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.

01.
arXiv (quant-ph) 2026-06-24

Quantum-enhanced estimation of stimulated Raman optical activity

arXiv:2606.23722v1 Announce Type: new Abstract: In recent times there has been growing interest in Raman optical activity (ROA) for its label free detection of absolute configuration, conformation, and stereochemical structure in chiral biosamples and drug molecules. Since ROA signals are generally small, techniques such as stimulation by a probe beam can be used to enhance the signal strength. However, with a classical probe, the measurement precision is still fundamentally limited by its shot noise. To solve this problem we propose the use of two-mode squeezed vacuum and show that it can achieve sub-shot noise limited measurement sensitivity. Using quantum estimation theory, we derived the quantum Fisher information and the quantum Cramér-Rao bound (QCRB) for stimulated ROA measurement to quantify the precision enhancement. This improvement comes from photon-number correlations which suppress the intensity fluctuation common to both modes. We further show that balanced detection of the output intensity difference is a practical measurement scheme that approaches the QCRB and becomes optimal in the small-chirality limit. This opens a promising path toward more sensitive Raman chiroptical spectroscopy of weak and photosensitive samples.

02.
arXiv (quant-ph) 2026-06-11

Fabricating fiber cavity mirror substrates compatible with high coupling efficiency

arXiv:2606.12168v1 Announce Type: cross Abstract: Fiber optical cavities offer small mode volumes and correspondingly strong light-matter interactions in an open Fabry-Perot geometry. However, existing fabrication techniques do not reliably produce substrates with surface profiles amenable to high mode matching between the cavity mode and fiber core, thereby limiting the achievable collection efficiency. Here we present a technique to fabricate fiber mirror substrates while using $in situ$ reflectometry to constrain the achievable mode matching prior to coating. By measuring the back-reflection from freshly cleaved fiber tips, we pre-select 138 fibers compatible with 96.5-99.5% mode matching, and after a single CO$_2$ laser ablation pulse, these fibers remained compatible with 95.3-99.2\%. This simple technique provides rapid feedback during each stage of substrate fabrication, greatly enhancing the yield of viable fiber mirror substrates prior to (expensive) coating runs.

03.
arXiv (CS.LG) 2026-06-18

The Illusion of Improvement: Reject Inference Strategies in Credit Scoring

arXiv:2606.18479v1 Announce Type: new Abstract: Reject inference methods are widely used to mitigate survival bias in credit scoring, yet their effectiveness remains poorly understood. We systematically evaluate several such methods and uncover a structural failure mode: in a natural retraining cycle, models whose accuracy improves while recall collapses create an illusion of improvement that leads practitioners to believe the system is getting better when, in fact, its rejection quality – the ability to correctly screen out defaulters – is deteriorating. We then propose a controlled exploration strategy that breaks the feedback loop without statistical assumptions: the lender deliberately approves a fraction of rejected applicants and observes their true outcomes. We show that accuracy and rejection quality give opposite recommendations on whether to explore: accuracy favors no exploration, while rejection quality improves with it, confirming that standard evaluation metrics are misleading under selection bias. Even minimal exploration rates (2–5\%) prove sufficient in our experiments to diagnose the severity of the feedback loop at near-zero cost. Our findings are consistent across two machine learning methods and three real-world datasets, and suggest that standard evaluation protocols are inadequate for assessing models trained under survival bias.

04.
medRxiv (Medicine) 2026-06-22

Virtual Responsive Neurostimulation Implantation: From Intracranial Connectivity to Optimized Lead Placement

