Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
arXiv (CS.CL) 2026-06-16

A Unified Definition of Hallucination: It's The World Model, Stupid!

Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review existing definitions of hallucination and fold them into a single, unified definition wherein prior definitions are subsumed. We argue that hallucination can be unified by defining it as simply inaccurate (internal) world modeling, in a form where it is observable to the user. For example, stating a fact which contradicts a knowledge base OR producing a summary which contradicts the source. By varying the reference world model and conflict policy, our framework unifies prior definitions. We argue that this unified view is useful because it forces evaluations to clarify their assumed reference "world", distinguishes true hallucinations from planning or reward errors, and provides a common language for comparison across benchmarks and discussion of mitigation strategies. Building on this definition, we also connect our framework to HalluWorld, a complementary benchmark that instantiates fully specified reference world models for stress-testing model hallucinations.

02.
arXiv (CS.LG) 2026-06-11

APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations

arXiv:2606.11553v1 Announce Type: new Abstract: Generic time-series foundation models transfer poorly to wireless network telemetry whose signals are bursty, zero-inflated, and coupled across protocol layers. We present APEX, a network-native, decoder-only transformer for forecasting enterprise AP telemetry, and evaluate it on DHCP degradation as a representative network task. APEX is pre-trained on 10-channel multivariate telemetry from ~4,500 production wireless networks (~100K AP time series, 34 metrics per AP), and is available as APEX-Large (269M, cloud) and APEX-Edge (10.5M, edge). On a 192-step (4-day) DHCP degradation benchmark, APEX-Large reduces MAE by 18% over the strongest foundation-model baseline (Toto) and 38% over SARIMA, with anomaly-detection F1 = 0.93, while APEX-Edge enables sub-second, privacy-preserving inference on AP-class edge hardware. These results suggest network-native pre-training is a practical foundation for proactive wireless operations.

04.
arXiv (CS.CV) 2026-06-11

CellNet – Localizing Cells using Sparse and Noisy Point Annotations

Counting living cells is an important step in many biological research workflows. Our collaborators at the Wellcome Sanger Institute study vital genes in humans via large scale saturation genome editing screening, which requires repeatedly counting cells a great number of times. Computer Vision based automation is crucial for high throughput and resource efficiency. In this work, we develop a regression-based deep learning computer vision algorithm to detect and count cells in phase-contrast microscopy images. To reduce annotation effort, which in practice often becomes a bottleneck, we focus on counting cells only using sparse point annotations, which are fast and easy to acquire. By comparison to state-of-the-art 0-shot methods, we show that regression-based counting is a promising alternative in low data regimes. Through developing methods to automatically count living cells in microscopy images, we contribute to valuable research on the human genome. The code is available at https://github.com/beijn/cellnet.

05.
arXiv (CS.AI) 2026-06-17

PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation

arXiv:2606.17199v1 Announce Type: cross Abstract: Standard on-policy distillation (OPD) for large language models estimates the reverse-KL objective using student-sampled tokens, yielding an unbiased single-sample Monte Carlo estimator that avoids vocabulary-wide computation. However, we show that this estimator suffers from severe training pathologies in practice: sample inefficiency, unstable generation dynamics, and a substantial performance gap compared to exact full-vocabulary OPD. Reward-level diagnosis traces these pathologies to the log-ratio reward, which is unbounded by construction, producing extremely high-variance gradients concentrated at early positions and persisting throughout training; standard post-hoc scaling fail as they operate only after this distortion occurs. To solve this problem, we propose PowerOPD: a family of natively bounded, sign-consistent rewards from the Box-Cox power transformation, parameterized by alpha > 0, of which the log-ratio is the degenerate alpha -> 0 limit. Across six mathematical reasoning benchmarks and four Qwen3 teacher-student pairs, PowerOPD achieves benchmark-averaged Avg@8/Pass@8 gains of up to +6.37/+5.71 over vanilla OPD, +3.01/+3.54 over post-hoc stabilization, and +2.59/+8.90 over full-vocabulary OPD, while reducing wall-clock time by 59.2% and peak GPU memory by 23.1%. Larger alpha generally improves accuracy, consistently shortens responses, and keeps gradient norms more than 3,000x smaller than vanilla OPD.

