arXiv:2606.02753v1 Announce Type: new
Abstract: Video world models are a foundational generative technology for embodied AI and the Metaverse, yet existing approaches are inherently limited to a single agent observing from a single perspective. Extending these models to multi-agent settings introduces two critical challenges: data scarcity (coordinated multi-view recordings are prohibitively expensive to collect for general open-domain scenarios) and world state alignment (independently generated video streams cannot ensure that shared physical environments and events evolve consistently across views). To address these challenges, we propose MetaWorld, a novel framework that scales multi-agent video world models to open-domain environments directly from single-view videos. First, we introduce Monocular World-State Unrolling (MWSU) to explicitly decompose monocular footage into the camera operator's ego-motion and the visible subject's spatial trajectory. This camera-trajectory decomposition naturally extracts synchronized multi-agent motion data within a shared 3D space, completely bypassing the need for multi-camera setups. Second, for precise visual control, we develop the Subject-Aware World Generator to enable appearance-driven simulation conditioned on per-agent identity images. Finally, to ensure both views are grounded in the identical physical reality, we propose World-State Alignment, a per-frame inter-branch cross-attention mechanism inserted at every transformer layer of the video DiT. By jointly synchronizing the denoising process, WSA enforces both static geometric consistency and dynamic motion consistency, encouraging that the shared 3D environment and physical events remain well-aligned across both egocentric views. Extensive experiments demonstrate that MetaWorld achieves superior cross-view consistency and identity fidelity, establishing a highly scalable, physics-driven paradigm for multi-agent video world modeling.
Science Journals
arXiv:2601.23229v2 Announce Type: replace
Abstract: Markov decision processes (MDPs) are a fundamental model in sequential decision making. Robust MDPs (RMDPs) extend this framework by allowing uncertainty in transition probabilities and optimizing against the worst-case realization of that uncertainty. In particular, $(s, a)$-rectangular RMDPs with $L_\infty$ uncertainty sets form a fundamental and expressive model: they subsume classical MDPs and turn-based stochastic games. We consider this model with discounted payoffs. The existence of polynomial and strongly-polynomial time algorithms is a fundamental problem for these optimization models. For MDPs, linear programming yields polynomial-time algorithms for any arbitrary discount factor, and the seminal work of Ye established strongly--polynomial time for a fixed discount factor. The generalization of such results to RMDPs has remained an important open problem. In this work, we show that a robust policy iteration algorithm runs in strongly-polynomial time for $(s, a)$-rectangular $L_\infty$ RMDPs with a constant (fixed) discount factor, resolving an important algorithmic question.
arXiv:2606.03207v1 Announce Type: new
Abstract: We report a passive stabilization of the repetition rate for a mode-locked fiber laser by using an electro-optic modulator in a phase-biased nonlinear amplifying loop mirror. The underlying mechanism, in contrast to active feedback operations, lies in the cross-phase modulation between electrical and optical pulses within an electro-optic crystal. The resulting spectral shift can automatically compensate the cavity-length drift via the group velocity dispersion. Consequently, the artificial actuator enables to obtain a capture range up to 2.3 mm, much longer than that achieved by index changes of the modulator. A robust and tight locking for the repetition rate is then realized with a standard deviation as low as 9 $\mu$Hz with a 1-s sample time over 11 hours, corresponding to a fractional instability of 4.3$\times$10$^{-13}$. Furthermore, a dynamic optical sampling by repetition-rate tuning has been manifested with a fast refresh rate at 100 kHz and a broad scanning range over 305 ps. The demonstrated passive servo action may provide a simple yet effective way to stabilize the repetition rate with high precision, large bandwidth and wide tunability.