Responsive neurostimulation (RNS) is an implanted device that delivers direct brain stimulation for drug-resistant focal epilepsy. Individual responses are highly variable, and no validated framework exists to predict outcome or guide lead placement before implantation. We hypothesized that this variability is partly explained by lead placement in relation to patterns of functional connectivity in brain networks. Fourty-nine patients with drug-resistant focal epilepsy who underwent pre-implantation intracranial EEG (iEEG) and RNS implantation across three independent epilepsy centers were retrospectively studied. We developed a composite functional connectivity score, based on simple Spearman correlation, combining the standard deviation and kurtosis of interictal iEEG connectivity distributions to predict the response outcome in a training cohort (HUP, n=18) and validated in two independent cohorts (NYU, n=17; UCSF, n=14). We accounted for a spatial mismatch between iEEG and RNS electrodes with a distance-based correction. The score was extended to generate patient-specific 3D maps of predicted RNS efficacy across 200 simulated, or virtual RNS, lead configurations. Accuracy of the score in predicting clinical outcome was 72% at the group level, 61% at the individual patient level, and, after distance-based optimization, 100% in patients with RNS electrodes placed close to location of iEEG electrodes. Applied to the validation cohort, the same score reached 68% accuracy (71% balanced accuracy, 55% sensitivity, 88% specificity). The spatial combination of the scores at different SEEG contacts localization gives a spatial score for each patient. Responders showed significantly higher spatial scores than non-responders, supporting that actual RNS lead placement in responders was located in map-identified favorable regions. Interictal iEEG functional connectivity predicts individual RNS response across independent epilepsy centers, and patient-specific 3D maps derived from this biomarker could prospectively guide lead implantation toward favorable network regions, opening a promising avenue toward network-informed RNS surgical planning.

05.
arXiv (CS.AI) 2026-06-16

RIDGECUT: Learning Graph Partitioning with Rings and Wedges

arXiv:2505.13986v4 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has shown promise for combinatorial optimization problems on graphs by learning heuristics that generalize across instances. However, effectively incorporating domain knowledge into RL frameworks for graph partitioning remains challenging, as existing approaches typically rely on unconstrained node-level actions that lead to large action spaces and inefficient exploration. In this paper, we propose RidgeCut, an RL framework that constrains the action space to enforce structure-aware partitioning in the Normalized Cut problem. Using transportation networks as a motivating example, we introduce a novel concept that leverages domain knowledge about urban road topology – where natural partitions often take the form of concentric rings and radial wedges. By transforming the graph into linear or circular representations, our method enables the use of transformer-based policies and efficient learning via Proximal Policy Optimization. The resulting partitions from RidgeCut are not only aligned with expected spatial layouts but also achieve lower normalized cuts compared to existing methods. Experimental results on synthetic and real-world traffic graphs demonstrate that RidgeCut consistently outperforms existing methods while exhibiting strong inductive generalization across graph sizes. Although motivated by road networks, RidgeCut provides a general mechanism for embedding structural priors into RL frameworks for graph partitioning.

07.
arXiv (CS.CV) 2026-06-12

Iterative Visual Thinking: Teaching Vision-Language Models Spatial Self-Correction through Visual Feedback

Vision-language models (VLMs) achieve strong singleshot spatial grounding, yet lack any mechanism to observe and correct their own predictions. We find that naively prompting a VLM to iterate over rendered visualizations of its predictions causes catastrophic failure: Acc@0.5 on referring expression comprehension collapses from 79.6% to 48.7% (a 31 percentage point drop), revealing a fundamental gap between grounding capability and self-correction ability. We propose Iterative Visual Thinking (IVT), a closed-loop framework in which the model predicts a bounding box, observes the prediction rendered on the image, and iteratively refines through visual feedback. A two-phase training recipe closes the self-correction gap: first, we exploit the base model's own predictions as realistic errors and prompt a teacher VLM to generate corrective reasoning traces, yielding supervised data without human annotation; second, we apply Group Relative Policy Optimization (GRPO) with a simple IoU reward to stabilize multi-step refinement. On a mixed benchmark spanning RefCOCOg, Ref-Adv, and Ref-L4 (505 test samples), SFT warm-up with IVT surpasses the single-shot base model on every metric: Acc@0.5 rises to 82.0% (+2.4pp), Acc@0.7 to 74.1% (+3.2pp), and Acc@0.9 to 48.3% (+2.8pp). GRPO further reduces per-step IoU degradation by 5x, stabilizing the refinement trajectory. All training uses only 2,400 samples on a single GPU, demonstrating that spatial self-correction is a learnable capability that can be instilled at modest scale.