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

Q-Net: Queue Length Estimation via Kalman-based Neural Networks

arXiv:2509.24725v4 Announce Type: replace-cross Abstract: Estimating queue lengths at signalized intersections is a long-standing challenge in traffic management. Partial observability of vehicle flows complicates this task despite the availability of two privacy-preserving data sources: (i) aggregated vehicle counts from loop detectors near stop lines, and (ii) aggregated floating car data (aFCD) that provide segment-wise average speed measurements. However, how to integrate these sources with differing spatial and temporal resolutions for queue length estimation is rather unclear. Addressing this question, we present Q-Net: a queue estimation framework built upon a state-space formulation. This design addresses key challenges in queue modeling, such as violations of traffic conservation assumptions. Q-Net follows the Kalman predict-update structure and maintains physical interpretability in both the state evolution and measurement models. Q-Net uses an AI-augmented Kalman filter to learn time-varying gain dynamics from data. The framework supports real-time implementation and improves spatial transferability by grouping aFCD measurements into fixed-size local groups, making the number of learnable parameters independent of section length. Evaluations on urban main roads in Rotterdam, the Netherlands, show that Q-Net outperforms baseline methods, tracks queue formation and dissipation accurately, and mitigates aFCD-induced delays. By combining data efficiency, interpretability, real-time applicability, and spatial transferability, Q-Net makes accurate queue length estimation possible without costly sensing infrastructure like cameras or radar.

07.
PLOS Computational Biology 2026-06-11

A zero-parameter first-principles gate framework for full-length TP53 missense variant interpretation

by Masamichi Iizumi Missense variant interpretation often achieves useful predictive performance but remains mechanistically opaque, particularly in proteins that combine structured domains with intrinsically disordered regions (IDRs). We developed Gate & Channel, a zero-parameter, first-principles framework for full-length TP53 missense variant analysis in which each prediction is generated by explicit IF-THEN gates derived from physicochemistry, geometry, structural constraints, and polymer physics rather than fitted weights. Variants are evaluated across independent channels representing distinct physical failure modes; a variant is predicted disruptive if any gate closes. A second hierarchical layer (“Geta”) encodes physically grounded post-closure exceptions, allowing sensitivity and specificity to be improved on disjoint variant populations. The v18 framework consists of 12 channels and 2 Getas spanning structured domains and IDRs, capturing DNA-contact disruption, Zn coordination, burial-dependent packing, secondary-structure compatibility, post-translational modification chemistry, short linear motif disruption (including a multi-partner coupled-folding face), proline-directed kinase recognition, and IDR-specific proline and glycine backbone constraints. Across 1,369 TP53 missense variants, the framework achieved 84.5% sensitivity and 89.1% positive predictive value, with 90.9% sensitivity preserved in the DNA-binding core and all 9/9 hotspot mutations captured. A post hoc audit of discordant IDR calls indicated that many apparent false positives had plausible molecular rationales, consistent with a distinction between molecular mechanism disruption and clinical penetrance. Applied to KRAS, TDP-43, and BRCA1, the same channels capture the dominant pathogenic mechanisms in each protein as a proof of principle, while residual missed variants name specific gates yet to be written. The framework is distributed as the open-source Python package pathogenicity-gates (v0.5.1, MIT). These results show that a substantial fraction of full-length TP53 missense variation can be resolved through explicit, auditable physical gates that carry meaning beyond TP53, with each remaining failure naming the next rule to be written.

08.
arXiv (CS.CV) 2026-06-16

Mask Proposal Voting Based on Geodesic Framework for Robust Image Segmentation

Despite great advances, finding accurate segmentation remains a challenging task, especially in scenarios with cluttered backgrounds, complex intensity variations and topology appearance. Minimal path models have exhibited their strong ability in addressing image segmentation tasks. However, the performance of minimal paths-based segmentation approaches is heavily influenced by model initialization, hence limiting their application scope in practice. In this work, we propose a novel mask proposal voting framework that overcomes the major drawback of classical approaches, allowing robust segmentation even in complicated scenarios. Firstly, we introduce an efficient method for constructing adaptive domain cuts as a constraint for initializing the region-based min-cut evolution, by which diverse and reliable mask proposal candidates can be generated, substantially increasing the possibility of accurately covering the objective region by these proposals. Secondly, we propose a new mask voting scheme to build a voting score map encoding the final segmentation information. In contrast to classical path voting methods, our model allows incorporating priors to assign different importance to each individual mask. As a consequence, the proposed segmentation model is capable of accurately delineating object boundaries under complex scenarios, and is insensitive to initialization. Experiments demonstrate that our method consistently outperforms state-of-the-art minimal path-based approaches in both accuracy and robustness.

