arXiv:2607.06772v4 Announce Type: replace
Abstract: Learned optimization aims to improve upon hand-designed optimizers (e.g., Adam and Muon) by meta-learning small neural network optimizers over a distribution of tasks. While recent work has greatly advanced the architectural design and inductive biases of learned optimizers (LOs), their meta-training remains biased toward short-unroll learning on particular tasks, resulting in redundant computation and leaving LOs often unable to compete with hand-designed optimizers. We introduce Efficient Long-hOrizon (ELO) learning, an efficient meta-training algorithm that (1) reallocates wasted meta-training compute to longer failure regimes, achieving efficient long-horizon learning, and (2) enforces decoupled progressive expert supervision, providing stable meta-learning signals that additionally improve the generalization of LOs. Our empirical study evaluates ELO for meta-training both element-wise and matrix-based LOs. Across downstream language modeling (GPT-2-124M/350M on FineWeb) and image classification (ViT-B/16, ResNet-50 on ImageNet-1K) tasks, ELO substantially improves the long-unroll performance and out-of-distribution generalization of the base LOs. In particular, ELO-Celo2 consistently outperforms well-tuned AdamW across all evaluated tasks, while remaining competitive with Muon on language modeling. \textit{Notably, all ELO baselines require less than 7 H100 GPU-hours for meta-training.}
Science Journals
arXiv:2607.06824v2 Announce Type: replace
Abstract: Physics-informed learning promises data-efficient and stable dynamics prediction, yet its strongest geometric guarantees have largely remained confined to closed conservative systems. This excludes robotic systems of interest, where actuation, dissipation, and constraints exchange energy and momentum with the environment. We introduce CaLiSym, a lightweight framework that extends symplectic learning to such systems by changing where the geometric prior is imposed. Rather than enforcing symplecticity on the measured state, CaLiSym embeds the state and its ports into a lifted phase space, where the dynamics evolve through a symplectic map. The lift is explicit and algebraic, requiring neither recurrent latent states, transformer decoders, implicit optimization, nor inference-time numerical integration. We instantiate the framework with SympNet predictors and introduce GRB-SympNet, a B-spline variant combining approximation with exact symplectic structure. Experiments on a controlled dissipative double pendulum, a real-world quadrotor, and a contact-constrained real-world quadruped demonstrate the lowest out-of-distribution autoregressive rollout error across systems, improving by up to 69.5% while using fewer parameters and up to 85x fewer floating-point operations per step than sequence-model baselines. The lifted dynamics preserve the symplectic form to numerical precision, extending symplectic learning beyond conservative mechanics toward real-world robotics.
arXiv:2607.07050v2 Announce Type: replace
Abstract: Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly. This makes multi-teacher on-policy distillation a natural training strategy: one teacher can specialize in tool calls, another in direct responses, and the student can learn from both on
its own generated distribution. We show that this strategy can induce a behavior shift that is invisible from aggregate losses alone. In a two-teacher tool-use setting, vanilla generalized knowledge distillation improves tool-call recall but also moves the model toward over-calling, where it calls tools
on examples that should be answered directly. Aggregate explanations are insufficient: tool-call samples do not receive more token exposure, and full-sequence per-token divergence is not larger for the tool-call teacher. We instead analyze behavior leverage imbalance: local token-level signals at mode-
entry and structural positions, such as <tool_call> and function names, can have disproportionate control over the global generation mode. We propose Soft Clamp, a per-token divergence calibration method that dynamically compresses extreme token-level Jensen-Shannon divergence while preserving nonzero
gradients. On APIGen-MT, Soft Clamp reduces over-calling from 13.7% to 9.0% relative to vanilla GKD while matching its decision accuracy. In a BFCL multi-turn diagnostic, it also lowers tool-call loops and repeated calls among GKD variants. These results suggest that multi-teacher OPD should monitor
where teacher signals act, not only how large they are in aggregate.
arXiv:2607.07420v2 Announce Type: replace
Abstract: Safety for generalist robots is usually discussed in terms of motion or dialogue. We argue a third question is missing: should the robot take its first hard-to-undo social action at all, such as a greeting, an uninvited grasp, or stepping into someone's space? We call this initiation authorization. Current frameworks rarely treat it as a separate safety layer. Today's stacks often skip this step: a high engagement score or a confident VLA rollout is treated as permission to act. But seeing a person is not the same as having their consent to be addressed. We frame initiation authorization within generalist-robot safety and contrast it with post-plan VLA guardrails, implementing PAS (probe-authorize-speak) on a doorway humanoid, comparing it with direct-init on logged traces, and proposing a three-condition user study, with open questions on metrics, governance, and where initiation ends and foundation-model generation begins.