arXiv:2601.21683v2 Announce Type: replace
Abstract: While end-to-end self-supervised learning with backpropagation (global BP-SSL) has become central for training modern AI systems, theories of local self-supervised learning (local-SSL) have struggled to build functional representations in deep neural networks. To establish a link between global and local rules, we first develop a theory for deep linear networks: we identify conditions for local-SSL algorithms (like Forward-forward or CLAPP) to implement exactly the same weight update as a global BP-SSL. Starting from the theoretical insights, we then develop novel variants of local-SSL algorithms to approximate global BP-SSL in deep non-linear convolutional neural networks. Variants that improve the similarity between gradient updates of local-SSL with those of global BP-SSL also show better performance on image datasets (CIFAR-10, STL-10, and Tiny ImageNet). The best local-SSL rule with the CLAPP loss function matches the performance of a comparable global BP-SSL with InfoNCE or CPC-like loss functions, and improves upon state-of-the-art for local SSL on these benchmarks.
arXiv:2606.03010v1 Announce Type: new
Abstract: Alternative data availability (AltDA) systems provide Ethereum L2s with an external data publication layer for high throughput rollup designs. By moving bulk data publication outside of Ethereum, AltDA allows L2s to process more data than native DA. However, this replacement introduces a new consensus critical integration layer. Existing ecosystem frameworks identify high level risks, such as external DA trust assumptions and the presence or absence of a DA verifier, but do not provide a complete specification for how an L2 should integrate with AltDA. This gap can lead to L2 halts, inconsistent derivation across honest L2 nodes, invalid state assertions, or bridge attacks. This paper presents a canonical validation framework for secure AltDA integration. We model the boundary as a typed, deterministic, and total translation from L1 inbox bytes to an AltDA commitment, then to externally available data, and finally to the rollup payload consumed by the rest of core L2s logic. The central principle is that every adversarial input must lead to a defined unique outcome. We show how missing obligations lead to concrete failure modes, including underconstrained settlement, derivation halts, inconsistent honest node behavior, invalid state assertions, and bridge safety failures. We then apply the framework to representative AltDA integration architectures, including Celestia-Blobstream, EigenDA based designs, and Avail-ZKsync. Our evaluation shows that secure AltDA integration is not determined solely by the DA provider or bridge. The surrounding L2 integration must also enforce the full validation relation connecting L1 inbox inputs to accepted L2 state.
arXiv:2606.03005v1 Announce Type: new
Abstract: Despite rapid progress, multimodal large language models (MLLMs) still fail on tasks that humans solve effortlessly, such as navigating a grid maze from a screenshot or selecting the correct puzzle piece. Rather than retraining the model, we ask a complementary question: how much capability can be elicited from a frozen MLLM purely by improving the execution scaffold around it? We introduce MUSE, a multimodal unified structured execution harness that wraps any off-the-shelf MLLM with composable modules for task representation, visual processing, perception tool use, structured parsing, deterministic verification, and verifier-guided repair, without any model retraining. We evaluate MUSE across diverse benchmarks spanning visual spatial planning, visual perception, multimodal reasoning, and fine-grained visual discrimination, using multiple state-of-the-art MLLMs. MUSE delivers consistent gains over the bare model in all settings, with the largest jumps on challenging instances. Further analysis reveals that many MLLM failures arise from harness-level shortcomings rather than fundamental model deficits, and can be addressed through verifier-guided repair without touching the model. These findings highlight the agentic multimodal harness as a critical yet underexplored design dimension, offering an orthogonal avenue for improving MLLMs beyond model-centric optimization.
arXiv:2605.26006v2 Announce Type: replace
Abstract: Enabling physics-based humanoids to execute diverse behaviors from high-level textual commands remains a significant challenge. Existing methods typically follow either a two-stage paradigm that combines kinematic motion generation with physics-based tracking, or an end-to-end imitation-learning paradigm that directly generates actions from text. However, the former suffers from the inherent domain shift between kinematic generation and physics-based tracking, while the latter struggles with the substantial modality gap between textual commands and low-level actions, limiting effective semantic alignment. Notably, humanoid states encode rich motion dynamics that are more semantically aligned with textual descriptions than low-level actions, making them a natural basis for deriving behavioral intent. Building upon this insight, we propose MIND, a novel end-to-end diffusion framework for text-driven physics-based humanoid control that leverages behavioral intent as a semantic bridge between textual commands and low-level actions. At its core, MIND introduces a multi-scale intent diffusion mechanism, where a holistic intent predictor captures global behavioral dynamics to guide overall behavior synthesis, while an immediate intent predictor provides step-wise, fine-grained signals for local behavior refinement at each diffusion step. This hierarchical intent formulation imposes a structured inductive bias for humanoid control, improving semantic alignment and behavioral naturalness. Furthermore, MIND encodes humanoid states into a latent space to enable more effective semantic intent modeling. Extensive experiments demonstrate that MIND outperforms existing methods and synthesizes coherent, physically plausible, and semantically aligned humanoid behaviors from text commands. Project page: https://binlee26.github.io/MIND_page.