08.
arXiv (CS.CL) 2026-06-19

Med-R2: Perception and Reflection-driven Complex Reasoning for Medical Report Generation

Automated medical report generation (MRG) is increasingly used to reduce the burden of manual reporting and for decision support. Large vision-language models (LVLMs) hold great promise for automated MRG due to their fine-grained image-text alignment and advanced text-generation capabilities. Currently, state-of-the-art MRGs primarily focus on adapting pre-trained LVLMs with direct supervised fine-tuning (SFT), a fine-tuning strategy with medical image-report pairs. However, several factors limit the performance of these LVLMs. Firstly, direct SFT enables LVLMs to generate medical reports directly without an intermediate thinking process of pathological feature perception and diagnostic reasoning. This causes a potential failure to perceive pathological features and thus leads to misdiagnosis. Secondly, direct SFT lacks the incorporation of radiology-specific knowledge guidance, causing LVLMs to misinterpret perceived pathological features and make incorrect diagnoses. To address these gaps, we propose a novel fine-tuning strategy named Med-R2. We introduce a perception-driven long reasoning process that precedes report generation and incorporates radiology-specific knowledge as guidance. Additionally, to alleviate potential perceptual errors in complex reasoning, a reflection mechanism is introduced to refine the perception of pathological features and the generated report. Our experiments demonstrate that Med-R2 effectively enhances the capability of pathological features perception and diagnosis accuracy for MRG via fine-tuned LVLMs.

09.
arXiv (CS.CV) 2026-06-19

Fast Human Attention Prediction for Fixation-guided Active Perception in Autonomous Navigation

Human visual attention relies on structured scanpaths to efficiently process scenes, yet instilling this behavior into robot autonomy is in its infancy and hindered by the high,computational costs of existing predictive models. To address this, we introduce GazeLNN, a computationally lightweight,scanpath prediction model that leverages Liquid Neural Networks as its recurrent engine and employs MobileNetV3 for feature extraction. Operating auto-regressively, the architecture predicts sequential fixation heatmaps conditioned on the current visual stimulus and fixation history. Despite requiring only 0.61 GFLOPs, GazeLNN achieves state-of-the-art performance on the MIT Low Resolution dataset achieving 0.47 ScanMatch score. It outperforms existing recurrent baselines across diverse evaluation metrics, while reducing computational costs by 99.40% and accelerating inference by up to six times. To investigate the role of human attention modeling in robot autonomy and demonstrate the practical utility of this highly efficient architecture, we integrate GazeLNN into an active camera-robot control policy trained via Reinforcement Learning. This integration enables human-fixation-guided perception during autonomous navigation, validated through successful real-world deployments on an aerial robot.

10.
arXiv (CS.LG) 2026-06-16

Quantization Robustness of Monotone Operator Equilibrium Networks

arXiv:2603.10562v2 Announce Type: replace-cross Abstract: Monotone operator equilibrium networks are implicit-layer models whose output is the unique equilibrium of a monotone operator, guaranteeing existence, uniqueness, and convergence. When deployed on low-precision hardware, weights are quantized, potentially destroying these guarantees. We analyze weight quantization as a spectral perturbation of the underlying monotone inclusion. Convergence of the quantized solver is guaranteed whenever the spectral-norm weight perturbation is smaller than the monotonicity margin; the displacement between quantized and full-precision equilibria is bounded in terms of the perturbation size and margin; and a condition number characterizing the ratio of the operator norm to the margin links quantization precision to forward error. MNIST experiments confirm a phase transition at the predicted threshold: three- and four-bit post-training quantization diverge, while five-bit and above converge. The backward-pass guarantee enables quantization-aware training, which recovers provable convergence at four bits.