arXiv:2607.07513v2 Announce Type: replace
Abstract: Self-supervised learning matches supervised accuracy from a fraction of the labels, but the labeled-sample efficiency behind this has lacked a theoretical explanation. We provide one. Data augmentation induces a similarity graph on the unlabeled data, so downstream learning on that graph is graph-Laplacian-regularized learning. We prove a fast transductive rate, $O(1/n_L)$ in the number of labels, in place of the supervised $O(1/\sqrt{n_L})$, by carrying the leave-one-out stability apparatus of Johnson and Zhang (JMLR 2007) over to the augmentation graph, and without the unrealistic assumptions of limit-based analyses (exact kernel, generalizing features). The bound makes augmentation quality explicit: the expected error is at most $C/n_L + R_{\mathrm{DA}}(y)$, where the data-augmentation alignment error $R_{\mathrm{DA}}(y)$ is proportional to the graph-cut mass of augmentations that cross a label boundary, so good augmentations let few labels suffice. The analysis uses a streamlined loss that drops the projector, negative-sample, and orthogonality overhead of standard objectives yet still recovers the top-$K$ ideal features in the infinite-data limit, the augmentation-kernel eigenspace studied by Zhai et al. The bound gives a mechanistic account of the accuracy-versus-label-count curve through augmentation quality, verified in a controlled model where the constants are known.
arXiv:2607.07836v3 Announce Type: replace
Abstract: We present Infinity-Parser2, a large multimodal model that couples a controllable data-synthesis pipeline with multi-task reinforcement learning for end-to-end document parsing, addressing the persistent scarcity of faithfully annotated parsing corpora. Our contributions are threefold. First, we build a scalable synthesis engine, pairing a controllable rendering framework with an iterative refinement loop, and use it to construct and open-source Infinity-Doc2-5M: a 5-million-sample bilingual (Chinese/English) corpus spanning diverse document types, annotated with element bounding boxes, canonical content forms (Markdown, HTML, LaTeX, SMILES, structured charts), and full-page reading order. Second, we introduce a verifiable, multi-task reward system that enables Joint Reinforcement Learning across eight co-trained objectives (document parsing, layout analysis, table parsing, math formula parsing, chart parsing, chemical formula parsing, document VQA, and general multimodal understanding), unifying perception, structure, and reasoning in a single optimization signal. Third, we release two variants under a shared architecture: Infinity-Parser2-Flash, optimized for low-latency inference with a 3.68x throughput gain over Infinity-Parser-7B, and Infinity-Parser2-Pro, engineered for precision-critical settings. Infinity-Parser2-Pro reaches state-of-the-art 87.6% on olmOCR-Bench and 74.3% on ParseBench, surpassing DeepSeek-OCR-2, PaddleOCR-VL-1.5, and MinerU2.5, with strong generalization to charts, chemical formulas, and document VQA.
arXiv:2607.08016v2 Announce Type: replace
Abstract: Video relighting requires balancing long-form temporal consistency with a physically grounded understanding of light transport, which depends on accurate estimation of intrinsic scene properties such as materials, geometry, and illumination. Existing methods follow two paradigms: (1) reconstruct a video's photometric properties via inverse rendering and relight them to a target illumination via forward rendering, using physically-based rendering (PBR) or a neural renderer; these suffer from noisy reconstructions and struggle with hard-to-model effects such as global illumination. (2) Frame the task as generative video-to-video translation conditioned on relighting targets (a target environment map or text); this limits relighting control and temporal stability, since diffusion models struggle to translate long-form videos, and is constrained by the availability of input/relit training pairs. We propose LightCrafter, a hybrid pipeline that reformulates video relighting as video translation of a proxy video: rather than translating the input video directly to the target, we translate a PBR rendering of the input under the target illumination to the final target. This bakes illumination targets into the PBR proxy, removing the need to teach the diffusion model illumination concepts like environment maps, and enables more intricate lighting control while naturally providing long-form temporal consistency. We show PBR renders alone already outperform some prior art but struggle with effects like global illumination; to capture these, we leverage photometric priors in video generation models by post-training CogVideoX on synthetic video pairs and real-world unpaired videos. We outperform prior state-of-the-art on existing real-world relighting benchmarks and contribute a synthetic benchmark for further analysis. We will release our dataset, benchmark, metrics, and code.