arXiv:2605.31530v2 Announce Type: replace-cross
Abstract: We present UNISON, a latent diffusion framework that unifies speech generation, sound generation, and audio editing within a single model. A single model handles text-to-audio, text-to-speech, zero-shot speaker cloning, mixed speech-and-sound generation, scene-level audio editing, speech-in-scene editing, and timed temporal composition, all of which share a single set of weights. Our architecture features two core designs: (1) Layer-wise deep LLM fusion, which injects hidden states from uniformly sampled layers of a frozen MLLM into corresponding MM-DiT blocks via learned projections, providing depth-matched semantic conditioning that improves instruction following over single-layer baselines; and (2) a unified multi-task architecture where task identity is encoded solely by a channel-wise mask and source audio is provided through VAE-encoded channel concatenation. Training is stabilized by an online GPU-side multi-task data synthesis pipeline with task-homogeneous batching and a two-stage curriculum. With 621M--732M trainable parameters, UNISON achieves results competitive with or exceeding task-specialist models across evaluated domains, while being roughly $4\times$ smaller than comparable unified systems.
arXiv:2604.19005v2 Announce Type: replace
Abstract: Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on explicit falsehoods. Addressing such omission-based manipulation requires reasoning not only about what is said, but also about what is left unsaid. We propose RADAR, a role-anchored multi-agent debate framework for omission-aware fact verification under realistic, noisy retrieval. RADAR assigns complementary roles to a Politician and a Scientist, who reason adversarially over shared retrieved evidence, moderated by a neutral Judge. A dual-threshold early termination controller adaptively decides when sufficient reasoning has been reached to issue a verdict. Experiments show that RADAR consistently outperforms strong single- and multi-agent baselines across datasets and backbones, improving omission detection accuracy while reducing reasoning cost. These results demonstrate that role-anchored, retrieval-grounded debate with adaptive control is an effective and scalable framework for uncovering missing context in fact verification.
arXiv:2604.19275v2 Announce Type: replace
Abstract: Modern UAV architectures increasingly aim to unify high-level autonomy and low-level flight control on a single General-Purpose Operating System (GPOS). However, complex multi-core System-on-Chips (SoCs) introduce significant timing indeterminism due to shared resource contention. This paper performs an architectural analysis of the PREEMPT RT Linux kernel on a Raspberry Pi 5, specifically isolating the impact of kernel activation paths (deferred execution SoftIRQs versus real-time direct activation) on a 250 Hz control loop. Results show that under heavy stress, the standard kernel is unsuitable, exhibiting worst-case latencies exceeding 9 ms. In contrast, PREEMPT RT reduced the worst-case latency by nearly 88 percent to under 225 microseconds, enforcing a direct wake-up path that mitigates OS noise. These findings demonstrate that while PREEMPT RT resolves scheduling variance, the residual jitter on modern SoCs is primarily driven by hardware memory contention.
arXiv:2603.05691v3 Announce Type: replace
Abstract: It is increasingly common in machine learning to use learned models to label data and then employ such data to train more capable models. The phenomenon of weak-to-strong generalization exemplifies the advantage of this two-stage procedure: a strong student is trained on imperfect labels obtained from a weak teacher, and yet the strong student outperforms the weak teacher. In this paper, we show that the potential improvement is substantial, in the sense that it affects the scaling law followed by the test error. Specifically, we consider students and teachers trained via random feature ridge regression (RFRR). Our main technical contribution is to derive a deterministic equivalent for the excess test error of the student trained on labels obtained via the teacher. Via this deterministic equivalent, we then identify regimes in which the scaling law of the student improves upon that of the teacher, unveiling that the improvement can be achieved both in bias-dominated and variance-dominated settings. Strikingly, the student may attain the minimax optimal rate regardless of the scaling law of the teacher -- in fact, when the test error of the teacher does not even decay with the sample size.