11.
arXiv (CS.CL) 2026-06-17

Regression Language Models for Code

We study code-to-metric regression: predicting numeric outcomes of code executions, a challenging task due to the open-ended nature of programming languages. While prior methods have resorted to heavy and domain-specific feature engineering, we show that a single unified Regression Language Model (RLM) using a frozen LLM encoder can simultaneously predict directly from text, (i) the memory footprint of code across multiple high-level languages such as Python and C++, (ii) the latency of Triton GPU kernels, and (iii) the accuracy and speed of trained neural networks represented in ONNX. In particular, a relatively small 300M parameter RLM based on T5Gemma, obtains >0.9 Spearman-rank on competitive programming submissions from APPS, and a single unified model achieves >0.5 average Spearman-rank across 24 different programming languages from CodeNet. Furthermore, the RLM can obtain the highest average Kendall-Tau of 0.46 on five classic NAS design spaces previously dominated by graph neural networks, and simultaneously predict architecture latencies on numerous hardware platforms.

12.
arXiv (CS.AI) 2026-06-19

The Hidden Evolution of Disguised Visual Context inside the VLM

arXiv:2606.20077v1 Announce Type: cross Abstract: Visual tokens enter Large Language Models (LLMs) as raw, foreign signals. How they are transformed into meaningful representations and interact with the language space depends entirely on the integration architecture. Whether by treating visual tokens as in-context prompts within the input sequence or injecting them directly into the LLM's intermediate layers. A controlled comparison and understanding of how these architectural choices affect visual information and its internal transformation to integrate with the LLM remains underexplored. We provide a fair comparison by evaluating in-context and layer-wise injection VLM integration paradigms under identical training conditions across single image, multi-image, and video benchmarks. In doing so, we uncover a hidden evolution where visual tokens enter the LLM as disguised visual context, raw representations lacking linguistic structure, but are progressively reshaped depending on the integration paradigm, each capturing fundamentally different frequency characteristics of the visual signal. We show that this evolution inside the LLM determines what visual features the VLM can utilize effectively, how visual representations align with the language space, and ultimately how each paradigm performs across different tasks. We further demonstrate that attention allocation alone is insufficient, and that performance is driven by the quality of visual representations at each layer.

13.
arXiv (math.PR) 2026-06-25

An RDT based approach to large deviations of Wishart and Wigner matrices spectral edges

arXiv:2606.25501v1 Announce Type: new Abstract: We present a novel methodology for studying large deviations principles (LDPs) of random matrices. By utilizing a partially lifted variant of random duality theory (RDT), we develop a generic LDP framework that completely circumvents traditional random matrix theory (RMT) methods. To demonstrate the framework's simplicity and accuracy, we apply it to the Wishart and Wigner GOE classical statistical ensembles. In both cases, we obtain elegant LDP characterizations of the upper and lower spectral edges that fully match the results achieved through traditional Coulomb gas methodologies in [85,95].

14.
arXiv (quant-ph) 2026-06-11

Q-DICE: Quantum Distributed Interconnect Compiler and Emulator

arXiv:2606.11340v1 Announce Type: new Abstract: As distributed quantum computing (DQC) offers a leading path towards scalable quantum computation, the ability to benchmark distributed algorithms under realistic conditions becomes critical for system co-design. However, without access to physical systems, researchers lack tools to evaluate distribution protocols. We introduce Q-DICE (Quantum Distributed Interconnect Compiler and Emulator), a hardware-aware emulation environment for benchmarking distributed quantum circuits on classical simulators and on NISQ-era monolithic hardware. This work provides three core contributions: (1) a programmatic scheme to construct distributed QPU backends, utilizing two novel techniques - QPU slicing and stitching - to facilitate distributed circuit mapping, (2) a methodology for modeling nonlocal link noise using physically motivated Kraus operators and stochastic error channels, and (3) a boundary-aware circuit mapping algorithm enforcing distributed QPU topology constraints during transpilation. Together, these components constitute a distribution-aware compiler and noise-modeling engine that faithfully enforces the physical limitations of distributed quantum hardware within existing execution environments. We validate Q-DICE against a multitude of experimentally demonstrated quantum circuits, including a distributed Grover's search on optically linked trapped-ion hardware, achieving a worst-case fidelity deviation of 4% between simulated and experimental results. These findings demonstrate Q-DICE's capacity to accurately reproduce real distributed quantum system behavior across platforms, streamlining experimentation with distributed quantum algorithms and architectures.