arXiv:2607.08801v2 Announce Type: replace
Abstract: Sharing databases and data streams imposes the danger of revealing private information in the form of complex events which can comprise individual data elements and their combinations. Identifying these privacy-revealing complex events is crucial for preserving privacy while maintaining data utility. However, data producers often lack the expertise to comprehensively identify these events, which undermines many state-of-the-art privacy-preserving mechanisms that rely on accurate event labeling. To address this challenge, we developed pArborist - a tool that can semi-automatically create a set of queries to identify and label privacy-revealing complex events in both static datasets and dynamic data streams, guided by the privacy requirements of the data producer. pArborist uses the schema of the database or data stream combined with initial input from the data producer, i.e., seed queries. From each seed query, pArborist grows a tree containing all possible syntactically correct queries, constrained by an upper limit on computational resources. Following this growing phase, the tree is refined by eliminating queries that lack correlation to the seed or are conditionally independent of the seed. Our evaluation indicates that pArborist achieves overall recall of 90% and precision of 93% in finding privacy-revealing queries, and this significantly surpasses the state-of-the-art approach FQID. In data stream processing experiments, pArborist introduces a delay of approximately 1.3 ms following an average warm-up period of 920 ms. The experiments also show that pArborist can automatically detect privacy-revealing complex events according to GDPR.
arXiv:2607.13563v1 Announce Type: new
Abstract: Generating high-quality triangle meshes is essential for film, gaming, and interactive 3D applications. Mainstream methods rely on mesh serialization and autoregressive processes, which stuggles in effective inference and is sensitive to error accumulation. In this paper, we present Nexus, a diffusion method that achieves holistic mesh generation via decoupled vertex and topology generation. First, we view mesh vertices as sparse voxels organized as an octree and adopt a diffusion model to generate the vertices in a coarse-to-fine manner. Second, for topology modeling, we propose Spacetime Interval, as an extension of Spacetime Distance to encode arbitrary edge and face topology into continuous per-vertex embeddings. It allows for a global and efficient recovery of complex topology. We then employ a diffusion model to generate the continuous embeddings on the generated vertices. Extensive experiments on the Objaverse and Toys4K datasets and in-the-wild images demonstrate that our method outperforms state-of-the-art autoregressive and two-stage baselines, effectively circumventing the inherent limitations of sequential mesh modeling. A blind user study from 3D practitioners confirms strong perceptual preference for our results.
arXiv:2604.09674v2 Announce Type: replace
Abstract: Do large language models (LLMs) think? Daniel Stoljar and Zhihe Vincent Zhang have recently developed an argument from rationality for the claim that LLMs do not think. We contend, however, that the argument from rationality not only falters, but leaves open an intriguing possibility: that LLMs engage only in arational, associative forms of thinking, and have purely associative minds. Our positive claim is that if LLMs think at all, they likely think precisely in this manner.
arXiv:2607.08842v2 Announce Type: replace
Abstract: Despite rapid AI adoption in education, rigorous evaluation of AI-powered educational (AIED) systems remains critically underdeveloped, particularly in second language (L2) education, one of the most common yet least evaluated AI applications. We introduce L2-Bench, an open-source benchmark of 1,000+ task-response pairs to aid the pedagogy-led evaluation of LLM capabilities relating to language learning and assessment. Crucially, L2-Bench measures model performativity on the application of learning experience design principles rather than mere knowledge of those principles or broad learning outcomes. Our contributions include: (1) a validated taxonomy of 12 competencies and 31 subcompetencies validated by 200+ expert practitioners (task authenticity: 4.42/5.00, criteria adequacy: 4.18/5.00); (2) a rubric-based evaluation methodology that we believe can, if adapted, generalize to similar (open-ended, qualitative) disciplines; (3) an evaluation dataset that produces reliable signal about model strengths, weaknesses, and contextual robustness across diverse L2 education scenarios. We find that, among large models, Claude Opus 4.7 performs best overall (85.5%), though is marginally outperformed on several constituent tasks. We also find that performance drops notably on harder tasks (69.9% to 73.4%). L2-Bench provides education stakeholders better methods to make more informed decisions about real-world AIED adoption, use, and governance, while advancing the maturing science of AI evaluations for education.
arXiv:2607.09776v2 Announce Type: replace
Abstract: When adapting Vision Language Action (VLA) models to downstream tasks, multiple rounds of post-training are often required to progressively address policy weaknesses. In this report, we focus on maximizing human efficiency during this iterative process, measured by policy improvement and task throughput per unit of human labor and time.
