中 EN
Sign In Register

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Sign In Register
01.
arXiv (quant-ph) 2026-06-16

Bi-qutrit entangled edge states of positive partial transposes with largest ranks

Authors:
Kyung Hoon Han↗Seung-Hyeok Kye↗

arXiv:2606.16265v1 Announce Type: new Abstract: Whenever $E$ is an eight dimensional subspace of the bi-qutrit quantum system whose orthogonal complement is spanned by a vector of Schmidt rank three, we show that there exist PPT entangled edge states with the range space $E$ whose partial transposes are of rank six, which is the largest possible rank. In this way, we exhibit a huge family of bi-qutrit PPT entangled edge states of type $(8,6)$. They make faces of the convex set of all PPT states, and we find bi-qutrit PPT entangled edge states of other types on the boundaries of such faces.

Read & Discuss → View Source →
02.
arXiv (CS.AI) 2026-06-17

OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction

Authors:
Lujie Yang↗Xiaoyu Huang↗Zhen Wu↗Angjoo Kanazawa↗Pieter Abbeel↗Carmelo Sferrazza↗C. Karen Liu↗Rocky Duan↗Guanya Shi↗

arXiv:2509.26633v3 Announce Type: replace-cross Abstract: A dominant paradigm for teaching humanoid robots complex skills is to retarget human motions as kinematic references to train reinforcement learning (RL) policies. However, existing retargeting pipelines often struggle with the significant embodiment gap between humans and robots, producing physically implausible artifacts like foot-skating and penetration. More importantly, common retargeting methods neglect the rich human-object and human-environment interactions essential for expressive locomotion and loco-manipulation. To address this, we introduce OmniRetarget, an interaction-preserving data generation engine based on an interaction mesh that explicitly models and preserves the crucial spatial and contact relationships between an agent, the terrain, and manipulated objects. By minimizing the Laplacian deformation between the human and robot meshes while enforcing kinematic constraints, OmniRetarget generates kinematically feasible trajectories. Moreover, preserving task-relevant interactions enables efficient data augmentation, from a single demonstration to different robot embodiments, terrains, and object configurations. We comprehensively evaluate OmniRetarget by retargeting motions from OMOMO, LAFAN1, and our in-house MoCap datasets, generating over 8-hour trajectories that achieve better kinematic constraint satisfaction and contact preservation than widely used baselines. Such high-quality data enables proprioceptive RL policies to successfully execute long-horizon (up to 30 seconds) parkour and loco-manipulation skills on a Unitree G1 humanoid, trained with only 5 reward terms and simple domain randomization shared by all tasks, without any learning curriculum.

Read & Discuss → View Source →
03.
arXiv (CS.AI) 2026-06-15

Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories

Authors:
Dake Bu↗Wei Huang↗Andi Han↗Atsushi Nitanda↗Bo Xue↗Qingfu Zhang↗Hau-San Wong↗Taiji Suzuki↗

arXiv:2511.07368v3 Announce Type: replace-cross Abstract: Foundation models exhibit broad knowledge but limited task-specific reasoning, motivating post-training strategies such as RL with verifiable rewards (RLVR) and test-time scaling (TTS). While recent work highlights the role of exploration in improving pass@K, empirical evidence points to a paradox: RLVR and ORM/PRM typically reinforce existing paths rather than expanding the reasoning scope, raising the question of why exploration helps if no new patterns emerge. To reconcile this paradox, we adopt the perspective of Kim et al. (2025), viewing easy (e.g., simplifying a fraction) versus hard (e.g., discovering the some symmetry) reasoning steps as low versus high probability Markov transitions. In this tractable model, pretraining corresponds to tree-graph discovering, while post-training corresponds to CoT reweighting. We provably show that, both RLVR and ORM/PRM would favor heavily to several high-probability paths, and thereby forget rare-but-crucial CoTs. Building on this, we further prove that exploration strategies such as rejecting easy instances and KL regularization help preserve rare CoTs. Empirical simulations corroborate our theoretical results.

