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) 2026-06-12

Schrödinger Symmetry in Spherically-symmetric Static Mini-superspaces with Matter Fields

arXiv:2512.13651v3 Announce Type: replace-cross Abstract: Schr\"{o}dinger symmetry has been shown to emerge in a ``fluid limit" from the full superspace to several mini-superspace models. To investigate one aspect of the robustness of this emergent symmetry, we consider two spherically-symmetric static mini-superspace models with matter fields at the classical level: (i) a Maxwell field with a cosmological constant and (ii) $n$ massless scalar fields. By developing a method based on canonical transformations, we demonstrate that for model (i), 3D Schrödinger symmetry emerges, and the solution is the (anti-)de Sitter Reissner-Nordström spacetime, and for model (ii), $(2+n)$D Schrödinger symmetry appears, and the solution is a generalized Janis-Newman-Winicour spacetime and its ``interior", a Kantowski-Sachs type closed universe. Furthermore, for the vacuum model, we find that 2D Schrödinger symmetry holds with different lapse functions and mini-superspace coordinates, suggesting the potential, yet unconfirmed, covariance of the symmetry. Finally, we propose a physical interpretation of the symmetry under the Hamiltonian constraint $H$: symmetry generators commuting with $H$ map a solution to another one, while those non-commuting with $H$ generate a new theory with the Schrödinger symmetry and the transformed configuration is a solution to the new theory. These results reinforce the robustness of the emergent Schrödinger symmetry and open new frontiers for exploring dynamics of matter and gravity.

02.
arXiv (CS.CV) 2026-06-12

TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment

Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content. However, extending these models to minute-level generation remains challenging: the limited KV-cache budget prevents the model from retaining the full history, while repeatedly conditioning on self-generated frames induces a context distribution shift that accumulates over time, leading to visual artifacts, quality degradation, and temporal drift. In this paper, we propose TetherCache, a training-free and plug-and-play cache management strategy for drift-resistant long video generation. TetherCache organizes the cache into sink, memory, and recent regions, and introduces two complementary mechanisms. First, GRAB (Gated Recall with Attention-Diversity Balancing) selects long-range memory frames using a gated score that combines attention-based relevance with temporal diversity, preserving informative yet diverse historical context under a fixed cache budget. Second, TAME (Trusted Alignment via Memory Editing) lightly edits newly recalled memory tokens by aligning their statistics to a trusted context distribution, reducing the pollution caused by drifted historical features. Built on Self-Forcing, TetherCache consistently improves long-video generation quality on VBench-Long across 30s, 60s, and 240s settings. In particular, for 240s generation, it substantially improves overall and semantic scores while reducing quality drift from 7.84 to 1.33, demonstrating its effectiveness for stable long-horizon autoregressive video diffusion.

03.
arXiv (math.PR) 2026-06-15

Mixing Times for the Facilitated Exclusion Process

arXiv:2402.18999v2 Announce Type: replace Abstract: The facilitated simple exclusion process (FEP) is a one-dimensional exclusion process with a dynamical constraint. We establish bounds on the mixing time of the FEP on the segment, with closed boundaries, and the circle. The FEP on these spaces exhibits transient states that, if the macroscopic density of particles is at least $1/2$, the process will eventually exit to reach an ergodic component. If the macroscopic density is less than $1/2$ the process will hit an absorbing state. We show that the symmetric FEP (SFEP) on the segment $\{1,\ldots,N\}$, with $k>N/2$ particles, has mixing time of order $N^{2}\log(N-k)$ and exhibits the pre-cutoff phenomenon. For the asymmetric FEP (AFEP) on the segment, we show that there exists initial conditions for which the hitting time of the ergodic component is exponentially slow in the number of holes $N-k$. In particular, when $N-k$ is large enough, the hitting time of the ergodic component determines the mixing time. For the SFEP on the circle of size $N$, and macroscopic particle density $\rho \in(1/2,1)$, we establish bounds on the mixing time of order $N^{2}\log N$ for the process restricted to its ergodic component. We also give an upper bound on the hitting time of the ergodic component of order $N^{2}\log N$ for a large class of initial conditions. The proofs rely on couplings with exclusion processes (both open and closed boundaries) via a novel lattice path (height function) construction of the FEP.