arXiv:2601.18627v2 Announce Type: replace-cross
Abstract: Cross-correlations between 21cm observations and galaxy surveys provide a powerful probe of reionization by providing robustness against foreground contamination while linking ionization morphology to galaxies. We quantified the constraining power of 21cm galaxy cross-power spectra for inferring the neutral hydrogen fraction, $x_\mathrm{HI}(z),$ and mean overdensity, $\langle 1+\delta_\mathrm{HI} \rangle(z)$, exploring dependence on the field of view; redshift precision, $\sigma_z$; and minimum halo mass, $M_\mathrm{h,min}$. We employed our simulation-based inference framework EoRFlow for likelihood-free parameter estimation. Mock observations include thermal noise for 100h of SKA-Low with foreground avoidance and realistic galaxy-survey effects. For a fiducial survey ($\mathrm{FOV}=100\,\mathrm{deg}^2$, $\sigma_z=0.001$, $M_\mathrm{h,min}=10^{11}\mathrm{M}_\odot$), cross-power spectra yield unbiased constraints with posterior volumes (PVs) of $\sim$10% relative to priors. Cross-power measurements reduce the PV by 20-30% versus 21cm auto-power alone. With foreground avoidance, spectroscopic redshift precision is essential; photometric redshifts render cross-correlations uninformative. Notably, cross-power spectra constrain ionizing source properties, the escape fraction $f_\mathrm{esc,}$ and the star formation efficiency $f_*$, which remain degenerate in auto-power (PV >60%). Tight constraints require either deep surveys detecting faint galaxies ($M_\mathrm{h,min} \sim 10^{10}\mathrm{M}_\odot$) with moderate foregrounds (PV~11%) or conservative mass limits with optimistic foreground removal (PV~19%). 21cm galaxy cross-correlations enhance morphology constraints beyond auto-power while enabling previously inaccessible source property constraints. Realizing full potential requires precise redshifts and either faint galaxy detection limits or improved 21cm foreground cleaning.
arXiv:2601.04120v2 Announce Type: replace-cross
Abstract: Optimal control of obstacle problems arises in a wide range of applications and is computationally challenging due to its nonsmoothness, nonlinearity, and bilevel structure. Classical numerical approaches rely on mesh-based discretization and typically require solving a sequence of costly subproblems. In this work, we propose a single-loop bilevel deep learning method, which is mesh-free, scalable to high-dimensional and complex domains, and avoids repeated solution of discretized subproblems. The method employs constraint-embedding neural networks to approximate the state and control and preserves the bilevel structure. To train the neural networks efficiently, we propose a Single-Loop Stochastic First-Order Bilevel Algorithm (S2-FOBA), which eliminates nested optimization and does not rely on restrictive lower-level uniqueness assumptions. We analyze the convergence behavior of S2-FOBA under mild assumptions. Numerical experiments on benchmark examples, including distributed and obstacle control problems with regular and irregular obstacles on complex domains, demonstrate that the proposed method achieves satisfactory accuracy while reducing computational cost compared to classical numerical methods.
