video, and natural images, and evaluate their frozen representations on downstream tasks. We propose a density-interaction scaling law that combines unique-image count $U$ and repetition $R$, fitting it on runs with at most 50 million image presentations and testing it at larger budgets $C$. On Maxar dataset, a random subset containing approximately 1.5% of the training pool improves average nearest-neighbor classification accuracy by 3.11 percentage points over training on the full pool at the same budget of 200 million image presentations. Smaller subsets also outperform the full pool on SATLAS and Ego4D, whereas ImageNet favors larger pools at higher budgets. At a fixed subset size, further training can improve performance, lead to a plateau, or reduce performance. Our law captures smaller-subset advantages that the compared baselines cannot represent and improves prediction at higher budgets on Maxar, SATLAS, and Ego4D under nearest-neighbor evaluation. These findings show that both the number of unique images and how often they are repeated matter when allocating a training budget.
Vision Transformers achieve strong performance but incur high computational costs from quadratic token interactions. Training-free token reduction methods improve efficiency, but their robustness remains underexplored. We propose Prune-and Merge ViT, a training-free framework for off-the-shelf models. It combines class attention-based pruning with similarity-based merging to reduce redundancy while preserving semantic information. To evaluate robustness we introduce two metrics. Relative Accuracy Drop (RAD) measures relative accuracy degradation under transformations, and Prediction Flip Rate (PFR) quantifies prediction consistency. On pretrained ViT and DeiT, Prune-and-Merge reduces computation competitively while maintaining robustness and better accuracy than existing token reduction methods. Our analysis suggests that hybrid token reduction does not introduce hallucination-like behavior and preserves prediction stability for common image transformations.
Recovering high-quality images from degraded underwater observations is crucial for underwater exploration. Polarization observations show promise as an effective source of complementary physical cues for recovering target radiance under clear-water conditions. However, existing methods have yet to jointly model raw intensity information and polarization cues to enable image restoration driven by an understanding of mixed underwater degradations. To overcome these limitations, we propose DORIS, a unified multimodal language-driven framework that jointly uses polarization and RGB information to generate textual descriptions of degradation types and severity levels through structured semantic instructions and enhances joint restoration representations under the guidance of degradation-aware semantic features to improve restoration robustness under mixed degradations. We further construct a new benchmark named MixPolar, which contains underwater images exhibiting real degradations and the corresponding annotations. It supports systematic evaluation of degradation perception, image restoration, and downstream task performance. Extensive experiments demonstrate that our method effectively integrates polarization and RGB information, achieving competitive performance in degradation perception and image restoration.
Tacit knowing, we argue, is an operating regime of one memory substrate, not a separate kind of content. In VaCoAl, an algebro-deterministic hyperdimensional memory over $\mathrm{GF}(2)$ realized as CASRAM and PyVaCoAl, one DAG of bound records is read in two ways. With every collision repaired (Rescue), the trace is exactly auditable but no path outranks another; with collisions tolerated (Don't Care), a path-integrated confidence $\mathrm{CR}_2$ ranks direct over circuitous routes without being stated. This audit-valuation complementarity formalizes Polanyi's claim that tacit and explicit knowledge are not sharply divided. (1) Polanyi's from-to structure reads as non-commutative binding. (2) Full explication destroys the valuation (Lemma 1), as with Polanyi's pianist; tacitness is thus contingent or regime-bound, placing Polanyi, Nonaka, Tsoukas and Collins on one substrate. (3) The same lemma answers a second dualism: the popular dual-process moral ("train slow, deliberate System 2 to tame fast, intuitive System 1") mirrors the two-store reading of tacit and explicit knowledge Polanyi rejected. Mercier and Sperber's reply, that reasoning is intuitive inference about reasons, matches Polanyi's; in the substrate, complete supervision is full rescue, which erases the valuation it should discipline. (4) Collins's three tacit knowledges map to bound structure, substrate valuation and value binding. (5) Our mentor-student DAG charts tacit transmission. (6) AI-solved problems with few follow-ups (Tao) are rootless explicit knowledge, re-rooted when LLMs generate, VaCoAl keeps the trace and the community values. (7) On Mercier and Sperber's theory, an LLM is a sophist: justification cut from tacit roots and evaluation. Truth-seeking lies in collective tacit knowing, Polanyi's conviviality, which we conjecture underlies evolvability and extends beyond humans. Testable predictions follow.
Spiking neural networks target energy-efficient language modeling through sparse, binary activations, but the efficiency-accuracy tradeoff of spiking language models is uncharacterized at scale. We present the first Chinchilla-style IsoFLOP scaling study of a spiking language model, sweeping SpikeGPT-family models (RWKV backbone) from width 384 to 1536 across compute budgets from $3\times10^{17}$ to $10^{19}$ FLOPs on FineWeb-EDU. We report two findings. First, the compute-optimal frontier is $N_{opt} \propto C^{0.56}$, close to the 0.50 that Hoffmann et al. report for dense Transformers, so spiking does not change how parameters and data should be traded off under a compute budget. Second, against non-spiking RWKV and Transformer baselines trained the same way, the loss gap splits into a backbone cost of about 0.16 nats that does not change with compute and a spiking cost that falls steadily with compute, from 0.34 to 0.23 nats over our range. These results give the first compute-optimal recipe for spiking language models and quantify the accuracy cost of their sparsity.