09.
PLOS Medicine 2026-06-01

Prenatal exposure to asthma medications and risk of neurodevelopmental disorders and educational difficulties: A systematic review and meta-analysis

by Lama A. Shakhshir, Alexia Karain, Jill P. Pell, Claire E. Hastie, Scott M. Nelson, Michael Fleming Background Since asthma exacerbations during pregnancy risk maternal and fetal health, continued medication is important. However, some studies have reported adverse neurodevelopmental outcomes following prenatal exposure to asthma medication. Therefore, this systematic review aimed to collate the existing evidence on the associations between prenatal exposure to asthma medication and neurodevelopmental and educational outcomes. Methods and findings A systematic review was conducted in accordance with PRISMA guidelines and the PECO framework. PubMed, Medline and Embase databases were searched for studies investigating prenatal exposure to one or more asthma medication and neurodevelopmental or educational outcomes published, in English, between January 2003 and September 2024, and updated in November 2025. Studies of asthma medication used for other indications were excluded. Study quality was assessed using the Newcastle-Ottawa scale. Random-effects meta-analyses were conducted where appropriate and heterogeneity was evaluated using Cochran’s Q and I2 tests.Of 16,824 studies identified by the initial search, seven were eligible for inclusion. All investigated beta-2-adrenergic agonists (B2AA), with one including B2AA as mono- and polytherapy—and one study also investigated inhaled corticosteroids (ICS) exposure. Two reported associations with autism spectrum disorder (ASD) and one with attention-deficit hyperactivity disorder (ADHD). An updated search identified one additional eligible study, which examined both ADHD and ASD, as well as other neurodevelopmental disorders. The included eight studies (n = 3,867,170 participants) comprised cohort (n = 5) and case-control (n = 3) designs and reported inconsistent results. Meta-analysis of three studies (n = 1,380,871) indicated significant associations with ASD for exposure to B2AA both preconception (aOR 1.34, 95% CI [1.19,1.52]) and during pregnancy (aOR 1.29, 95% CI [1.16,1.42]). Heterogeneity was low, with no evidence of significant publication bias. Limitations of the included studies comprised residual confounding and exposure misclassification. Additionally, studies included in the meta-analysis were few in number and did not adequately distinguish between medication effects and underlying maternal asthma. Conclusion Meta-analysis suggested an association between prenatal exposure to B2AA and ASD. An association with ADHD, reported in a single study, requires corroboration. To date, based on our search strategy, no association has been reported with communication skills, motor skills, problem-solving and personal-social skills, or cerebral palsy.

10.
arXiv (quant-ph) 2026-06-11

Quest for quantum advantage: Monte Carlo wave-function simulations of the Coherent Ising Machine

arXiv:2501.02681v2 Announce Type: replace Abstract: The Coherent Ising Machine (CIM) is a quantum network of optical parametric oscillators (OPOs) intended to find ground states of the Ising model. This is an NP-hard problem, related to several important minimization problems, including the max-cut graph problem. In order to enhance its potential performance, we analyze the coherent coupling strategy for the CIM in a highly quantum regime. To explore this limit, without assuming gaussianity, we employ accurate numerical simulations. Due to the inherent complexity of the system, the maximum network size is limited. While master equation methods can be used, their scalability diminishes rapidly for larger systems. Instead, we use Monte Carlo wave-function methods, which scale as the wave-function dimension, and use large numbers of samples. These simulations involve Hilbert spaces exceeding $10^{7}$ dimensions. To evaluate success probabilities, we use quadrature probabilities. We demonstrate the potential for quantum computational advantage by reducing the time required to reach maximum success probability in a low-dissipation regime enabled by initial quantum superpositions and entanglement. Furthermore, we demonstrate that tailored time-dependent couplings can amplify these quantum effects. Comparisons with classical CIM models give evidence that quantum tunneling effects in this strong coupling limit can overcome trapping in false minima. This can greatly increase success rates, indicating a potential for quantum advantage. Finally, we perform a coherence analysis based on the state purity to examine the role of quantum coherence in CIM performance and to determine how state purity correlates with improved optimization outcomes.