04.
Nature (Science) 2026-06-15

Nanocrystal-tailored recombination for all-perovskite tandem solar modules

Authors:

The commercialization of all-perovskite tandem solar modules is hindered by the reliance on the conventional gold-based tunnel recombination junction (TRJ)1,2. Specifically, this TRJ introduces substantial near-infrared parasitic absorption3 and suffers from interfacial instability4, limiting both photocurrent generation and operational durability. Here, we develop a solution-processed interconnecting layer based on surface-engineered indium oxide (In2O3) nanocrystals featuring high optical transparency, wherein controlled nanocrystal morphology and tailored ligand chemistry enable smooth interfacial contact and favorable energy level alignment. Critically, we introduce a phosphonic acid additive into the lead–tin (Pb–Sn) perovskite precursor, which synergistically improves the electronic contact with the In2O3 recombination layer, thereby enhancing hole extraction. In addition, the additive regulates perovskite crystallization to mitigate residual strain during film formation, ensuring high-quality large-area deposits. This coordinated interfacial and crystallization engineering strategy simultaneously enhances carrier recombination efficiency at the interconnection layer, improves carrier extraction, and promotes large-area film uniformity in all-perovskite tandems. As a result, a 65-cm2 all-perovskite tandem solar module achieves a certified power conversion efficiency of 26.2%5, with an open-circuit voltage of 2.182 V, a fill factor of 77.4%, and a short-circuit current density of 15.6 mA cm-2 in terms of averaged subcell performance, measured by Japan Electrical Safety and Environment Technology Laboratories (JET). This marks a significant advance toward scalable perovskite tandem photovoltaics.

05.
arXiv (CS.LG) 2026-06-15

Adaptive Nucleus Truncation for Long-Form Reasoning

arXiv:2606.13982v1 Announce Type: cross Abstract: Sampling plays an important role in long-form language-model reasoning. Over thousands of decoding steps, small changes in the candidate token set can compound into different reasoning trajectories, stability profiles, and final answers. Existing truncation methods such as top-$p$, min-$p$, and fixed top-$n\sigma$ sampling improve over unrestricted sampling, but they rely on fixed thresholds that cannot adapt to changes in entropy, task difficulty, training stage, or generation budget. We introduce Adaptive Nucleus Truncation Sampling (ANTS), which extends top-\(n\sigma\) sampling from a fixed decoding rule into an adaptive rollout-control mechanism for long-form generation. ANTS selects standardized neighborhoods around the maximum logit before temperature scaling, adapts the truncation width using an entropy-conditioned controller, and retains a no-truncation fallback arm to stabilize training when truncation becomes unsafe. On a 33B-total / 4B-active sparse Mixture-of-Experts reasoning model, ANTS improves average performance over percentage-based benchmarks by +1.9, +3.8, and +5.2 points at 8K, 16K, and 32K generation budgets, respectively. The strongest gains appear on instruction following and mathematical reasoning, with IFBench improving by more than 10 points at 32K and AIME 2025 improving by 7 points. Code generation reveals an important budget interaction. On Codeforces, ANTS trails the baseline at 8K, but reverses this gap and substantially improves ELO at 16K and 32K. These results suggest that sampler design should be treated not just as a decoding hyperparameter, but as part of how we stabilize and scale long-budget reasoning.