15.
arXiv (CS.AI) 2026-06-18

UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning

arXiv:2606.19328v1 Announce Type: cross Abstract: Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing the need for explicit reward design. However, existing methods typically rely on passive data collection and suffer from poor sample efficiency, especially during the early stages of learning. We introduce a model-based approach that actively directs exploration by jointly reasoning over uncertainties in the reward, dynamics, and value functions. Our method, Uncertainty-Balanced Preference Planning (UBP2), uses ensembles of reward, dynamics, and value function models to evaluate candidate trajectories according to a unified score that combines expected reward, terminal value, and epistemic uncertainty. Planning under this objective yields an explicit tradeoff between exploitation and information acquisition without requiring ad hoc exploration heuristics. Under standard regularity assumptions, we establish sublinear regret guarantees for both finite-horizon and infinite-horizon settings. Empirically, experiments on the Meta-World benchmark show UBP2 achieves substantially higher sample efficiency than model-free preference-based methods and non-optimistic model-based baselines.

16.
arXiv (CS.LG) 2026-06-19

Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL

arXiv:2605.05481v2 Announce Type: replace Abstract: We revisit a classic "chicken-and-egg" problem in reinforcement learning: to safely improve a policy, the value function must be accurate on the state-visitation distribution of the updated policy. That distribution over states is unknown and cannot be sampled for the purposes of training the value function. Conservative updates solve this problem, but at the cost of shrinking the policy update. This paper explores an alternative solution, Approximate Next Policy Sampling (ANPS), which addresses the problem by modifying the training distribution rather than constraining the policy update. ANPS is satisfied if the distribution of the training data approximates that of the next policy. To demonstrate the feasibility and efficacy of ANPS, we introduce Stable Value Approximate Policy Iteration (SV-API). SV-API modifies the standard approximate policy iteration loop to hold the target policy fixed while an iteratively updated behavioral policy gathers relevant experience. It only commits to a new policy once a convergence criterion has been met. If certain stability criteria are met, the update is guaranteed to be safe; otherwise, it remains no less safe than standard approximate policy iteration. Applying SV-API to PPO yields Stable Value PPO (SV-PPO), which matches or improves performance on high-dimensional discrete (Atari) and continuous control benchmarks while executing substantially larger target policy updates. These results demonstrate the viability of ANPS as a new solution to this classic challenge in RL.

17.
arXiv (CS.LG) 2026-06-19

Reinforcement Twinning for Hybrid Control of Flapping-Wing Drones

arXiv:2505.18201v2 Announce Type: replace-cross Abstract: Controlling flapping-wing drones requires controllers that handle time-varying, nonlinear, underactuated dynamics from incomplete, noisy sensor data. Recent advances in artificial intelligence (AI), particularly reinforcement learning (RL), have opened new perspectives for addressing such complex control problems through data-driven policy optimization from interaction with the environment. Yet purely data-driven methods are sample-inefficient, demanding extensive, sometimes unsafe exploration, especially without guiding physical models. This motivates hybrid AI-physics frameworks. This article proposes a hybrid model-free/model-based flight-control approach using the reinforcement twinning algorithm. The model-based (MB) component uses an adjoint formulation and an adaptive digital twin continuously identified from live trajectories; the model-free (MF) component uses RL. The two agents share knowledge via transfer learning, imitation learning, and shared experience between the real environment and the digital twin, coordinated by a policy referee that selects which agent acts in reality based on digital-twin performance and a real-to-virtual consistency ratio. The framework is evaluated for the longitudinal control of a flapping-wing drone, modelled as a nonlinear time-varying system driven by quasi-steady aerodynamic forces. The hybrid strategy is tested under three adaptive-model initializations: (1) offline identification from existing data, (2) random initialization with fully online identification, and (3) offline pre-training with biased parameters followed by online adaptation. In all cases, the hybrid framework improves performance, robustness, and sample efficiency over purely model-free and purely model-based approaches.