Read & Discuss → View Source →
04.
arXiv (CS.AI) 2026-06-19

cAPM: Continual AI-Assisted Pace-Mapping with Active Learning

Authors:
Dylan O'Hara↗Pradeep Bajracharya↗Casey Meisenzahl↗Karli Gillette↗Anton J. Prassl↗Gernot Plank↗Saman Nazarian↗Roderick Tung↗John L Sapp↗Linwei Wang↗

arXiv:2606.19373v1 Announce Type: cross Abstract: Ventricular tachycardia is a life-threatening rhythm disorder and a major cause of sudden cardiac death. Pace-mapping is a clinical procedure for identifying the intervention target during catheter ablation of VT. It requires clinicians to pace different sites in the ventricles and rapidly interpret the resulting electrocardiograms to determine where to pace next or whether a target site has been identified. Active learning AI models have been proposed to guide clinicians to the next pacing site, showing promise in reducing the number of pacing sites and improving the efficiency of pace-mapping. Existing methods require retraining each target without the ability to transfer knowledge across multiple VTs within the same patient or across patients. We introduce cAPM for continuous AI-assisted pace-mapping to capture and transfer knowledge accumulated from past pace-mapping data to reduce the number of pace-mapping data needed for future target VTs. This is made possible by a task-agnostic surrogate neural network that learns the mapping from pacing sites to 12-lead ECG morphology, an active-learning strategy that refines this surrogate model by selecting the most informative pacing site for each target, and a continual learning strategy to do so sequentially while retaining knowledge from prior targets. Evaluated on an in-silico testbed consisting of sequentially-presented localization tasks across different physiological conditions and ventricular geometries, cAPM with and without replay of past data samples achieved an 81% probability of localizing within clinical tolerance (5 mm accuracy) using 4.5 pace-mapping sites, compared to the state-of-the-art active-learning method achieving 38% probability using 13.7 pacing sites. These results provide a strong basis for preparing cAPM towards in-vivo preclinical and clinical studies where it can be used to guide pace-mapping.

Read & Discuss → View Source →
05.
arXiv (CS.LG) 2026-06-16

Towards Data-Efficient Cross-Device Generalization of Grad-Shafranov Equilibria via Transfer Learning Neural Operator

Authors:
Jay Phil Yoo↗William Howes↗Yashika Ghai↗Kazuma Kobayashi↗Souvik Chakraborty↗Syed Bahauddin Alam↗

arXiv:2606.15512v1 Announce Type: new Abstract: Real-time reconstruction of magnetohydrodynamic equilibria is essential for plasma shaping, stability assessment and feedback control in magnetic confinement fusion. However, Grad-Shafranov equilibrium calculations remain largely device-specific and iterative, limiting their use in latency-constrained control settings. Existing neural approaches can accelerate individual equilibrium predictions, but they do not generally provide reusable models across changing plasma boundaries or tokamak geometries. Here we show that equilibrium reconstruction can be recast as a cross-device operator learning problem. We develop a domain-specific neural operator framework that maps geometry and profile parameters directly to the poloidal flux field, replacing repeated solve-on-demand computation with amortized operator inference. Using the analytically tractable Solov'ev family as a controlled Grad-Shafranov testbed, we generate equilibria across eight geometrically distinct tokamak-like configurations and benchmark five neural operator architectures under four transfer-learning strategies. Single-geometry pretraining gives poor transfer to unseen devices, whereas multi-geometry pretraining enables data-efficient adaptation. The Wavelet Neural Operator gives the strongest cross-geometry performance, reaching mean relative L2 errors below 4% with 100 labelled target equilibria and below 2% with full fine-tuning. The predicted magnetic fields satisfy the divergence-free constraint to numerical precision, and four architectures achieve millisecond or sub-millisecond inference. These results identify neural operator pretraining as a route towards reusable, real-time equilibrium inference across fusion device configurations.

Read & Discuss → View Source →
06.
arXiv (CS.CV) 2026-06-18

Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication

Authors:
Wenqi Jia↗Zhewen Hu↗Ying Huang↗Yu Gong↗Stavros Kalafatis↗Yuke Wang↗Wei Niu↗Chengming Zhang↗Ang Li↗Sheng Di↗Yuede Ji↗Bo Fang↗…

3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated regions, causing global inconsistency, or rely on global Gaussian-level exchanges, which lead to substantial growth in inter-GPU communication and quickly dominate iteration time. We propose Splaxel, a communication-efficient distributed 3DGS training framework based on pixel-level local rendering and global composition. Instead of synchronizing Gaussians, each GPU renders its local subset and exchanges only partial pixel values, maintaining mathematical consistency while keeping communication cost stable as the scene size increases. Splaxel further reduces pixel-level redundancy through geometric and transmittance visibility prediction and improves GPU utilization via conflict-free camera-view consolidation. Evaluated on large-scale datasets with up to 120M Gaussians, Splaxel achieves up to 7.6$\times$ speedup over the state-of-the-art distributed 3DGS framework while preserving high reconstruction quality.

