Papers

Safety-aligned large language models (LLMs) remain vulnerable to adversarial prompts that bypass their safety training. Existing automated red-teaming methods either require privileged access unavailable in production, rely on manually engineered per-model templates, or optimize a single objective without population-level diversity. We present REPRO (Reflective Evolutionary Prompt Optimization), a pure black-box framework that discovers adversarial prompts through evolutionary optimization driven entirely by a compressed open-weight 7B reflective model on a single consumer GPU. REPRO introduces two mechanisms absent from prior work, both isolated in a component ablation: semantic crossover, an LLM-guided multi-parent recombination operator, and Bayesian strategy selection via Thompson Sampling informed by structured failure analysis. We catalog REPRO's behavior on AdvBench, JailbreakBench, and HarmBench across 36 target models from 11 families, including GPT-5-nano, Claude-3.5-Sonnet, Gemini-2.5-Pro, and Grok-4.1. Under our protocol REPRO reaches 100% attack success rate (ASR) on every evaluated target in a single turn, at a median of 24 target queries per behavior. Two properties of the protocol qualify that figure. The judge scoring candidates during optimization also produces the reported ASR, and search halts when it accepts, so ASR reports whether search succeeded within the iteration budget rather than success at a fixed budget. All baseline figures are transcribed from their original papers, which use different judges, budgets, and model versions. We therefore present this as a catalog of model coverage under one protocol rather than a head-to-head ranking, and develop both qualifications in the paper.

Coherent multi-shot audio-visual video generation requires maintaining consistent identities while depicting evolving states and coordinating sounds across shot boundaries. Although dense captions describe individual shots in detail, they rarely specify which entities persist, how their states change, or which entities and actions produce sounds. To address this limitation, we propose Structured Stateful Relational Scripts (SSRS), a textual supervision representation that separates persistent entity and voice identities from shot-specific visual and auditory states. SSRS explicitly encodes sound-source bindings and temporal relations, while a global audio-visual event sequence connects local actions and sounds, including events that continue across shot boundaries. We further introduce MSAV-Script-100K, a large-scale dataset of curated multi-shot audio-visual videos paired with detailed SSRS annotations, enabling models to learn identity persistence, state transitions, and event continuity from structured supervision. Experiments demonstrate improvements in cross-shot consistency, adherence to specified state changes, and audio-visual alignment, highlighting the effectiveness of our SSRS and MSAV-Script-100K for coherent multi-shot audio-visual generation. Our proposed dataset is available at \href{https://huggingface.co/datasets/shenlehan/MSAV-Script-100K}{MSAV-Script-100K}.

We show that, in ambient dimension at most seven, varifold limits of the minimizing movements scheme introduced by Almgren–Taylor–Wang and Luckhaus–Sturzenhecker are integral Brakke flows. As a consequence, we show that $L^1$-limit points of the scheme, usually known as flat flows, are generalized BV flows. The result is unconditional and, in particular, remains valid even in the absence of energy convergence and in the presence of fattening.

Non-firm connection products can accelerate grid access while reinforcements are delayed, but their planning value depends on evidence supporting the contractual promise. We develop a one-way evidence-to-access framework for calendarized products. Stage A constructs and fixes directional restriction calendars from public residual-load and day-ahead price-timing signals. Stage B audits the submitted calendar and one bounded common repair, tests joint threshold attainability under the shared annual budget, and applies an aggregation-aware Power Transfer Distribution Factor (PTDF) certificate. Stage C treats the resulting ledger as fixed in queue-aware allocation and intervention planning. In the primary policy-package evaluation, the evidence-supported menu returns the same $2.119$~GW allocation as firm-only access, whereas authorizing the uniformly derated fallback raises awards to $6.442$~GW and reduces backlog from $136.076$ to $113.601$~GW-years; all $4.489$~GW of non-firm awards use the fallback. In a target-free matched control, evidence-routed and state-blind fallback menus attain primary objectives equivalent within EUR~1 and return the same accepted applicants, award years, routes, and intervention portfolio. Thus, in the reported testbed, fallback authorization rather than calendar-specific evidence support drives the access-volume effect.