06.
PLOS Computational Biology 2026-06-18

scMagnifier: Resolving fine-grained cell subtypes via GRN-informed perturbations and consensus clustering

Authors:

by Zhenhui He, Dong Kangning Resolving fine-grained cell subtypes in single-cell RNA sequencing (scRNA-seq) data remains challenging, as their subtle transcriptional differences are often obscured by technical noise and data sparsity. Here, we present scMagnifier, a consensus clustering framework that leverages gene regulatory network (GRN)-informed in silico perturbations to amplify subtle transcriptional differences and uncover latent cell subpopulations. scMagnifier perturbs candidate transcription factors (TFs), propagates perturbation effects through cluster-specific GRNs to simulate post-perturbation expression profiles, and integrates clustering results across multiple perturbations into stable subtype assignments. Additionally, scMagnifier introduces regulatory perturbation consensus UMAP (rpcUMAP), a perturbation-aware visualization that provides clearer separation between cell subtypes and guides the selection of the optimal number of clusters. In both single-batch and multi-batch benchmarks, scMagnifier consistently improves the resolution and accuracy of fine-grained cell type identification. Notably, when integrated with spatial clustering methods such as STAGATE, scMagnifier is compatible with spatial transcriptomics workflows and effectively reveals tumor cell subtypes and their spatial organization in ovarian cancer.

07.
arXiv (CS.AI) 2026-06-11

From Consumption to Reflection: Designing Human-AI Relations for Stable Reasoning

arXiv:2606.11195v1 Announce Type: cross Abstract: Large language models (LLMs) have transformed how humans access information, but not how we reason with it. Their fluency accelerates consumption while bypassing the slow, reflective processes that underpin sound judgment. This paper introduces Relational Reflective Intelligence (RRI), an inference-time governance layer that operationalizes reflection through auditable reasoning loops. RRI operates not inside the model but around it, providing a practical structure for stable, auditable reasoning between humans and LLMs. The core premise is that LLMs inherit cognitive vulnerabilities similar to those that shape human thought: reliance on intuitive shortcuts, confusion between representation and reality, and a preference for coherence over falsification. When humans and models share these tendencies, their errors compound. We refer to this as relational drift, a failure that arises from interaction rather than from the model alone. Addressing this requires a shift from modeling relations between words to structuring relations between model outputs and human reasoning. RRI provides this missing layer through three components: the Rose-Frame, which identifies likely breakdowns in reasoning; the Architect's Pen, which introduces targeted reflection steps at critical moments; and an inference-time workflow that embeds these steps without retraining the model. Together, these elements transform human-AI interaction into a joint reasoning system with explicit checkpoints, conflict surfacing, and an auditable trail of assumptions. Rather than making machines think like humans or forcing humans to reason like machines, RRI creates a structured interaction in which both compensate for each other's limitations. It reframes AI safety as a cognitive architecture problem, where reliable decisions depend on embedding reflection directly into the interaction process.

08.
arXiv (quant-ph) 2026-06-19

Vine Codes: Low-Overhead Quantum LDPC Codes on a Planar Square Grid

arXiv:2606.20263v1 Announce Type: new Abstract: The surface code is a promising route towards large-scale quantum computing, requiring only nearest-neighbour gates amenable to superconducting hardware. However, surface codes incur large qubit overheads. Novel quantum low-density parity check (qLDPC) codes promise to reduce overheads but require long-range connections that are difficult to achieve on superconducting platforms. Here, we introduce "Vine Codes" - qLDPC codes that are implementable on a planar square grid through nearest-neighbour, two-qubit gates native to superconducting platforms (iSWAP and CZ). Our approach generalises "Directional Codes" recently introduced by Gehér et. al. (2025) which are constrained to a torus. In contrast, vine codes have open boundary conditions constructed with the aid of routing qubits. We perform extensive numeric searches and find promising candidate vine codes, e.g. [[121,4,6]], [[221,6,7]], and [[234,9,6]] codes. We verify the circuit distances and show that data and measure qubits required can be reduced by up to ~28% relative to the surface code at a circuit distance of 7. Even including routing qubits, vine codes require fewer total qubits than the surface code (e.g. ~18% reduction at circuit distance 10) and benefits are expected to increase at higher distances. We perform circuit-level noise simulations to demonstrate that under a realistic noise model and at a near-term noise rate of $10^{-3}$, vine codes can perform better than the surface code while using fewer qubits. We give an exhaustive list of all unique vine codes up to stabiliser-weight 9. We additionally introduce "Flip-Vine Codes" which possess single-qubit transversal Clifford gates useful for fault-tolerant logic and magic state cultivation. We furthermore construct examples of generalised open boundaries for vine codes that go beyond the familiar X/Z boundaries of the surface and tile codes.