We propose HELP, a Human-Efficient Large-scale robot Post-training pipeline in which two specialized operators supervise twelve robots concurrently. A trained Teleoperator provides high-value remote interventions and recovery demonstrations, while a Floor Operator monitors the robot fleet, triggers takeovers, and performs physical resets. This role specialization improves human efficiency by reducing task switching, lowering operator training costs, and expanding robot interaction coverage. Beyond increasing rollout volume, concurrent supervision also broadens the range of policy behaviors observed by the human team, making recurring failure modes easier to identify and enabling more targeted takeovers, resets, and recovery demonstrations. To efficiently utilize the large and mixed-quality rollout data, HELP incorporates \vlac, an automatic rollout segmentation critic specifically designed for this setting. It separates autonomous trajectories into progress-making, idle, failure-inducing, and recovery segments. Useful rollout segments are retained and combined with Human-in-the-Loop data for the next post-training round.
Across four real-world manipulation tasks, HELP achieves 80\%--95\% success rates and improves task throughput by 1.7$\times$--4.2$\times$ over the base model. Under matched HITL recovery budgets, VLAC-CUT further amplifies throughput gains by 1.20$\times$--3.43$\times$ and success-rate gains by 1.50$\times$--3.00$\times$ over HITL-only updates.
arXiv:2607.13399v1 Announce Type: new
Abstract: On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood. We present a systematic study examining the role, pathologies, and regulations of OPD. We first clarify the role of OPD as an exploration catalyst: it steers the student toward correct reasoning paths via dense token-level guidance, without expanding capability ceiling. We confirm this by showing that prompt diversity matters more than per-problem sampling numbers, and critically, that the effectiveness of OPD hinges entirely on the quality of its guiding signal. This dependency exposes two pathologies that derail exploration. The Student-Teacher Mismatch occurs when a large teacher-student distributional gap causes the guiding signal to misalign with task correctness, steering exploration in counterproductive directions. Length Exploitation arises when the aggregated token-level objective creates length-dependent shortcuts, allowing the student to game the reward landscape through response truncation or redundant padding, exploring degenerate length modes rather than reasoning strategies. To tame these pathologies, we investigate lightweight signal regulations: advantage clipping and log-scale compression, ensuring exploration is guided by faithful signals. Experiments across seven benchmarks demonstrate that these regulations alleviate length exploitation and enable effective distillation, stably surpassing OPD variants and RLVR baselines, thereby confirming that well-regulated signal quality, rather than mere teacher scale, governs successful exploration in OPD.
arXiv:2607.13405v1 Announce Type: new
Abstract: LiDAR-inertial odometry (LIO) is a key component of autonomous navigation, but high-dynamic driving exposes two coupled challenges: intra-scan motion distortion and vibration-contaminated inertial measurements. Most real-time LiDAR-inertial pipelines propagate the system state by integrating raw IMU measurements and then use the propagated trajectory for point cloud de-distortion, thereby propagating inertial noise into both the corrected scan and the subsequent scan-to-map registration. This paper presents WNOJ-LIO, a LiDAR-IMU fusion framework based on a White-Noise-on-Jerk (WNOJ) Extended Kalman Filter (EKF). WNOJ-LIO employs a decoupled WNOJ prior on $\R^3 \times \SO(3)$ for state prediction and treats the IMU as a high-frequency measurement source rather than the driver of state propagation. The resulting posterior state history is then used for LiDAR scan de-distortion and subsequent point-to-plane LiDAR updates. The decoupled process model enables closed-form covariance propagation, thereby bridging the gap between batch WNOJ Gaussian process (GP) trajectory priors and recursive filtering.
Simulation results demonstrate improvements in acceleration and angular-velocity denoising, scan de-distortion, and localization accuracy over a FAST-LIO-style baseline.