arXiv:2601.00990v3 Announce Type: replace-cross
Abstract: Fetal ultrasound is the cornerstone of antenatal care, and accurate recognition of a small set of standard anatomical planes underpins biometry, growth surveillance, and detection of structural anomalies. Deep learning classifiers now match or exceed expert accuracy on curated benchmarks, but most remain opaque and miscalibrated, leaving clinicians without the calibrated confidence or faithful explanations needed for safe decision support. We systematically reviewed 78 studies published between January 1, 2015 and April 30, 2026 that paired automated fetal plane classification with explainability or predictive uncertainty quantification, following PRISMA 2020. Pooled balanced accuracy across six standard planes was 0.93 (95% CI 0.91 to 0.95), but only 19 studies (24%) reported calibration and 14 (18%) reported selective prediction. We propose CALIB-XFUS, a 22-item reporting framework that operationalises calibration, explanation faithfulness, and fairness for regulated fetal ultrasound artificial intelligence. The framework spans six domains: clinical task and indication for use; dataset provenance and representativeness; model and training pipeline; calibration and selective prediction; explanation faithfulness and clinician validation; and post-market surveillance. We argue that uncertainty-calibrated, faithfully explained, and fairness-audited fetal ultrasound AI is now both technically feasible and regulatorily expected under the FDA Good Machine Learning Practice principles and the EU AI Act high-risk obligations.
arXiv:2512.14508v2 Announce Type: replace-cross
Abstract: Strain engineering enables quantum confinement in pristine graphene without degrading its intrinsic mobility and spin coherence. Here, we extend previously proposed strain-induced charge-qubit architectures by incorporating spin degrees of freedom through Rashba spin-orbit coupling (RSOC) and Zeeman fields, enabling spin-qubit operation in single-layer graphene (SLG). In a graphene p-n junction, a strain-induced nanobubble generates a pseudo-magnetic field that forms double quantum dots with gate-tunable level hybridization. Tight-binding quantum transport simulations and a four-band model reveal two distinct avoided crossings: spin-conserving gaps at zero detuning and spin-flip gaps at finite detuning, the latter increasing with SOC strength while the former decreases. Time-domain simulations confirm detuning-dependent Rabi oscillations corresponding to these two operational regimes. These results demonstrate that strain-induced confinement combined with tunable SOC provides a viable mechanism for coherent spin manipulation in pristine graphene, positioning strained SLG as a promising platform for scalable spin-based quantum technologies.
arXiv:2604.20183v2 Announce Type: replace
Abstract: Large Language Models (LLMs) often struggle with structural ambiguity in optimization problems, where a single problem admits multiple related but conflicting modeling paradigms, hindering effective solution generation. To address this, we propose Dual-Cluster Memory Agent (DCM-Agent) to enhance performance by leveraging historical solutions in a training-free manner. Central to this is Dual-Cluster Memory Construction. This agent assigns historical solutions to modeling and coding clusters, then distills each cluster's content into three structured types: Approach, Checklist, and Pitfall. This process derives generalizable guidance knowledge. Furthermore, this agent introduces Memory-augmented Inference to dynamically navigate solution paths, detect and repair errors, and adaptively switch reasoning paths with structured knowledge. The experiments across seven optimization benchmarks demonstrate that DCM-Agent achieves an average performance improvement of 11%- 21%. Notably, our analysis reveals a ``knowledge inheritance'' phenomenon: memory constructed by larger models can guide smaller models toward superior performance, highlighting the framework's scalability and efficiency.
arXiv:2606.01629v2 Announce Type: replace
Abstract: As large language models (LLMs) are increasingly used for long-form generation, reliably evaluating long-form outputs has become a critical challenge. LLM-as-a-judge offers a scalable alternative to human evaluation, yet its reliability in long-form output evaluation remains underexamined: existing meta-evaluation benchmarks focus mainly on short-form outputs. Compared with short-form evaluation, long-form evaluation is not merely a matter of output length; it often requires judges to make more complex document-level assessments of overall organization, task-relevant coverage and depth, cross-section consistency, and scenario-specific quality criteria. In this work, we introduce LongJudgeBench, a comprehensive benchmark for evaluating LLM judges on long-form outputs across diverse real-world scenarios and judging protocols. We systematically evaluate a broad range of LLM judges, covering multiple base models and judging settings. Our results reveal a substantial reliability gap: current LLM judges remain unstable across scenarios, and rubrics or references are helpful but not always sufficient. We hope LongJudgeBench will support future research on more robust, context-aware, and human-aligned LLM-as-a-judge methods. Our code is available at https://github.com/cjj826/LongJudgeBench.