19.
arXiv (CS.CV) 2026-06-11

Continual Learning with Support Boundary Experience Blending

Continual learning (CL) seeks to mitigate catastrophic forgetting when models are trained with sequential tasks. A common approach, experience replay (ER), stores past exemplars but only sparsely approximates the data distribution, yielding fragile and oversimplified decision boundaries. We address this limitation by introducing Support Boundary Data (SBD), generated via differential-privacy-inspired noise into latent features to create boundary-adjacent representations that implicitly regularize decision boundaries. Building on this idea, we propose Experience Blending (EB), a framework that jointly trains on exemplars and SBD through a dual-model aggregation strategy. EB has two components: (1) latent-space noise injection to generate support boundary data, and (2) end-to-end training that jointly leverages exemplars and SBD. Unlike standard experience replay, SBD enriches the feature space near decision boundaries, leading to more stable and robust continual learning. Extensive experiments on CIFAR-10, CIFAR-100, Tiny ImageNet, and ImageNet1K demonstrate consistent accuracy improvements of 10%, 6%, 13%, 2%, respectively.

20.
arXiv (CS.CL) 2026-06-24

Towards Spec Learning: Inference-Time Alignment from Preference Pairs

Steering a large language model (LLM) toward a desired behavior typically relies on an iterative process of hand-crafting a prompt based on a careful inspection of the model's responses. This is an involved, brittle, and error-prone process. Preference-based fine-tuning is a more rigorous but often prohibitively expensive solution. We propose spec learning, a framework that relies on a brief user instruction and a small set of preference judgments. These are compiled into specifications in the form of natural-language prompts for an LLM. Specifications condition LLMs at inference time, and no parameter updates to the underlying models are required. We show that the responses generated based on the compiled specifications often outperform direct preference optimization (DPO) on datasets from specialized domains whose preference signal is dense. Unlike opaque weight updates, the resulting specifications are human-readable and double as interpretable and transparent written embodiments of the preference signal that produced them.

21.
arXiv (CS.LG) 2026-06-24

Anticipating the Optimism Gap: Predicting Distribution-Shift Degradation of RF-Impairment Detectors from In-Distribution Statistics

arXiv:2606.22054v2 Announce Type: replace-cross Abstract: Detectors for GNSS radio-frequency impairments (jamming, spoofing, multipath) are usually reported with a single AUC measured on the distribution they were tuned on. That number falls once conditions move, and the size of the drop is rarely known in advance because labelled field data is scarce. We ask whether this optimism can be predicted before any out-of-distribution data is seen. On an open, parameter-grounded synthetic testbed with a tunable severity shift, we evaluate thirteen detectors (five physics baselines, full-feature logistic regression and multilayer perceptrons, and single-feature learned controls) across four impairment classes. The optimism gap, the difference between in-distribution and shifted AUC, grows monotonically as the shift deepens (mean Spearman correlation 0.50). It is driven by how many observables a detector uses rather than by whether it is learned, and it varies systematically by class. Centrally, a ridge model built only from in-distribution score statistics predicts the gap for a detector it has never seen (R^2 = 0.47) and for an impairment class it has never seen (R^2 = 0.46); both are significant against a 2000-fold permutation null (p < 0.001) and survive removing the feature that is, by construction, part of the target. The headline findings are synthetic. We then run the pre-registered protocol on three open field corpora: on Jammertest 2024 the cross-detector prediction holds (R^2 = 0.11, p = 0.009), and on SatGrid, whose spoofer power sweep gives a calibrated severity axis, in-distribution AUC overstates higher-severity AUC by up to 0.22 and to the point of sign inversion, with in-distribution AUC and realised gap perfectly rank-correlated (Spearman rho = 1.0). The mechanism survives contact with real data, at smaller magnitude than in simulation. We release the testbed, a software-receiver front end, the ingest adapters and the protocol.