Real-world experiments were conducted using an autonomous racing car on four driving segments with maximum speeds ranging from 53 to 208~km/h, covering a wide range of vehicle vibration levels. The experiments further validate the proposed method and provide a comprehensive evaluation of its performance in estimating acceleration, angular velocity, body-frame linear velocity, attitude, and position under highly dynamic driving. The source code of WNOJ-LIO is publicly available at https://github.com/LvJohny/wnoj-ekf-lio.git.
arXiv:2607.13410v1 Announce Type: new
Abstract: World model (WM)-based reinforcement learning enables sample-efficient end-to-end autonomous driving learning by imagining long-horizon trajectories in latent space. However, most driving WMs operate on bird's-eye-view (BEV) representations that are inherently egocentric: the transition between consecutive frames entangles the ego vehicle's own motion with scene dynamics. As a result, the WM devotes significant capacity to recovering ego-motion from warped observations, at the cost of scene modeling fidelity and imagination accuracy. This work proposes DynaDreamer, a dynamics-augmented Dreamer-style reinforcement learning method to address this problem by augmenting the WM with an explicit ego-dynamics prior. A physics-informed ego-dynamics encoder-decoder extracts the ego-state history into a compact and identifiable context, which modulates a causal Transformer WM to condition both its prior and posterior latents. During imagination, the ego-dynamics predictor propagates this context forward to keep the ego-dynamics prior synchronized with the rollout. An information-theoretic analysis shows that conditioning on this context reduces both the predictive entropy of the observation transition and the prior--posterior Kullback--Leibler divergence, confining the WM's modeling burden to the scene dynamics beyond ego-motion. An additional benefit is zero-shot cross-chassis adaptation: the ego-dynamics context depends on identifiable chassis parameters, so that a vehicle with previously unseen dynamic characteristics can adapt the WM to the new chassis without retraining. Experiments demonstrate that DynaDreamer improves task success rates over the strongest baseline by 28% and 61% in urban and highway driving scenarios, respectively, with the advantage rising to 73% when extrapolating to unseen chassis.
arXiv:2607.10261v2 Announce Type: replace
Abstract: This paper presents gradient-enhanced non-dominated sorting genetic algorithm II (G-NSGA-II) to address the challenges of local optima and solution non-uniqueness in the complex permittivity extraction problem for the first time. This adaptive hybrid algorithm integrates the global exploration capability of NSGA-II with gradient-based local refinement, triggered by a population-stagnation detection mechanism. Furthermore, multi-dimensional constraints are incorporated by jointly optimizing transmission and reflection coefficients across multiple sample thicknesses. Experimental validation conducted on six typical polymers in the 20--40 GHz band demonstrates that the retrieved relative permittivity and thicknesses are in high agreement with literature values and physical measurements. Compared to standard heuristic and gradient-based algorithms, the proposed G-NSGA-II reduces the number of generations required for convergence by approximately 50\%. This significant improvement in speed, combined with enhanced robustness, provides a highly reliable and efficient solution for broadband dielectric characterization in architectural and electromagnetic engineering. The simple measurement method and the proposed efficient algorithm allow for a rapid evalutaion of wireless performance within indoor environments. This approach serves as a valuable tool for optimizing existing wireless layouts and improving network performance.
arXiv:2607.10293v2 Announce Type: replace
Abstract: The robustness of approximate Riemann solutions has been a crucial topic in computational magnetohydrodynamics, from both theoretical and practical perspectives. Recently, the widely used HLLD approximate Riemann solution was revised, becoming significantly more robust under strong magnetic fields. Yet, simplifications were needed as the compressible slow magnetoacoustic mode is not included in the HLLD scheme, and as a result non-physical density distribution has been found when having strong slow shocks. In this note, a simple fix is introduced for the estimated intermediate internal energy, providing robust results in several representative test cases, preserving pressure-positivity when the magnetic field is enhanced by a factor of 1000.
arXiv:2607.10443v2 Announce Type: replace
Abstract: Cloud Haskell brings Erlang-style distributed programming to Haskell, but its treatment of mobile code exposes a difficult boundary in the source-level API. Remote processes must be expressed as static closures, messages must satisfy serialisation constraints, and participating nodes are assumed to share the relevant code.
This paper explores a different design point. We present CloudMicroHaskell, a Cloud Haskell-style library built on MicroHaskell, whose runtime represents both code and data as a combinator graph. When a process or message crosses a node boundary, CloudMicroHaskell serialises the reachable graph directly. As a result, remote spawning can be written in direct style: process bodies may capture variables from their surrounding scope, and messages may contain ordinary values, including functions, without programmer-written closure conversion.