09.
arXiv (quant-ph) 2026-06-15

Extending Covariant Fluctuation Theorems into Quantum Regime through Quasiprobability Approach

arXiv:2606.14519v1 Announce Type: cross Abstract: The covariant formulation of stochastic thermodynamics requires treating the stochastic work as a 4-vector, posing significant challenges for quantum systems due to the non-commutativity. We introduce a new quasiprobability distribution for the work 4-vector, which combines the Wigner and Margenau-Hill quasiprobabilities. This extends the covariant fluctuation theorems from classical to quantum regime. We illustrate our findings with a scalar field driven by classical particles with a generalized version of trace formula. Our work establishes a quasiprobability approach to studying relativistic quantum thermodynamics in a covariant way.

10.
arXiv (quant-ph) 2026-06-16

Optimizing resource bounds in direct fidelity estimation

arXiv:2606.16336v1 Announce Type: new Abstract: Direct fidelity estimation provides a way to estimate the fidelity between an experimentally prepared state and a desired pure target state without performing full tomography. Two influential formulations were introduced in 2011 by Flammia and Liu and by da Silva, Landon-Cardinal, and Poulin. In these protocols, the total estimation error is controlled through two distinct probabilistic steps: first, the fidelity is approximated using randomly sampled Pauli observables; second, each sampled expectation value is estimated from finitely many measurement outcomes. In this work we show that additional structural information about the noise can substantially sharpen the corresponding resource bounds. In particular, for some canonical channels the effective number of sampled Pauli settings can be reduced, leading to lower measurement cost both in the general pure-state setting and in the case of a stabilizer state. These results illustrate a broader point: worst-case confidence bounds in direct fidelity estimation can be significantly conservative when experimentally relevant structure is ignored. As a technical ingredient, we also revisit the allocation of the total accuracy and confidence budgets between the two probabilistic steps. Reformulating the analysis in terms of separate error parameters yields a constrained optimization problem whose solution lowers the average number of measurements in the general pure-state setting. Numerical simulations based on quantum circuits implemented in Qiskit illustrate both the improvement obtained under structured-noise assumptions and the conservativeness of the original worst-case bounds.

11.
Nature (Science) 2026-06-17

Spatial distribution of the proteome in the human body and in cancers

Authors:

A detailed, spatially resolved quantitative map of the human proteome is essential for a deeper understanding of human biology and disease1–4. Here we present a comprehensive human proteomic landscape, generated by profiling more than 13,000 proteins across 2,856 samples using data-independent acquisition mass spectrometry. The dataset spans 58 major tissue types, 251 specific tissue subtypes and 25 distinct carcinomas. This resource enables the depiction of spatially resolved proteome trajectories across tissue types and physiological states, including fetal, tumour, adjacent non-tumour and healthy adult tissue, thereby providing insight into both developmental processes and oncogenic progression. Furthermore, quantitative proteomics comparisons across diverse tissue types and states facilitate the indication of organ-specific toxicity, the identification of repurposable anticancer drug candidates and the prioritization of therapeutic targets for cancers. This study establishes a quantitative resource for navigating the proteome in the human body and in common cancers. A spatially resolved map of the human proteome across a variety of healthy tissues and cancers provides wide-ranging insights in developmental biology and oncology, and could aid the identification of therapeutic targets and development of treatments for cancer.

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

Stochastic-Dimension Frozen Sampled Neural Network for High-Dimensional Gross-Pitaevskii Equations on Unbounded Domains