Read & Discuss → View Source →
07.
Nature (Science) 2026-06-15

Daily briefing: Iron-Age human bones were made into tools before interment

Authors:
Flora Graham↗

Newly uncovered bones hint at how Iron Age Britons treated their dead. Plus, AI models have failed to beat human mathematicians at research-level problems and the everyday items that make great scientific tools. Newly uncovered bones hint at how Iron Age Britons treated their dead. Plus, AI models have failed to beat human mathematicians at research-level problems and the everyday items that make great scientific tools.

Read & Discuss → View Source →
08.
arXiv (CS.LG) 2026-06-12

Adaptive Model-Predictive Control of a Soft Continuum Robot Using a Physics-Informed Neural Network Based on Cosserat Rod Theory

Authors:
Johann Licher↗Max Bartholdt↗Henrik Krauss↗Tim-Lukas Habich↗Thomas Seel↗Moritz Schappler↗

arXiv:2508.12681v3 Announce Type: replace-cross Abstract: Dynamic control of soft continuum robots (SCRs) holds great potential for expanding their applications, but remains a challenging problem due to the high computational demands of accurate dynamic models. While data-driven approaches like Koopman-operator-based methods have been proposed, they typically lack adaptability and cannot reconstruct the full robot shape, limiting their applicability. This work introduces a real-time-capable nonlinear model-predictive control (MPC) framework for SCRs based on a domain-decoupled physics-informed neural network (DD-PINN) with adaptable bending stiffness. The DD-PINN serves as a surrogate for the dynamic Cosserat rod model with a speed-up factor of up to 44,000. It is also used within an unscented Kalman filter for estimating the model states and bending compliance from end-effector position measurements. We implement a nonlinear evolutionary MPC running at 70 Hz on the GPU. In simulation, it demonstrates accurate tracking of dynamic trajectories and setpoint control with end-effector position errors below 3 mm (2.3\% of the actuator's length). In real-world experiments, the controller achieves similar accuracy and accelerations up to 3.55 m/s2.

Read & Discuss → View Source →
09.
arXiv (CS.AI) 2026-06-12

Geometric and Quantum Kernel Methods for Predicting Skeletal Muscle Outcomes in chronic obstructive pulmonary disease

Authors:
Azadeh Alavi↗Hamidreza Khalili↗Stanley H. Chan↗Fatemeh Kouchmeshki↗Muhammad Usman↗Ross Vlahos↗

arXiv:2601.00921v3 Announce Type: replace-cross Abstract: Chronic obstructive pulmonary disease (COPD) affects hundreds of millions of people worldwide, and skeletal-muscle dysfunction is clinically important. Quantum machine learning is increasingly explored for biomedical prediction, but its value in small biomarker cohorts requires benchmarking against strong classical baselines. We analysed a cigarette-smoke COPD cohort of 213 animals with blood and bronchoalveolar-lavage biomarkers to predict tibialis anterior muscle weight, muscle quality, and force. We developed a kernel-geometric quantum hybrid method in which synthetic symmetric positive definite (SPD) references are mapped through a reproducing kernel Hilbert space, compressed using train-only random projection, normalised, and supplied to low-dimensional quantum regression circuits. We benchmarked this approach against classical ridge/kernel models, SPD relational representations, and quantum-kernel regression (QKR). All methods were evaluated using condition-stratified repeated cross-validation. The largest numerical improvement was observed for muscle weight, where the proposed method had the numerically lowest mean root mean squared error (RMSE), approximately 1.8% below the best classical comparator; paired fold-level testing did not establish statistically significant superiority after Holm adjustment, but the endpoint is biologically meaningful. The method also had the numerically lowest mean RMSE for muscle quality. For force, biomarker-only Ridge performed best, suggesting a more linear endpoint structure.