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

Differential Privacy of Gaussian Process Posterior Sampling

arXiv:2606.17995v1 Announce Type: cross Abstract: We study the privacy of releasing posterior sample paths from a Gaussian process (GP) when the entire training set including covariates and responses is private. Unlike standard differential-privacy (DP) mechanisms that add external noise, posterior sampling is random by construction. We show that this intrinsic randomness yields DP guarantees by deriving explicit Rényi-DP bounds for GP posterior sample-path release. The bounds separate posterior-mean leakage from data-dependent posterior-covariance leakage showing that meaningful privacy depends sharply on effective ridge regularisation. We apply membership-inference attacks to show that empirical leakage follows the predicted dependence on regularisation, posterior variance and the number of released posterior sample-paths. Utility experiments on downstream posterior-sampling tasks identify noisy-observation regimes where privacy-compatible regularisation preserves useful decisions with modest utility loss. When stronger privacy is needed, the intrinsic guarantee can be sharpened by adding calibrated GP noise, providing an explicit additional privacy knob.

12.
arXiv (CS.LG) 2026-06-11

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal

arXiv:2606.12360v1 Announce Type: new Abstract: Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata. This abstraction gives practitioners little visibility into what their data actually teaches models, allowing spurious correlations to be learned by a model and inducing undesirable behaviors such as over-stylization and sycophancy. To address this problem, we ask: can we inspect a preference dataset before optimization and decide, at the level of concepts, which behaviors a model should be allowed to learn? Motivated by this, we introduce a data-centric post-training pipeline that uses interpretability protocols to develop statistical hypotheses for the latent concepts separating preferred from dispreferred generations, making them explicit for fine-grained user feedback. Building on this view, we unify several interpretability-based training protocols as ways of shaping rewards via feature or data interventions. Empirically, we show that our pipeline diagnoses undesirable signals in existing preference data, mitigates off-target learning, and can also help amplify or shape desired properties such as safeguards and model personality. More broadly, our results suggest that interpretability can turn post-training from optimizing opaque proxy rewards into a process of auditing and sculpting the learning signal itself.

13.
arXiv (quant-ph) 2026-06-11

Sharing quantum indistinguishability with multiple parties

arXiv:2512.15199v3 Announce Type: replace Abstract: Quantum indistinguishability of non-orthogonal quantum states is a valuable resource in quantum information applications such as cryptography and randomness generation. In this article, we present a sequential state-discrimination scheme that enables multiple parties to share quantum uncertainty, in terms of the max relative entropy, generated by a single party. Our scheme is based upon maximum-confidence measurements and takes advantages of weak measurements to allow a number of parties to perform state discrimination on a single quantum system. We review known sequential state discrimination and show how our scheme would work through a number of examples where ensembles may or may not contain symmetries. Our results will have a role to play in understanding the ultimate limits of sequential information extraction and guide the development of quantum resource sharing in sequential settings.

14.
arXiv (CS.AI) 2026-06-16

PolyKV: Heterogeneous Retention and Allocation for KV Cache Compression

arXiv:2606.15157v1 Announce Type: cross Abstract: KV cache compression is essential for reducing the memory cost of long-context large language model inference. Existing approaches, however, typically apply a single compression policy and a uniform cache budget across all transformer layers. This uniform design ignores the fact that different layers can play different roles during prefill and decoding, and may therefore require different eviction strategies and cache capacities. We present PolyKV, a layer-wise KV cache optimization framework that considers design space with method selection and budget allocation. PolyKV routes each layer to a suitable KV compression policy based on layer-level signals, while assigning non-uniform budgets under a fixed total budget. This formulation enables heterogeneous compositions of existing KV cache methods. Experiments on LLaMA-3.1-8B and Qwen3-8B show that, under the same 512-token average KV budget, PolyKV recovers 54.5% and 25.7% of the LongBench performance gap between the strongest single-policy baseline and FullKV, respectively. Across 128-1024 budget sweep, PolyKV consistently improves over the strongest baseline by 1.7%-6.4%, corresponding to 40.0%-54.5% recovery of the FullKV gap.