arXiv:2604.09361v4 Announce Type: replace Abstract: This paper introduces the Stochastic-Dimension Frozen Sampled Neural Network (SD-FSNN), a novel computational framework for solving high-dimensional Gross-Pitaevskii equation (GPE) on unbounded domain. The proposed method circumvents the curse-of-dimensionality that plagues traditional discretizations and the computational bottlenecks of gradient-based neural network solvers through a synergistic combination of techniques. First, a prescribed Gaussian envelope encodes the far-field decay of the wavefunction, enabling a space-time separation where the spatial approximation is handled by a frozen, single-hidden-layer neural network with data-driven sampled features. This yields a gradient-free formalism where spatial derivatives are analytically precomputed and time-dependence is evolved via reduced ODEs. Second, a stochastic-dimension sampler provides a conditionally unbiased estimate of the spatial operator by evaluating only a small subset of spatial dimensions at each time step, essentially reducing computational and memory costs. Discrete conservation laws are also enforced, ensuring long-term stability. Extensive numerical experiments on GPE in up to 1000 dimensions demonstrate that SD-FSNN achieves significantly higher accuracy and efficiency compared to state-of-the-art methods, including PINNs, randomized feature methods, and tensor-network approaches. The results confirm that SD-FSNN effectively mitigates the Kolmogorov $n$-width barrier for frozen-basis models on structured solution manifolds.

13.
arXiv (quant-ph) 2026-06-12

Approximate quantum error correction theory of non-isometric codes

arXiv:2606.13559v1 Announce Type: new Abstract: Non-isometric encoding arises in various important contexts in quantum error correction, most notably in the finite-energy, non-ideal codewords inevitable in experimental realizations of continuous-variable codes, and holographic quantum gravity. In this work, we present a general and systematic theory of non-isometric quantum error-correcting codes. In particular, we employ the approximate quantum error correction framework to quantitatively study the fundamental limitations imposed by non-isometric encodings on the accuracy of quantum error correction and implementation of logical operations. We apply our theory to analyze GKP and tiger codes under energy constraints, and discuss the implications to holography.

14.
arXiv (CS.LG) 2026-06-11

Apertus LLM Family Expansion via Distillation and Quantization

arXiv:2605.29128v2 Announce Type: replace Abstract: The wide adoption of LLMs has led to their use in great variety of applications and scenarios, such as chatbot assistants and data annotation, creating the need for the models to satisfy certain budget and hardware constraints. This has led to the trend of LLMs being released in batches consisting of similar models of various sizes for the family of models to adhere to as wide of a range of constraints as possible. In this paper, we validate distillation and quantization as a cost-effective way to expand model families to new sizes and hardware formats. Based on the open-recipe Apertus 8B LLM, we produce Apertus-v1.1 - a distilled family of models with up to 4B parameters trained on 1.7T permissive license tokens. We demonstrate cost-efficiency and strong accuracy performance of our approach for covering large ranges of hardware and systems requirements.

15.
arXiv (CS.AI) 2026-06-11

Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning

arXiv:2606.11767v1 Announce Type: cross Abstract: Blind grasping with a dexterous hand is a crucial manipulation capability. Nevertheless, learning such tactile-only policies for real robots remains challenging due to the tactile sim-to-real gap and the limited expressiveness of sparse tactile signals. To bridge this gap, we propose a framework for tactile-only blind grasping that is deployable on a physical multi-fingered robotic hand. Our approach combines three key components. First, we introduce a Real2Sim tactile calibration pipeline that constructs a contact-calibrated digital-twin simulator capable of reproducing real tactile signals. Second, we improve the expressiveness of sparse tactile observations using a layout-aware tactile encoder, which incorporates sensor-geometry priors through self-supervised pretraining. Third, to improve generalization to unseen objects, we train object-specific reinforcement-learning experts in the calibrated simulator and aggregate their successful grasp trajectories into a tactile-conditioned Diffusion Policy. We evaluate our method on a physical LEAP Hand equipped with distributed tactile sensing across 10 seen and 10 unseen objects. The deployed policy achieves a 27\% real-world grasp success rate across all 20 objects, without real-world grasping demonstrations or visual input. Simulation ablations show that layout-aware tactile pretraining improves grasping performance, while sensing-level evaluations confirm that Real2Sim calibration increases the consistency of tactile contact events between simulation and hardware. Together, these results suggest that contact-event calibration, geometry-aware tactile representation learning, and diffusion-based policy aggregation provide an effective path toward tactile-only blind grasping on real dexterous robotic hands. Project page:Dex-Blind-Grasp.github.io.