Read & Discuss → View Source →
10.
arXiv (CS.AI) 2026-06-16

Learning in the Recurrent State: Gradient Descent with Linear Recurrent Networks

Authors:
Yudou Tian↗Neeraj Mohan Sushma↗Harshvardhan Mestha↗Nicolo Colombo↗David Kappel↗Anand Subramoney↗

arXiv:2410.11687v3 Announce Type: replace-cross Abstract: Linear recurrent networks (LRNNs) offer linear-time sequence modeling, but standard recurrent updates do not directly expose the supervised products needed for in-context gradient descent. We propose a sufficient constructive inductive bias for LRNNs: equip a diagonal recurrent state with multiplicative readout and a short sliding-window cross-product self-attention update. The resulting architecture, Gradient-based Recurrent In-context Learner (GRIL), can implement minibatch gradient descent on a task-specific linear predictor during a single forward pass. The same design extends to multi-step updates and cross-entropy classification, with a limited MLP-based extension to non-linear regression. Empirically, trained GRILs recover the behavior and parameters predicted by the construction on synthetic ICL tasks, and the same architectural bias yields useful performance on Long Range Arena and language modelling. These results present windowed cross-product self-attention as a practical, testable inductive bias for LRNNs that learn in context through gradient-descent-like updates.

Read & Discuss → View Source →
11.
arXiv (CS.LG) 2026-06-16

PromptShift-CRC: Drift-Aware Conformal Risk Control for Foundation Models Under Prompt and Domain Shift

Authors:
Jeffery Opoku↗David Banahene↗

arXiv:2606.15964v1 Announce Type: cross Abstract: Foundation models are now used in settings where the prompts they receive can change quickly. Users change, topics change, policies change, and the model may suddenly face a kind of request that was rare in the calibration data. This makes fixed calibration risky. Conformal prediction and conformal risk control give model-agnostic ways to control error, but they work best when the calibration data still look like the future data. This paper develops PromptShift CRC, a drift-aware conformal risk control method for foundation-model outputs under prompt and domain shift. The method embeds prompts and responses, measures how far the current prompt stream has moved from the calibration pool, gives more weight to relevant or recent calibration examples, and updates the risk level online after observed violations. It reports three practical diagnostics: realized risk error, prompt drift, and effective calibration size. We give conditions under which the method controls risk up to terms for distribution mismatch and weighted quantile uncertainty. In a synthetic prompt-shift benchmark, static conformal risk control fails sharply after drift, while PromptShift-CRC gives the best coverage among the adaptive baselines considered. We then evaluate the same calibration layer on public benchmark derived streams for question answering, toxicity, summarization factuality, and long-context hallucination risk

Read & Discuss → View Source →
12.
arXiv (CS.LG) 2026-06-19

3D-DLP: Self-Supervised 3D Object-Centric Scene Representation Learning

Authors:
Ellina Zhang↗Madhaven Iyengar↗Amir Zadeh↗Chuan Li↗Deepak Pathak↗David Held↗Tal Daniel↗

arXiv:2606.19451v1 Announce Type: new Abstract: We introduce 3D-DLP, a self-supervised object-centric representation learning model that decomposes scene-level RGB-D or voxel observations into a set of 3D latent particles. Building on the Deep Latent Particles (DLP) framework, each particle encodes disentangled attributes, including 3D keypoint position, bounding box dimensions, and appearance features, and represents a distinct entity in the scene. The model learns interpretable per-particle segmentation maps through an end-to-end self-supervised reconstruction objective. We demonstrate on both simulated and real-world datasets that the learned latent space is interpretable and controllable: by manipulating particle positions and decoding, we can generate novel scene configurations. Furthermore, we show that leveraging these compact 3D latent particles for downstream robotic manipulation improves performance over baselines that either lack explicit 3D information or rely on memory-intensive dense 3D inputs without object-centric structure. Code and videos are available at https://eubooks3003.github.io/3d-dlp.

Read & Discuss → View Source →
13.
arXiv (CS.AI) 2026-06-17

Statistical Foundations of LLM-based A/B Testing: A Surrogacy Framework for Human Causal Inference