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

Estimating carbon pools in the European Shelf sea environment: replacing reanalysis by model-informed machine learning?

arXiv:2508.10178v3 Announce Type: replace-cross Abstract: Shelf seas are important for the economy and the carbon cycle, but shelf sea observations for carbon pools are often sparse, or highly uncertain. An alternative can be provided by carbon reanalyses (whether assimilating proxy variables, such as chlorophyll-$a$, or directly carbon), but these are often expensive to run. We propose to use a computationally cheap ensemble of neural networks (i.e. deep ensemble) to learn the relationship between the directly observable (atmospheric, riverine and ocean) variables and marine carbon pools from a coupled physics-biogeochemistry model. The deep ensemble was trained on a North-West European Shelf (NWES) physical-biogeochemistry model free run simulation. After training, the deep ensemble was run using inputs from the NWES reanalysis instead of the free run, demonstrating that it can efficiently predict several NWES carbon pools (e.g., detritus, zooplankton, heterotrophic bacteria) in much better agreement with the reanalysis than the free run, while also providing uncertainty information. We further show that the deep ensemble performs similarly well when it is driven directly by the observations assimilated into the reanalysis, with the limitation that carbon pools can then be predicted only at the observed locations and times. We focus on explainability of the results and demonstrate potential use of the deep ensembles for future climate what-if scenarios. We suggest that model-informed machine learning presents a viable alternative to expensive reanalyses and could complement observations, wherever they are missing and/or highly uncertain.

16.
arXiv (CS.AI) 2026-06-12

CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction

arXiv:2603.00610v3 Announce Type: replace-cross Abstract: While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind. In this paper, we bridge this critical gap by establishing a comprehensive ecosystem for music reward modeling under Compositional Multimodal Instruction (CMI), where the generated music may be conditioned on text descriptions, lyrics, and audio prompts. We first introduce CMI-Pref-Pseudo, a large-scale preference dataset comprising 110k pseudo-labeled samples, and CMI-Pref, a high-quality, human-annotated corpus tailored for fine-grained alignment tasks. To unify the evaluation landscape, we propose CMI-RewardBench, a unified benchmark that evaluates music reward models on heterogeneous samples across musicality, text-music alignment, and compositional instruction alignment. Leveraging these resources, we develop CMI reward models (CMI-RMs), a parameter-efficient reward model family capable of processing heterogeneous inputs. We evaluate their correlation with human judgment scores on musicality and alignment on CMI-Pref along with previous datasets. Further experiments demonstrate that CMI-RM not only correlates strongly with human judgments, but also enables effective inference-time scaling via top-k filtering. Code is available at GitHub (https://github.com/Haiwen-Xia/CMI-RewardBench). Model weights: CMI-RM (https://huggingface.co/HaiwenXia/CMI-RM). Datasets: CMI-Pref-Pseudo (https://huggingface.co/datasets/HaiwenXia/cmi-pref-pseudo) and CMI-Pref (https://huggingface.co/datasets/HaiwenXia/cmi-pref)

17.
arXiv (quant-ph) 2026-06-16

Inflationary branch decoherence and the cosmological arrow of time

作者:

arXiv:2602.21263v3 Announce Type: cross Abstract: We analyze branch decoherence in inflationary quantum cosmology by computing reduced density matrices and branch-overlap factors for long-wavelength perturbations. The Hartle-Hawking no-boundary state is real in the semiclassical regime and contains both expanding and contracting WKB components, whereas the tunneling state is selected as an outgoing complex WKB branch; expanding-contracting decoherence is therefore central for the former and mainly diagnostic for the latter. Using the influence-functional formalism, we derive the noise kernel for a light spectator environment and evaluate decoherence under horizon-based and EFT-motivated coarse grainings. We then compute the single-mode branch overlap directly from the Bunch-Davies mode functions, obtaining $|\mathcal{D}_k(z)|=[z^2/(z^2+1)]^{1/4}$ in the massless limit and $|\mathcal{D}_k(z)|\sim z^\nu$ on superhorizon scales for massive fields, where $z=-k\eta$ is the dimensionless wavenumber with $\eta$ the conformal time. In the massless case, the accumulated geometric branch functional is evaluated in closed form, with a leading cutoff-sensitive phase-space term and a universal subleading contribution. The calculation provides an explicit quantitative bridge between quantum-cosmological boundary conditions, inflationary squeezing, and the emergence of effectively classical cosmological histories.