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

Lect\=uraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

Effective personalized AI-assisted learning demands systems that can not only generate accurate learner-specific educational materials, but also dynamically adapt their instruction to diverse learners. However, existing educational agents have primarily focused on lecture content automation and simulations, which often fall short of modelling multimodal and embodied instructional methods tailored for the individual learner. To this end, we propose Lect\=uraAgents - a multi-agent framework that enables personalized learning through end-to-end adaptive embodied teaching. At its core, Lect\=uraAgents mirrors a professor-student relationship, in which a ProfessorAgent leads a collaborative team of specialized subordinate agents through research, planning, review, and embodied delivery of lecture contents that adapt to a learner's needs. The framework offers three main contributions: (1) a hierarchical multi-agent architecture for end-to-end personalized learning; (2) an adaptive embodied teaching mechanism, wherein the ProfessorAgent executes visible and pedagogically motivated teaching actions (e.g., handwrite, highlight, underline, etc.) over contents in a teaching environment; and (3) a Teaching Action-Speech Alignment (TASA) algorithm that employs salience-based heuristics and temporal semantic segmentation to generate coherent teaching action sequences aligned with learner profiles. We evaluate Lect\=uraAgents on diverse courses at high school, undergraduate, and graduate levels using sample-specific rubric-based analysis; with generated lecture materials and teaching actions assessed and validated by expert educators. Experimental results show consistent gains in lecture content quality, embodied teaching quality, assessment, and personalization over existing approaches, positioning Lect\=uraAgents as a pedagogically well-grounded framework for personalized learning at scale.

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

Physics-Informed Discovery of Yield Functions in Plasticity via Convex Neural Representations

arXiv:2606.19375v1 Announce Type: new Abstract: Identifying anisotropic yield functions remains challenging since yielding is not directly observed in full-field mechanical measurements, directional calibration can require many loading directions, and selecting an appropriate analytical form is nontrivial. This study proposes a physics-informed framework for discovering yield functions from full-field displacement data and reaction force data, without stress observations, plastic strain measurements, direct yield surface data, or a prescribed parametric yield function. The framework identifies the yield function as a mechanically constrained constitutive component inside elastoplastic stress integration, rather than through direct stress-space supervision. The yield function is represented by a convex neural network that enforces convexity and positive homogeneity of degree one while imposing the assumed tension-compression symmetry, and this neural yield function is trained with a differentiable stress update and a physics-informed force equilibrium loss across multiple loading cases. The proposed framework is validated using finite element (FE) benchmark studies with von Mises, Hill 1948, and Yld2000-2d yield functions, assessing yield contour agreement, displacement-noise sensitivity, identifiability through plastically active stress states, epistemic uncertainty, and polynomial-surrogate deployment. This study provides a mechanics-constrained pathway for discovering anisotropic yield functions from displacement and force data while keeping the identified component within the structure of elastoplastic stress integration.

18.
arXiv (math.PR) 2026-06-11

Capital Asset Pricing Model with Size Factor and Normalizing by Volatility Index

arXiv:2411.19444v5 Announce Type: replace-cross Abstract: The Capital Asset Pricing Model (CAPM) relates a well-diversified stock portfolio to a benchmark portfolio. We insert size effect in CAPM, capturing the observation that small stocks have higher risk and return than large stocks, on average. For some size-based stock portfolios, dividing their returns by the Volatility Index makes them closer to independent and normal. In this article, we combine these ideas to create a new discrete-time model, which includes volatility, relative size, and CAPM. We fit this model using real-world data, prove the long-term stability, and connect this research to Stochastic Portfolio Theory. We fill important gaps in our previous article on CAPM with the size factor.