arXiv:2604.22900v2 Announce Type: replace
Abstract: We extend the CDPR's quantum attack from ideal lattices to module lattices over $2^k$-th cyclotomic rings. Using trace orthogonality of the power basis, we decompose a rank-$d$ module into mutually orthogonal rank-$1$ submodules, and apply CDPR's analysis to each independently and return the shortest candidate. The Hermite factor $\exp(\tilde{O}(\sqrt{n}))$ matches the ideal case, with a module reduction factor $\alpha_d=O(1)$ independent of the rank, under a balance hypothesis (proved for Gaussian distribution) automatic for MLWE-distributed bases. To enable a bounded-precision implementation, we replace coordinate-wise rounding with Chinese Remainder Theorem-scaled rounding at totally split primes, reducing the Gram-Schmidt rounding radius from $n/2$ to $\le 1$ at cost $O(d^2 r n \log n)$. Finally, we reformulate the CDPR's sign-selection step as a mixed-integer linear program and prove its optimum is no more than 1/2 for all $k$ ($\approx 0.4407$ for all tested $k\le 12$, conjecturally universal). This replaces the previous heuristic discrepancy $\Theta(\sqrt{nk})$. All results build on the class number condition $h_k^+=1$ established in Part I of this series.
arXiv:2604.25417v3 Announce Type: replace
Abstract: We present a novel and unifying framework for constructing spectral approximations to fractional integral operators. These spectral approximations are based on transplanted Chebyshev polynomials, which are obtained by composing Chebyshev polynomials with a variable transform. When an algebraic transform is used, the framework produces spectral approximations based on Jacobi fractional polynomials. When an exponential transform is used, it yields a versatile spectral approximation that is applicable to a much broader class of fractional calculus problems. The construction of such spectral approximations is both numerically stable and optimal in terms of complexity. These spectral approximations lead to stable and fast spectral methods for fractional calculus. The spectral approximation based on the double-exponential transform is demonstrated through extensive numerical examples that are intractable for existing spectral methods.
arXiv:2604.25928v2 Announce Type: replace
Abstract: Retrieval-Augmented Generation (RAG) frameworks typically process all queries through a one-size-fits-all pipeline, ignoring the heterogeneous cognitive demands of different tasks. This cognitive-blind approach causes two failure modes: cascading errors when low-level factual gaps trigger hallucinated reasoning, and reasoning-answer inconsistency in higher-order analytical tasks. We introduce CogRAG, a training-free, domain-agnostic framework that tackles these heterogeneous cognitive demands via stratified retrieval and reasoning. Inspired by Bloom's Taxonomy, CogRAG uses the predicted cognitive load of a query as a central control signal that coordinates two modules: Cognition-Adaptive Evidence Refinement supplements missing context via fact-centric or option-centric paths, and Cognition-Stratified Structured Reasoning replaces unconstrained chain-of-thought with cognition-aligned reasoning templates. We evaluate CogRAG on a demanding professional testbed, the Registered Dietitian qualification examination. CogRAG effectively reduces early-stage factual errors and eliminates reasoning-answer inconsistency, raising Qwen3-8B accuracy from 73.4\% to 85.8\% in single-choice mode and from 63.3\% to 80.5\% in scenario mode. These results highlight cognitive-stratified control as an effective, generalizable paradigm for reliable complex reasoning in large language models.
arXiv:2604.26594v3 Announce Type: replace
Abstract: Antarctic sea ice has undergone unprecedented changes in recent years, raising questions about how this key geophysical system is responding to climate change. Decades of slow expansion were replaced by a precipitous decline in 2014-2017, a subsequent apparent recovery, and a renewed collapse from 2022 to the present. We diagnosed sea ice concentration (SIC) from satellite observations with a hierarchical decomposition method based on Dynamic Mode Decomposition (DMD) that finds coherent spatiotemporal modes. We find that the 2014-2017 decline and apparent recovery are the result of interacting interannual modes and that a climate change signal emerges in 2012, which becomes unambiguous by 2022 when it dominates over interannual variability. These rapid changes underscore the need for seasonal-to-annual forecasts of SIC. However, existing forecasts are subject to limited prediction horizons combined with high computational costs. Our predictive DMD model (IceDMD) is regularised to prioritize the stationary spatiotemporal modes found by the decomposition. The predictive model can forecast SIC anomalies in 2023-2024 up to two years in advance, outperforming all existing approaches with the additional benefits of physical interpretability and extremely cheap computational cost. Finally, this framework for regularising predictive DMD models can be generalized to a range of multi-scale systems.