Authors:
Joel Persson↗M{\aa}rten Schultzberg↗Sebastian Ankargren↗

arXiv:2606.17165v1 Announce Type: cross Abstract: Organizations and researchers show increasing interest in using large language models (LLMs) in place of human participants in A/B tests, in the hope of experimenting faster and at lower cost. We study when a treatment effect estimated on LLM outcomes recovers the effect that would have been measured on the human population of interest. Distributional equivalence between LLM and human outcomes would make any standard estimator valid but is unrealistic. We therefore develop a statistical framework that adapts surrogate endpoint theory to LLMs. The framework shows that calibrating LLM outcomes to human outcomes identifies the average treatment effect under surrogacy and comparability conditions that are jointly weaker than distributional equivalence. When these conditions fail, the effect of interest is only partially identified, and we provide diagnostics that can falsify surrogacy on historical experiments together with a bound on the worst-case bias from limited overlap. We further show that the stochasticity inherent to LLMs introduces both bias and variance, but using an average of multiple draws as the surrogate mitigates both. We illustrate the methods and theory in simulations and an application to A/B tests on Upworthy headlines. A central takeaway from our work is that the validity of LLM outcomes as surrogates can only be falsified for past treatments and never verified for new ones, so human experiments remain indispensable for novel interventions. We discuss the role of LLM choice, prompting, and temperature as design variables, and how to size human experiments for validation.

Read & Discuss → View Source →
14.
Nature (Science) 2026-06-17

Navigating a crowded developing brain leaves neurons with broken DNA

Authors:
Monica D. Manam↗

As neurons migrate to their final destinations in the forming brain, their DNA gets damaged. The brain has evolved a fix, but there can be lasting consequences if repair fails. As neurons migrate to their final destinations in the forming brain, their DNA gets damaged. The brain has evolved a fix, but there can be lasting consequences if repair fails.

Read & Discuss → View Source →
15.
arXiv (CS.CL) 2026-06-18

SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR

Authors:
Siddharth Aphale↗Kelly Liu↗

The standard heuristic of selecting the SFT checkpoint with the highest pass@1 for GRPO can fail when SFT compresses the rollout distribution. For binary rewards, the expected within group advantage variance is $p(1{-}p)(g{-}1)/g$; when early GRPO drives $p$ below $p^*(g)$, most groups have identical rewards and provide no group relative signal. We study SFT depth ladders for Qwen2.5-Coder-3B and DeepSeek-Coder-6.7B. We test Qwen2.5-Coder-3B across five depths and three seeds, and DeepSeek-Coder-6.7B across four matched depths and three seeds. On Qwen, pre RL pass@1 rises with SFT depth, but peak GRPO pass@10 falls from $0.806$ to $0.481$ (3 seed mean, $n{=}20$); pre RL entropy is positively associated with the GRPO outcome ($\rho{=}{+}0.69$). On DeepSeek, pass@1 remains far above $p^*(8){=}0.083$, and GRPO outcomes compress rather than invert. A two stage diagnostic, combining pre RL entropy triage with an early GRPO entropy monitor, flags high risk checkpoints and can stop failing runs early. Simple KL to reference regularisation and label smoothing variants do not rescue the collapsed Qwen checkpoint in our setting, suggesting the failure is not a trivial GRPO hyperparameter artefact.

Read & Discuss → View Source →
16.
arXiv (CS.CV) 2026-06-11

SG2Loc: Sequential Visual Localization on 3D Scene Graphs

Authors:
Nicole Damblon↗Olga Vysotska↗Federico Tombari↗Marc Pollefeys↗Daniel Barath↗

Visual localization in complex indoor environments remains a critical challenge for robotics and AR applications. Sequential localization, where pose estimates are refined over time, is important for autonomous agents. However, traditional methods often require storing extensive image databases or point clouds, leading to significant overhead. This paper introduces a novel, lightweight approach to sequential visual localization using 3D scene graphs. Our method represents the environment with a compact scene graph, where nodes represent objects (with coarse meshes) and edges encode spatial relationships. For each image in the localization phase, we extract per-patch semantic features, predicting object identities. Localization is performed within a particle filter framework. Each particle, representing a camera pose, projects the coarse object meshes from the scene graph into the image, assigning object identities to patches based on visibility. The similarity of the per-patch features, in the input image, and object features from the scene graph determines the weight of a particle. Subsequent images are incorporated sequentially, refining the pose estimate. By leveraging a compact scene graph and efficient semantic matching, our method significantly reduces storage while maintaining performance on real-world datasets. The code will be available at https://github.com/DmblnNicole/sg2loc.