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

Adaptive Memory Crystallization for Autonomous AI Agent Learning in Dynamic Environments

arXiv:2604.13085v2 Announce Type: replace-cross Abstract: Autonomous AI agents operating in dynamic environments face a persistent challenge: acquiring new capabilities without erasing prior knowledge. We present Adaptive Memory Crystallization (AMC), a memory architecture for progressive experience consolidation in continual reinforcement learning. AMC is conceptually inspired by the qualitative structure of synaptic tagging and capture (STC) theory, the idea that memories transition through discrete stability phases, but makes no claim to model the underlying molecular or synaptic mechanisms. AMC models memory as a continuous crystallization process in which experiences migrate from plastic to stable states according to a multi-objective utility signal. The framework introduces a three-phase memory hierarchy (Liquid–Glass–Crystal) governed by an Itô stochastic differential equation (SDE) whose population-level behavior is captured by an explicit Fokker–Planck equation admitting a closed-form Beta stationary distribution. We provide proofs of: (i) well-posedness and global convergence of the crystallization SDE to a unique Beta stationary distribution; (ii) exponential convergence of individual crystallization states to their fixed points, with explicit rates and variance bounds; and (iii) end-to-end Q-learning error bounds and matching memory-capacity lower bounds that link SDE parameters directly to agent performance. Empirical evaluation on Meta-World MT50, Atari 20-game sequential learning, and MuJoCo continual locomotion consistently shows improvements in forward transfer (+34–43\% over the strongest baseline), reductions in catastrophic forgetting (67–80\%), and a 62\% decrease in memory footprint.

20.
arXiv (CS.CL) 2026-06-19

Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings

Aligning language models with human preferences often requires optimising multiple behavioural objectives. A practical approach is to apply these objectives sequentially using preference optimisation methods such as Direct Preference Optimisation (DPO), but it remains unclear whether later training uniformly degrades preferences learned earlier or whether the effect depends on the relationship between objectives. We study sequential DPO across four preference settings covering distributional conflict, multi-attribute interaction, strong safety signal, and compatible response-quality objectives. Using Llama-3.1-8B-Instruct with LoRA adapters, we evaluate all objectives after every stage with a fixed base-model reference. We find that sequential DPO does not produce a single forgetting pattern; preference change ranges from partial degradation to stability, pair-level redistribution, or positive transfer depending on objective relationship, signal strength, and training order. Pair-level analysis using length-normalised policy margins shows that aggregate metrics can mask heterogeneous changes across preference pairs, whereas quartile decomposition reveals that high-confidence pairs can either degrade or improve depending on the setting. Mechanistic diagnostics show that Stage~2 gradients and adapter updates are near-orthogonal to the previous objective across all settings, providing little evidence that direct gradient opposition is the primary driver. These findings suggest that future sequential alignment pipelines should account for objective compatibility and signal strength, rather than assuming that later objectives affect earlier preferences uniformly.

21.
arXiv (CS.CV) 2026-06-11

SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning

Controlled character animation requires transferring motion from a driving sequence to a reference character. Prior works heavily rely on intermediate representations, including pose skeletons to represent motion or masked background to represent environment, which inevitably leads to information loss. To address this, we present SCAIL-2, a framework that bypasses those intermediates and achieves end-to-end character animation. By directly concatenating driving videos to the sequence, the model can obtain all the required visual information from the input video. To address the lack of end-to-end data, we unify sub-tasks of character animation with decoupled conditions and then curate a pipeline to synthesize MotionPair-60K, an end-to-end motion transfer dataset containing heterogeneous tasks of character animation. To achieve the unification, we utilize in-context mask conditioning and mode-specific RoPE as soft guidance beyond textual instructions and raw visual information. To address synthetic discrepancy in detailed regions, we propose Bias-Aware DPO to construct preference items to mitigate the errors. Extensive experiments demonstrate that our method substantially outperforms existing state-of-the-art approaches in various character animation tasks. A large subset of synthetic data as well as model weights will be released at our project page: https://teal024.github.io/SCAIL-2/.