We describe the implementation of the CloudMicroHaskell node runtime, including remote spawn, message delivery, monitors, exit propagation, and library implementations of generic servers and supervisors. We evaluate the system with process/message benchmarks, a distributed work-pool benchmark, a file-synchronisation case study, and a heterogeneous deployment on microcontrollers. The results show that runtime graph serialisation makes the \ch{} programming model substantially more direct, while also making the tradeoff explicit: some guarantees enforced by \ch{}'s source-level types become dynamic checks, and programmers must be aware of laziness and runtime-owned resources when moving graphs between nodes.
arXiv:2607.13428v1 Announce Type: new
Abstract: Positive-Unlabeled (PU) learning aims to achieve high-accuracy binary classification with limited labeled positive examples and numerous unlabeled ones. Existing cost-sensitive-based methods often rely on strong assumptions that examples with an observed positive label were selected entirely at random. In fact, the uneven distribution of labels is prevalent in real-world PU problems, indicating that most actual positive and unlabeled data are subject to selection bias. Building on the SAR-PU propensity-weighted framework of Bekker et al., we study a PU learning enhancement (PUe) framework using normalized propensity scores and normalized inverse probability weighting (NIPW). PUe's main contributions are a normalized inverse-probability-weighted PU risk formulation; additional theoretical analyses of normalized sample-weight error and common PU estimators under biased labeling; regularized deep propensity-score estimation; integration with modern cost-sensitive PU methods; and support for selectively labeled negative classes. Experiments on MNIST, CIFAR-10, and ADNI demonstrate improvements over several PU baselines under non-uniform label distributions.
arXiv:2607.10541v3 Announce Type: replace
Abstract: Sequential recommender systems typically infer user preferences through single-pass encoding of interaction histories without iterative refinement, relying on increasingly deep architectures to capture complex patterns. In this work, we revisit sequential recommendation from a recursive inference perspective: can user preferences be modeled as a persistent latent state that is recursively refined? We propose RecRec (Recursive Recommendation), a lightweight model that maintains a compact latent state and updates it through a shared recursive module conditioned on interaction evidence. Unlike prior recursive models, RecRec introduces an evidence-anchored correction mechanism that stabilizes refinement by grounding each update in the original interaction context, preventing semantic drift during deep recursive reasoning. Experiments on three benchmark datasets under standard evaluation protocols show that RecRec matches or outperforms state-of-the-art sequential, graph-based, and reasoning-enhanced recommenders while using only 3.9M to 14M parameters. Ablation studies demonstrate that both recursive refinement and the evidence-anchored correction gate contribute significantly to performance, highlighting the effectiveness of recursive latent inference as a scalable alternative to deeper or language-based architectures. Code is available at https://anonymous.4open.science/r/RecRec-6B67/README.md.
arXiv:2607.10611v2 Announce Type: replace
Abstract: Training with quantized weights can reduce costs but often results in degraded accuracy, especially when optimization is carried out in low precision, without storing high-precision copies. We identify a key failure mode: under low precision, standard optimizers can get stuck and not make progress, especially at large weight magnitudes due to coarse mantissa resolution. To overcome this, multiplicative updates have been previously proposed, in place of additive updates in standard optimizers. While successful under extremely low precision, such as under the logarithmic number system, they suffer from failures near zero and across sign changes. The failure modes of additive and multiplicative updates are therefore complementary. To exploit this, we propose M+Adam, which combines both update types: additive steps handle sign changes and small magnitudes, while multiplicative steps ensure progress at large magnitudes when additive updates are zeroed out under rounding. We prove monotone descent for M+Adam under standard smoothness assumptions. Across LLaMA-style pretraining with 60M-1B models, 1x-8x Chinchilla budgets, and using only BF16, FP8, and FP4 master weights, M+Adam consistently improves low-precision training.
arXiv:2607.10653v3 Announce Type: replace
Abstract: Frequency-domain analysis based on converter output admittance is a key tool for studying converter-driven stability in power grids. This paper presents a Python-based identification tool built on a completely open-source simulator, eliminating the need for commercial licenses such as MATLAB or PSCAD and improving configurability through an MIT-licensed stack. The identification method uses steady-state signal injection with a sinusoidal sweep, deriving frequency-domain admittance from time-domain simulations. Analytical output-admittance models are developed for both grid-forming (disturbance-observer-based) and grid-following (phase-locked-loop-based) control to verify the numerical results. The tool's results are compared against a commercial PSCAD-based alternative, demonstrating accurate admittance identification across control methods. Code and examples are available online to support reproducibility.