Read & Discuss → View Source →
17.
Nature (Science) 2026-06-17

<i>CHPO</i> coordinates chilling recovery and nitrogen use in rice

Authors:
Jie Cao↗

Global rice production faces mounting challenges from abnormal temperature fluctuations and nitrogen-fertilizer-driven environmental pollution1–7. Developing varieties that balance chilling resilience and nitrogen-use efficiency (NUE) offers a promising solution, but the molecular networks coordinating these traits remain poorly understood. Here we identify CHILLING PHOENIX (CHPO), a major gene underlying the quantitative trait locus shared by both chilling tolerance and resilience. It encodes a MYB transcription factor that acts as a key regulator coordinating post-chilling recovery with nitrogen use in rice. Natural variation in a GCG-repeat-encoded polyalanine tract alters CHPO DNA-binding preference and redirects regulatory outputs between the japonica-type (CHPOjap) and indica-type (CHPOind), causing opposing effects on chilling tolerance and resilience. This allelic variation is shaped by domestication selection, with the CHPOjap allele probably derived from Chinese wild rice. CHPOjap directly targets OsTCP19 and OsNRT2.4 to fine-tune NUE, thereby enhancing chilling tolerance and resilience. These findings provide a mechanistic framework for a chilling-induced high-nitrogen-utilization module that alleviates the damage caused by chilling stress, and a potential molecular design&nbsp;strategy for breeding rice varieties with both chilling resilience and high NUE at the&nbsp;recovery stage. A rice gene, CHPO, links chilling resilience with nitrogen-use efficiency, revealing a domestication-shaped regulatory mechanism that could guide breeding of climate-resilient, sustainable rice varieties.

Read & Discuss → View Source →
18.
arXiv (CS.AI) 2026-06-16

The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution

Authors:
Deepak Panigrahy↗Aakash Tyagi↗

arXiv:2605.27599v2 Announce Type: replace-cross Abstract: Agentic AI workloads - where a single user goal triggers multi-step orchestration, tool calls, retries, and failure recovery - are being targeted for edge deployment, with NVIDIA, Dell, HP, ASUS, MSI, Acer, and Gigabyte all shipping GB10-based desktop AI systems in 2026. We recently demonstrated that orchestration structure dominates agentic energy cost, with workflows consuming 4.33x more energy per successful goal than linear baselines and OOI reaching 7.63x for multi-step reasoning tasks. Separately, Raj et al. show that CPU-side processing accounts for up to 90.6% of total latency and 44% of total dynamic energy in agentic workloads. We report a systematic energy-observability audit of the ASUS Ascent GX10 (GB10 SoC) and find that the platform exposes no CPU energy counter, no INA power-rail monitor, no IPMI/BMC, and no SCMI powercap protocol through any supported software interface. The only on-device energy telemetry is instantaneous GPU power via NVML. We further discover that the MediaTek firmware already computes per-rail energy internally via an undocumented ACPI interface (SPBM), but NVIDIA states there are "no plans to expose CPU rail information." On-device per-process energy attribution - as performed on x86 via RAPL - is therefore not reproducible on this platform through supported interfaces. We formalize a hardware requirements specification for energy-attributed AI, propose an interim calibration bridge for per-domain energy decomposition - confirmed on the Acer Veriton GN100 where CPU energy accumulators are live - and identify a standards-track path via SCMI powercap. Our findings motivate the low-carbon computing community to demand energy observability as a first-class hardware requirement.

Read & Discuss → View Source →
19.
arXiv (CS.CV) 2026-06-15

Temporal Backtracking Search for Test-time Generative Video Reasoning

Authors:
Sejoon Jun↗Zheng Ding↗Huangyuan Su↗Weirui Ye↗Yilun Du↗

While test-time scaling has revolutionized reasoning in large language models, generative video reasoning remains bottlenecked by a single-shot paradigm. We demonstrate that searching over denoising steps cannot rescue logically flawed rollouts because spatial trajectories commit early in the diffusion process. Root-level Best-of-N (BoN) sampling is similarly inefficient: reasoning errors cluster early in the temporal axis, and resampling blindly discards verified upstream progress. To unlock effective test-time scaling for video models, we introduce Temporal Backtracking Search (TBS), which shifts the search space to the temporal axis. TBS transforms video generation into an iterative generate-verify-restart loop via three core mechanisms: (1) variable-K conditioning to resume generation from arbitrary clean prefixes; (2) temporal process verification to localize failures and extract valid restart anchors; and (3) prefix-based search to reallocate compute toward extending correct trajectories rather than root resampling. Across algorithmic, navigation, and robotics domains, TBS Pareto-dominates matched-budget BoN. In a strict out-of-distribution setting where one-shot generation collapses (0.7% for BoN), TBS achieves 22.7%, with every solved episode stemming from a restarted branch. Ultimately, TBS reveals that the local reasoning competence of video models far exceeds what single-shot rollouts indicate, providing a scalable test-time framework to unlock it.