22.
arXiv (CS.AI) 2026-06-16

Multiple Descents in Deep Learning as a Sequence of Order-Chaos Transitions in LSTM Networks

arXiv:2505.20030v2 Announce Type: replace-cross Abstract: We observe a novel `multiple-descent' phenomenon during the learning process of a recurrent neural network called long-short-term memory (LSTM) networks during its training on real-world task, in which the performance goes through long cycles of up and down trends multiple times after the model is overtrained. By carrying out asymptotic stability analysis of the models, we found that the cycles in performance – indicated by loss function in test data – are closely associated with the phase transition process between order and chaos of the model, and the local optimal training step are consistently at the critical transition point between the two phases. More importantly, the most optimal point of the model usually occurs at the first transition from order to chaos, where the `width' of the `edge of chaos' is often the widest, allowing the best exploration of weight configurations for learning.

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

LLM Judges Have Dark Current: A Psychometric Datasheet for LLM-as-a-Judge Evaluation

LLM-as-a-judge systems are now routinely used for open-ended model evaluation, where human preference annotation is costly, slow, and difficult to reproduce. Yet these judges are often reported as scalar accuracy, win-rate, or agreement devices. We argue that a judge should instead be reported as a measurement instrument. We introduce a Judge Datasheet protocol that measures dark current under true-vacuum inputs, stable cross-sensitivity to same-quality surface variation, positional false preference, target sensitivity on a controlled quality ladder, and the criterion or operating point induced by tie instructions. The direction-stability decomposition reveals that apparent Delta0 preference can be stable surface response or disguised position bias. In a three-judge open-weight case study, Llama-3.1-8B shows high dark current and presentation-conflicted Delta0 behavior, Qwen2.5-14B is vacuum-clean and target-sensitive but mixes stable and positional over-discrimination, and Qwen2.5-32B is vacuum-clean with low stable cross-sensitivity and low positional false preference. A strict tie criterion eliminates Qwen32B Delta0 false preference but absorbs marginal Delta1 target signals into ties while preserving Delta5 sensitivity. The results show that prompting moves the criterion, not the resolution. We do not claim that the downstream mechanism hypothesis that motivated this work is confirmed; the contribution is a metrological protocol for measuring the measuring device before downstream claims are made.

24.
arXiv (CS.AI) 2026-06-15

LEPO: Latent Reasoning Policy Optimization for Large Language Models

arXiv:2604.17892v4 Announce Type: replace-cross Abstract: Recently, latent reasoning has been introduced into large language models (LLMs) to leverage rich information within a continuous space. However, without stochastic sampling, these methods inevitably collapse to deterministic inference, failing to discover diverse reasoning paths. To bridge the gap, we inject controllable stochasticity into latent reasoning via Gumbel-Softmax, restoring LLMs' exploratory capacity and enhancing their compatibility with Reinforcement Learning (RL). Building on this, we propose \underline{L}atent R\underline{e}asoning \underline{P}olicy \underline{O}ptimization~(LEPO), a novel framework that applies RL directly to continuous latent representations. Specifically, in rollout stage, LEPO maintains stochasticity to enable diverse trajectory sampling, while in optimization stage, LEPO constructs a unified gradient estimation for both latent representations and discrete tokens. Extensive experiments show that LEPO significantly outperforms existing RL methods for discrete and latent reasoning.

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

Exposure Bias as Epistemic Underidentification in Recursive Forecasting

arXiv:2606.12990v1 Announce Type: new Abstract: Recursive multi-step forecasting is usually framed as distribution shift: models are trained on observed histories but deployed on their own predictions. We show this framing is incomplete by proving that, under partial observability or state truncation, recursive rollout is also an epistemic underidentification problem. Even with deterministic latent dynamics, one-step Bayes supervision identifies behavior only on observed contexts and need not identify the deployed recursive predictor once rollout queries self-generated induced states whose correct local targets are not determined by numeric state alone. We formalize this with induced states $Z$ and provenance variables $P$, and derive a decomposition of induced-state error into teacher-forcing/rollout mismatch, representation–class approximation, and provenance information gaps. Empirically, we show that rollout enters a distinct induced-state regime, that fixed induced states define a distinct local corrective task, and that closed-loop gains arise not only from local adaptation but also from changing the induced states visited during rollout. Using a simple binary provenance encoding, provenance-aware correction can further improve performance, though gains are conditional rather than uniform. These results recast exposure bias as reasoning under self-induced epistemic uncertainty.