arXiv:2604.27147v3 Announce Type: replace
Abstract: In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human preferences, a problem known as \textit{guidance}. Despite their widespread use, existing guidance methods either require expensive multi-particle, many-step schemes or rely on poorly understood approximations. We reformulate guidance as a \textit{deterministic optimal control problem}, yielding a hierarchy of algorithms that subsumes existing approaches at the coarsest level. We show that the \textit{flow map}, an object of significant recent interest for its role in fast inference, arises naturally in the optimal solution. Based on this observation, we propose \textbf{Flow Map Reward Guidance (FMRG)}: a training-free, \textit{single-trajectory} framework that uses the flow map to both integrate and guide the flow. At text-to-image scale, FMRG matches or surpasses baselines across inverse problems and reward-guided generation with \textbf{as few as 3 NFEs}, giving at least an order-of-magnitude speedup in comparison to prior state of the art. Code is available at https://github.com/jrrhuang/fmrg.
arXiv:2512.07053v3 Announce Type: replace-cross
Abstract: Integrating contention-based random access procedures into low Earth orbit (LEO) satellite communication (SatCom) systems poses new challenges, including long propagation delays, large Doppler shifts, and a large number of simultaneous access attempts. These factors degrade the efficiency and responsiveness of conventional random access schemes, particularly in scenarios such as satellite-based internet of things and direct-to-device services. In this paper, we propose a deep learning-based random access framework designed for LEO SatCom systems. The framework incorporates an early preamble collision classifier that uses multi-antenna correlation features and a lightweight 1D convolutional neural network to estimate the number of collided users at the earliest stage. Based on this estimate, we introduce an opportunistic transmission scheme that balances access probability and resource efficiency to improve success rates and reduce delay. Simulation results under 3GPP-compliant LEO settings confirm that the proposed framework achieves higher access success probability, lower delay, better physical uplink shared channel utilization, and reduced computational complexity compared to existing schemes.
arXiv:2603.04956v2 Announce Type: replace
Abstract: This paper considers the problem of converting a given dense linear layer to low precision. The tradeoff between compressed length and output discrepancy is analyzed information theoretically (IT). It is shown that a popular GPTQ algorithm may have an arbitrarily large gap to the IT limit. To alleviate this problem, a novel algorithm, termed ``WaterSIC'', is proposed and is shown to be within a rate gap of 0.255 bits to the IT limit, uniformly over all possible covariance matrices of input activations. The key innovation of WaterSIC's is to allocate different quantization rates to different columns (in-features) of the weight matrix, mimicking the classical IT solution known as "waterfilling". Applying WaterSIC to the Llama and Qwen family of LLMs establishes new state-of-the-art performance for all quantization rates from 1 to 4 bits. Our code is available at https://github.com/egorlifar/watersic.
arXiv:2511.13899v2 Announce Type: replace-cross
Abstract: Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity. Although their functional connectivity is low-rank, it lacks independence interpretations, making it difficult to assign distinct computational roles to different latent dimensions. To address this, we propose the Factored Recurrent Neural Network (FacRNN), a generative lrRNN framework that assumes group-wise independence among latent dynamics while allowing flexible within-group entanglement. These independent latent groups allow latent dynamics to evolve separately, but are internally rich for complex computation. We reformulate the lrRNN under a variational autoencoder (VAE) framework, enabling us to introduce a partial correlation penalty that encourages independence between groups of latent dimensions. Experiments on synthetic, monkey M1, and mouse voltage imaging data show that FacRNN consistently improves the disentanglement and interpretability of learned neural latent trajectories in low-dimensional space and low-rank connectivity over baseline lrRNNs that do not encourage group-wise independence.