Read & Discuss → View Source →
20.
arXiv (CS.LG) 2026-06-16

Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning

Authors:
Dmitriy Bystrov↗Daniil Medyakov↗Dmitry Bylinkin↗Aleksandr Beznosikov↗

arXiv:2606.14970v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse downstream tasks and domain-specific data. A major obstacle in large-scale fine-tuning is the memory overhead of backpropagation, which requires storing activations, gradients, and optimizer states. Zeroth-order (ZO) optimization offers a memory-efficient alternative, but its performance is highly sensitive to the stepsize and smoothing parameter, often requiring costly task-specific tuning. Parameter-free (PF) optimization addresses this issue by adapting algorithmic parameters without prior knowledge of problem-dependent constants. Moreover, large-scale fine-tuning can benefit from geometry-aware updates that account for the heterogeneous structure of parameter blocks, which can be modeled through methods that exploit linear minimization oracle (LMO). In this work, we study PF adaptation for LMO-based ZO optimization and introduce $\texttt{AdaNAGED}$, a method that unifies gradient-free training, adaptive tuning, and non-Euclidean update geometry. We establish convergence guarantees and validate the method on large-scale LLM fine-tuning task with $\texttt{OPT}-1.3\mathrm{B}$ model.

Read & Discuss → View Source →
21.
arXiv (CS.AI) 2026-06-19

Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning

Authors:
Ismail Geles↗Leonard Bauersfeld↗Markus Wulfmeier↗Davide Scaramuzza↗

arXiv:2605.22748v2 Announce Type: replace-cross Abstract: Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain brittle in shared, dynamic real-world spaces. This failure stems from the dominant single-agent paradigm for physical applications, where other actors are ignored or treated as environmental noise, preventing effective coordination. Here we show that multi-agent reinforcement learning provides the essential safety scaffolding required for real-world interaction. Using high-speed quadrotor racing as a high-stakes testbed, we train agents to navigate complex aerodynamic interactions and strategic maneuvering with a variable number of racers. Through league-based self-play, agents evolve sophisticated anticipatory behaviors, including proactive collision avoidance, overtaking, and handling multi-agent physical interactions, including aerodynamic downwash. Our agents outperform a champion-level human pilot in multi-player races at speeds exceeding 22 m/s, while simultaneously reducing collision rates by 50 % compared to state-of-the-art single-agent baselines. Crucially, training with diverse artificial agents enables zero-shot generalization to safer human interaction. These results suggest that the path to robust robotic co-existence lies not in isolated safety constraints, but in the rigorous demands of multi-agent interaction. Multimedia materials are available at: https://rpg.ifi.uzh.ch/marl

Read & Discuss → View Source →
22.
arXiv (CS.AI) 2026-06-16

FOUNDv2: Learning Unified User Quantized Tokenizers for User Representation

Authors:
Chuan He↗Yang Chen↗Bin Dou↗Wuliang Huang↗Baokun Wang↗Yongchao Liu↗Xing Fu↗Yu Cheng↗Chuntao Hong↗Weiqiang Wang↗Zhongle Xie↗Jiajun Zheng↗…

arXiv:2508.00956v3 Announce Type: replace-cross Abstract: User representation learning serves as a fundamental pillar for personalized services on large-scale web platforms. Despite its importance, conventional continuous embedding methods face significant challenges, including the lack of a unified paradigm for multi-source data integration, prohibitive storage overhead due to low information density, and the lack of multi-scale modeling granularity. To overcome these limitations, we introduce FOUNDv2, a comprehensive user representation scheme centered on the Unified User Quantized Tokenizer U2QT) framework. FOUNDv2 transforms heterogeneous user data into a standardized discrete token space through a robust two-stage architecture. Specifically, the framework first extracts compact feature representations and subsequently employs a multi-view RQ-VAE to discretize them into storage-efficient tokens using shared and source-specific codebooks. To empower these representations with predictive intelligence, we further design multi-scale alignment objectives to capture both fine-grained behavioral dependencies and macro-temporal periodicity. Extensive experiments on various benchmarks demonstrate that FOUNDv2 consistently outperforms task-specific baselines while achieving substantial reductions in storage and computational costs. Finally, the large-scale deployment of FOUNDv2 on Alipay validates its practical scalability and efficiency across diverse industrial scenarios. The main code is available at: https://github.com/chuanhe1999/FOUNDv2.