22.
arXiv (math.PR) 2026-06-25

Pointwise Hurst Estimation via Scale Accumulation: A Noise-Robust Approach for Rough Volatility

arXiv:2606.25771v1 Announce Type: cross Abstract: We introduce an estimator for the pointwise, time-varying Hölder exponent (Hurst parameter) of a stochastic process, based on the geometry accumulation integral G_Lambda(t) = integral from Lambda to 1 of |eth_s X(t)| s^{-1} ds, where eth_s X(t) = (X(t+s)-X(t))/s is the scale derivative at resolution s. We prove consistency, noise robustness with explicit threshold Lambda* = sigma^{1/H}, and a CLT at rate (log Lambda)^{-1/2}. The estimator is pointwise in time, defined at finite resolution, and eliminates microstructure noise by scale separation. Existing estimators give a global H from integrated variance; this gives a time-varying H(t) directly from the price path.

23.
arXiv (CS.CV) 2026-06-16

EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video

Humans naturally understand object physics through everyday interactions, but faithfully predicting complex deformable dynamics, such as elastic materials and fabrics, remains a major challenge for computer vision and robotics. We present EgoPhys, a framework that constructs deformable physical digital twins from egocentric RGB-only video using generalizable priors. EgoPhys overcomes the limitations of existing methods to enable controllable deformable digital twin generation from egocentric videos by distilling per-object inverse-physics solutions into a compact codebook, enabling prediction of dense spring stiffness fields for unseen objects without per-spring test-time optimization. Trained with generalizable priors from diverse egocentric interactions, EgoPhys outperforms baselines in reconstruction, future prediction, and zero-shot generalization. To support training and evaluation, we curate an egocentric interaction dataset covering diverse deformable objects, scenes, and manipulation styles. We deploy EgoPhys on a real xArm6 robot, demonstrating that a digital twin initialized from a single egocentric human play video can serve as an internal world representation to aid in deformable-object planning, highlighting egocentric RGB observations as a scalable path toward real-to-sim pipelines.

24.
arXiv (CS.AI) 2026-06-12

Select and Improve: Understanding the Mechanics of Post-Training for Reasoning

arXiv:2606.13125v1 Announce Type: cross Abstract: Reinforcement learning has rapidly emerged as a key component in the training of reasoning and coding models, yet it remains poorly understood from a mechanistic perspective. We study how and through what underlying processes capabilities are acquired or enhanced via reinforcement learning post-training. Our analysis, based on controlled math reasoning experiments with Qwen-2.5-1.5B, reveals two core mechanisms: strategy selection and strategy improvement. Our results highlight the role of SFT data and reinforcement learning data in activating these mechanisms, in particular showing how supervising the model on diverse reasoning strategies can enable strategy selection and how increasing difficulty in reinforcement learning data can enable strategy improvement. Taken together, our results provide mechanistic insight into RL training and suggest practical interventions to continue scaling reasoning capabilities.

25.
arXiv (CS.LG) 2026-06-15

Muon$^p$: Muon with Fractional Spectral Powers

arXiv:2606.13867v1 Announce Type: new Abstract: Muon is an increasingly widely used optimizer that replaces a gradient $G=USV^\top$ with its polar factor $UV^\top$, thereby flattening the singular spectrum. However, full flattening discards singular-value information that may matter for adaptation. We introduce Muon$^p$, a Muon-style optimizer that instead uses fractional spectral-power updates $US^pV^\top$ for rational $p\in(0,1)$, interpolating between Muon and gradient descent. To make it practical, we prove that fractional spectral powers cannot be computed by any fixed univariate polynomial iteration, and furthermore derive low-degree odd bivariate recurrences that approximate $US^pV^\top$ using only matrix multiplications, preserving Muon's matrix-multiplication-only structure and compute complexity. We show that Muon$^p$ maximizes the linear improvement in loss under the Schatten $q$-norm for $q=1+\frac{1}{p}$. Empirically, Muon$^p$ is especially effective for finetuning: on billion-scale models, Muon$^p$ improves validation perplexity and downstream task performance. We further analyze when Muon$^p$ is less suitable, through the lens of spectral geometry. Our results reveal important insights on when preserving the singular spectrum can bring significant gains, and introduce a principled way to achieve them.