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

SED:Lightweight Saliency prediction for Event-based data via Distillation

Event-based saliency prediction has gained attention recently, as combining event cameras with saliency estimation can act as an upstream stage that naturally improves the efficiency of downstream eventbased perception at the edge. However, current approaches are either neuromorphic, underperforming on event-based saliency benchmarks, or too heavy for resource-constrained edge applications due to their reliance on transformers or 3D convolutions. Drawing inspiration from efficient convolutional modules, SED and aiming to exploit the temporal information in event data, we propose a lightweight network, trained through knowledge distillation, built on a Depthwise Spatio-Temporal Block (DSTconv) – a factorization of the 3D depthwise separable convolution. Relative to its teacher, our model reduces the model size from 180 MB to 0.32 MB (562x) and the parameter count from 45M to 81k (554x), while matching or outperforming it on the N-DHF1K and N-UCF Sports datasets. Moreover, it generalizes strongly beyond its training distribution, transferring from synthetic to real event data where a model trained from scratch fails.

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

SHARD: Safe and Helpful Alignment via Self-Reframing Distillation

Large language models often struggle with sensitive prompts. They may refuse outright, provide generic safety boilerplate, or fail to address the user's legitimate informational needs that can be answered safely. We introduce SHARD, a self-reframing distillation method to improve safe-helpfulness. It first rewrites sensitive prompts to surface benign intent using philosophical guidelines, then reframes its original responses into safe, more helpful ones, and finally fine-tunes the model on its self-reframed responses. Across DNA and the English subset of LINGUASAFE, SHARD improves helpfulness for most model families while preserving safety. It also remains competitive with distillation from a larger teacher model, suggesting that models can internalize safe and helpful behavior elicited from their own. Warning: This paper contains content that may be offensive or harmful.

20.
arXiv (CS.CV) 2026-06-11

Learning Instance-Adaptive Low-Rank Orthogonal Subspaces for Clothes-Changing Person Re-Identification

Clothes-changing person re-identification (CC-ReID) aims to recognize individuals despite drastic appearance changes caused by clothing variation. While existing methods rely on adversarial learning to disentangle clothing features, we propose Ortho-ReID, which explicitly models a low-rank clothing subspace from VLM text descriptions and extracts clothing-invariant representations via direct geometric constraints. A critical component is our transformer-based Basis Maker, which refines a shared, low-dimensional clothing prior into an instance-adaptive low-rank subspace through cross-attention with image patches, enabling robust clothing feature extraction even under varying visibility conditions. This instance-adaptive subspace is supervised via alignment with clothing text embeddings, while identity features are extracted via a learnable projection head and geometrically constrained to be strictly orthogonal to it. Extensive experiments demonstrate state-of-the-art performance on PRCC (+5.9% top-1), Celeb-reID-light (+3.5%), and LaST (+5.3%), with competitive results on LTCC.

21.
arXiv (CS.CL) 2026-06-15

Rethinking the Trust Region in LLM Reinforcement Learning

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio clipping mechanism in PPO is structurally ill-suited for the large vocabularies inherent to LLMs. PPO constrains policy updates based on the probability ratio of sampled tokens, which serves as a noisy single-sample Monte Carlo estimate of the true policy divergence. This creates a sub-optimal learning dynamic: updates to low-probability tokens are aggressively over-penalized, while potentially catastrophic shifts in high-probability tokens are under-constrained, leading to training inefficiency and instability. To address this, we propose Divergence Proximal Policy Optimization (DPPO), which substitutes heuristic clipping with a more principled constraint based on a direct estimate of policy divergence (e.g., Total Variation or KL). To avoid huge memory footprint, we introduce the efficient Binary and Top-K approximations to capture the essential divergence with negligible overhead. Extensive empirical evaluations demonstrate that DPPO achieves superior training stability and efficiency compared to existing methods, offering a more robust foundation for RL-based LLM fine-tuning. Our code is available at https://github.com/sail-sg/Stable-RL.

22.
arXiv (quant-ph) 2026-06-11

Dissociative recombination and ion-pair formation in $\mathrm{HeH^+}$ isotopologues: A time-dependent wave-packet study including rotational coupling