arXiv:2607.10852v3 Announce Type: replace
Abstract: The electrical conductivity $\sigma$ of the plasma filament left behind by an ultrashort pulsed laser (USPL) optical pulse after it is geometrically then self-focused in air via the Kerr effect is measured by attenuation of a 3.2 GHz TE$_{10}$ mode within an S-band waveguide through which the filament passes, taking into account the characteristic radius $R$ of the filament, as determined by fast camera visible light imaging. Models of the major air constituents' ionization rate $W_{i}$ vs. local laser intensity $I$, and of temperature $T$ and mean axial electron momentum $\left\langle p_{{z}}\right\rangle $ vs. peak laser intensity $I_{0}$ are then used to infer a hypothetical steady state filament's $I_{0}$, $T$, major species particle densities, and assumed axially invariant current time integral $Q$ and current decay rate $\nu$ after pulse passage. $Q$ is independently measured via the filament's self-emission signal in the waveguide for comparison. The theoretical far field microwave radiation pattern due to the actual axial variation in $Q=Q\left( z\right)$ is compared favorably to published measurements. A much lower upper bound on $\nu$ is inferred once such radiation is taken into account. Results are presented along a $30$ cm long filament at a broad range of atmospheric pressures.
arXiv:2607.10936v2 Announce Type: replace
Abstract: We study the bandit-feedback version of online principal component analysis (Bandit PCA): in each round $t = 1,\dots,T$, the adversary selects a $d \times d$ symmetric gain matrix $G_t$ with spectrum in $[0,1]$ and rank at most $r$; the learner simultaneously selects a unit vector $w_t \in S^{d-1}$ and receives the reward $w_t^\top G_t w_t$. The learner receives no other feedback, and aims to minimize the regret against the best unit vector in hindsight. This problem was introduced by Kotlowski and Neu (2019), who gave an algorithm with regret $O(d\sqrt{rT \log T})$ and showed the lower bound of $\Omega(r\sqrt{T/\log T})$. We improve upon both of these bounds and essentially bridge the gap between them, establishing the minimax regret of order $r\sqrt{dT}$ up to polylogarithmic factors in $d$ and $T$. The upper bound is attained by a novel algorithm, which combines online mirror descent on the spectrahedron of (real) density matrices with a multiscale exploration scheme in which the eigenspaces with different spectral magnitudes are updated at different rates. For the lower bound, we construct an adaptive adversary that refines a hidden large-reward subspace based on the learner's actions, in such a way that low regret is impossible without estimating the subspace; as a result, lower-bounding the regret reduces to studying the arising subspace estimation problem. Finally, we discuss connections of Bandit PCA with adaptive-measurement quantum tomography.
arXiv:2607.10949v2 Announce Type: replace
Abstract: Turning movement counts are essential for intersection-level traffic management, yet their collection remains predominantly manual due to the cost of per-camera region annotation. This paper presents an unsupervised pipeline that identifies entry and exit regions directly from raw vehicle trajectories extracted via object detection and multi-object tracking, requiring no manual annotation, camera calibration, or prior knowledge of intersection geometry. Unlike trajectory clustering methods that classify individual trajectories using pairwise similarity and must be re-executed on every new batch, the proposed pipeline clusters initial and terminal point locations to produce persistent spatial region polygons that classify future trajectories by point-in-polygon containment at linear cost. The pipeline comprises six sequential steps, five of which introduce configurable parameters evaluated through a systematic statistical analysis spanning 17,100 pipeline executions across 9 surveillance cameras capturing dense heterogeneous traffic in Bengaluru, India, and 10 sequences from the UA-DETRAC benchmark dataset. Both parametric and nonparametric testing frameworks identify three consistently significant parameters and yield an empirically grounded recommended configuration. Under this configuration, the pipeline achieves a median classification error of 3.4% across all 25 Bengaluru cameras, including 16 held-out locations, with a median per-turning-movement GEH of 2.43. Compared with two trajectory clustering baselines, the proposed pipeline exhibits greater stability across camera views and lower computational cost, at the expense of higher median error. Extended evaluation demonstrates that calibration clips of at least 60 minutes and peak-traffic selection further improve region estimation quality.