Read & Discuss → View Source →
23.
arXiv (quant-ph) 2026-06-11

Optimizing Encoder Circuits of Entanglement-Assisted Quantum LDPC Codes via Beam Search

Authors:
Aditya Sodhani↗Pavan Kumar↗Shayan Srinivasa Garani↗Keshab K. Parhi↗

arXiv:2606.11468v1 Announce Type: new Abstract: Entanglement-assisted (EA) quantum QC-LDPC codes offer strong error-correction capabilities with structured parity-check matrices, but their practical use depends on efficient encoder circuits and the availability of pre-shared Bell pairs (ebits). In all encoder implementations based on the stabilizer formalism, the dominant contribution to this complexity comes from the use of controlled gates. In this paper, we adopt the Sharma-Kumar-Garani (SKG) encoder construction. We formulate the encoder optimization as a search over GF(2) row operations that decompose the binary matrix derived from its CNOT sub-sequence. We solve this problem using a beam search algorithm guided by a Hamming-distance heuristic. For the tested EA quantum QC-LDPC code families, the proposed method achieves CNOT-count reductions of 7.3-34.0% relative to the SKG baseline encoder. The optimized circuits also yield lower CNOT counts than Patel-Markov-Hayes synthesis on all tested instances and are verified by stabilizer-tableau simulation. These results show that substantial encoder simplification is possible for structured EA QC-LDPC codes.

Read & Discuss → View Source →
24.
arXiv (CS.CL) 2026-06-11

System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5

Authors:
Haotao Xie↗

Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry. However, domain-specific research on precise translation and affective-semantic understanding of classical poetry remains limited. The main challenge is that most studies treat the poetic appreciation task as a general-domain problem, neglecting the distinctive features of poetic appreciation, while high-quality and domain-specific datasets are extremely limited. To address this limitation, we decompose the task into three subtasks: term interpretation, semantic interpretation, and emotional inference. Based on multiple open-source datasets, we perform data cleansing and alignment to construct the Classical Chinese Poetry Instruction Pair Dataset (CCPoetry-49K), which comprises 49,404 high-quality instruction-response pairs explicitly optimized for this domain. We then propose a domain-specialized LLM, called PoetryQwen, by applying Low-Rank Adaptation (LoRA) to fine-tune the Qwen2.5-14B model. Experimental results on the CCL25-Eval Task 5 benchmark demonstrate that PoetryQwen achieves a score of 0.757, representing a 9.7% improvement over the Qwen2.5-14B-Instruct baseline (0.690). These findings clearly indicate that PoetryQwen significantly enhances performance in precise translation and emotional understanding of classical poetry. We present new dataset and methodological considerations intended to support the domain-specific optimization of LLMs.

Read & Discuss → View Source →
25.
arXiv (CS.CV) 2026-06-11

Frames2LoRA: Parametric Video Internalization for Vision-Language Models

Authors:
Manan Suri↗Sarvesh Baskar↗Dinesh Manocha↗

Processing video in vision-language models is expensive: each frame occupies hundreds of tokens, and inference cost scales with every frame and every repeated query. We introduce Frames2LoRA, a method for parametric video internalization. A perceiver hypernetwork reads the intermediate representations produced layer-by-layer as a frozen VLM encodes a video, and generates a Low-Rank Adaptation (LoRA) adapter in a single forward pass. Unlike standard LoRA fine-tuning, which requires iterative gradient updates, Frames2LoRA predicts these weights directly from the video. Trained for SmolVLM2 500M and 2.2B on video summarization and captioning, Frames2LoRA enables the same frozen VLM to answer queries from the adapter alone, with zero visual tokens in its context at query time. Frames2LoRA is statistically non-inferior and equivalent to direct video-in-context inference across all five captioning benchmarks at both model scales, and across seven of eight video question answering benchmark-scale pairings. Although trained only on 12 frames at 384px, it remains stable up to 1,024 frames and 1024px, where direct video-in-context inference often degenerates. Across this sweep, it reduces answer-time visual-token load by up to 1,500x and query TTFT by 6-80x, while preserving video-faithful outputs. We also find that independently generated adapters for non-overlapping video segments can compose in rank space, suggesting a path toward chunked long-video internalization.

Read & Discuss → View Source →