arXiv:2606.11352v1 Announce Type: cross Abstract: We present a comprehensive theoretical investigation of dissociative recombination (DR) and resonant ion-pair (RIP) formation in $\mathrm{HeH^+}$ isotopologues using time-dependent wave-packet propagation methods. Nuclear dynamics are treated on a set of 23 coupled electronic states, including $^2\Sigma$, $^2\Pi$, and $^2\Delta$ symmetries, in both adiabatic and strictly diabatic representations, with rotational couplings explicitly included. Reaction cross sections are computed over collision energies ranging from 0 to 50 eV. The results reveal that inclusion of a large manifold of resonant states and rotational couplings significantly enhances the DR cross section relative to earlier theoretical studies. In the diabatic representation, $^2\Sigma$ states dominate the recombination dynamics, while in the adiabatic representation, $^2\Pi$ and $^2\Delta$ states contribute significantly at low collision energies. For RIP formation, two different diabatization schemes yield systematically larger cross sections than previous models, highlighting the sensitivity of ion-pair production to electronic coupling structure. Isotopic effects are examined, showing a clear inverse dependence of cross section magnitude on reduced mass. The present results underscore the importance of multi-state coupling and nonadiabatic effects in accurately describing electron-molecule collision processes in primordial and astrophysical plasmas.

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

Multi-Grade Deep Learning for Partial Differential Equations with Applications to the Burgers Equation

arXiv:2309.07401v2 Announce Type: replace-cross Abstract: Deep neural networks (DNNs) show great promise for solving partial differential equations (PDEs), but their deep architectures introduce complex, large-scale, non-convex optimization challenges. Nonlinear PDEs, like the viscous Burgers' equation, compound these difficulties due to steep gradients and shock-like solutions. To address this, we propose a two-stage multi-grade deep learning (TS-MGDL) method. In the first stage, shallow networks are trained progressively grade by grade to fit the target function from low- to high-frequency components; previously learned grades are frozen, and each new residual block is trained solely to minimize the remaining approximation error. The second stage unfreezes and retrains selected layers using the first-stage network as initialization, achieving an interpretable, stable hierarchical refinement while mitigating optimization complexity. Furthermore, we theoretically prove that each grade and stage in TS-MGDL monotonically reduces the loss function under an appropriate optimization strategy. Numerical experiments on 1D, 2D, and 3D viscous Burgers' equations demonstrate that TS-MGDL significantly outperforms single-grade learning (SGL), reducing predictive errors by up to a factor of 60.

24.
arXiv (CS.CL) 2026-06-16

JE-IRT: A Geometric Lens on LLM Abilities through Joint Embedding Item Response Theory

Standard LLM evaluation practices compress diverse abilities into single scores, obscuring their inherently multidimensional nature. We present JE-IRT, a geometric item-response framework that embeds both LLMs and questions in a shared space. For question embeddings, the direction encodes semantics and the norm encodes difficulty, while correctness on each question is determined by the geometric interaction between the model and question embeddings. This geometry replaces a global ranking of LLMs with topical specialization and enables smooth variation across related questions. Building on this framework, our experimental results reveal that out-of-distribution behavior can be explained through directional alignment, and that larger norms consistently indicate harder questions. Moreover, JE-IRT naturally supports generalization: once the space is learned, new LLMs are added by fitting a single embedding. The learned space further reveals an LLM-internal taxonomy that only partially aligns with human-defined subject categories. We also show that simple linear probes of the embedding space recover cross-subject ability directions, such as an arithmetic axis that highlights quantitatively demanding questions in seemingly distant subjects like virology and global facts. JE-IRT thus establishes a unified and interpretable geometric lens that connects LLM abilities with the structure of questions, offering a distinctive perspective on model evaluation and generalization.

25.
arXiv (CS.CV) 2026-06-12

VideoMDM: Towards 3D Human Motion Generation From 2D Supervision

We introduce VideoMDM, a diffusion-based framework that trains 3D human motion priors directly from accurate 2D poses extracted from monocular videos, without any 3D ground truth. A pretrained 2D-to-3D lifter provides approximate 3D pose sequences that serve as a noisy teacher: these are diffused, denoised by the model in 3D, and supervised in 2D by reprojecting the prediction and comparing against accurate keypoints. We show that, under mild assumptions, a depth-weighted 2D reprojection loss is equivalent in expectation to direct 3D supervision, and we adapt standard 3D motion regularizers - velocity consistency and over-parameterized representation alignment - to this 2D setting. Unlike methods that lift 2D to 3D only at inference, VideoMDM learns a coherent 3D motion manifold during training. On HumanML3D it nearly closes the gap to fully 3D-supervised MDM (FID 0.88 vs 0.54); On real video datasets Fit3D and NBA the method learns to generate motions consistently preferred by humans, with strong quantitative results.