KV caches make long-context serving efficient by reusing past computation, but model switching breaks this reuse and forces the receiver to prefill the context again. We study zero-prefill cross-model context handoff: translating a sender cache into a receiver-compatible state so that the receiver can continue directly without prefilling same context. Existing affine transport methods show that receiver KV states can be substantially reconstructed from sender caches. However, through extensive analyses, we find that reconstruction fidelity is a poor proxy for receiver utility. Similar K/V reconstruction errors can lead to substantially different attention patterns, predictive distributions, and downstream accuracy, because conventional reconstruction objectives overlook the query-dependent functional importance of K and V in receiver attention. We thus introduce CACHELINK, which learns a coupled K/V correction through the receiver behavior directly. Across four independently trained sender–receiver pairs and seven evaluation panels, CACHELINK improves the equal-weight mean over all methods for every pair. In matched diagnostics, CACHELINK changes K/V squared error by less than 0.4% while substantially changing receiver attention and next-token behavior. At 32K context, it reduces handoff latency by up to $7.27\times$ relative to receiver re-prefill. Our findings verify that reconstruction fidelity alone is insufficient and that preserving the receiver computation induced by the transported cache is important for effective cross-model KV transport.

In this paper, we study phase transitions and scalar quasinormal modes(QNMs) of magnetically charged Euler–Heisenberg-dilaton AdS black holes in the extended phase space. We classify the horizon structures for all three signs of the EH coupling and derive the extended first law when the pressure and coupling are varied. For negative coupling, the physical branch exhibits a Van der Waals-like small/large black-hole transition. Using the improved asymptotic iteration method, we find two separated QNM trajectories below the critical pressure, whereas they merge into one continuous curve at the critical point. The GHS limit and the positive couplings considered here do not produce a finite-radius critical point.

In this paper, we consider the orbital stability of solitary waves for the derivative nonlinear Schrödinger equation $$iq_t+q_{xx}+i\partial_x\bigl(|q|^2q\bigr)=0, \quad (t,x)\in\mathbb{R}\times\mathbb{R}.$$ For the endpoint solitary waves satisfying $c>0$ and $c^2=4\omega$, we prove the orbital stability in $H^1(\mathbb{R})$ without any additional assumptions. The proof uses conservation of mass and the second Hamiltonian $\mathcal{H}_2$ to keep the Bäcklund-transformed solution small in $H^1(\mathbb{R})$ uniformly in time. We establish an inverse Bäcklund compactness result to reconstruct the algebraic solitary wave as the spectral zero approaches the negative real axis.

Collaborative filtering predicts user-item interactions from implicit feedback. We focus on matrix factorization (MF) trained with the Bayesian Personalized Ranking loss. This loss updates each user embedding only through that user's observed items and sampled negatives, so sparse feedback gives MF few constraints. To constrain each user through other users, we propose Pathwise Alignment for Collaborative Filtering (PACF), which trains MF with one network shared by all training pairs. At points between user and item embeddings, a flow matching term trains the network to predict the user-to-item step, reversed and scaled for sampled negatives. A trajectory consistency term pulls each user's predicted path to end at the observed item. Both terms update the embeddings, so the network is discarded after training, thereby maintaining the efficiency of MF at inference. We prove that a network with bounded sensitivity to its input point accurately fits users who share an item only if their embeddings are close, so these users constrain one another. Against eleven discriminative and generative baselines, PACF achieves the highest performance on all seven datasets. Its relative gains over MF are largest where feedback is sparsest. The shared network thus supplies the missing constraints through other users.

Federated Recommendation Systems (FedRSs) learn collaborative scores from interaction histories on device and rank items by them, so a higher score means a higher rank. Item text and images add semantic information that can reorder the list. Existing Federated Multimodal Recommenders (FedMRs) fuse this content into their models, which can obscure how content reorders the list. We therefore propose the SEmantic Residual Adapter (SERA), which keeps content out of an existing FedRS and adds semantic residual scores to its collaborative scores. Content can then lift an item above another only when its semantic residual score exceeds the other's by more than their collaborative score gap. This score grows with the item's content similarity to the user's interaction history and is capped at a residual bound. We prove that for any content, an item can enter the list only if its collaborative score is within twice this bound of the lowest one in the list. A larger bound lets content lift more items, including irrelevant ones, so the bound trades off how far content reaches against accuracy. With a validated bound, SERA improves all three FedRSs on all six datasets without adding personalized parameters. It outperforms FedMRs in most comparisons and lifts some FedRSs above centralized baselines.

We study isomorphic embeddings into Musielak-Orlicz sequence spaces \(\ell_\Phi\), where the normalized generating sequence \(\Phi=\{\phi_n\}\) satisfies the \(\delta_2\) condition. Using admissible normalized blocks, we construct an associated limiting family \(\mathcal C_{\Phi,\tau}\) of Orlicz functions. If a Banach space \(X\) with a symmetric basis embeds into \(\ell_\Phi\), then there is a function \(\psi\in\mathcal C_{\Phi,\tau}\) such that the basis of \(X\) is equivalent to the canonical basis of \(\ell_\psi\). An Orlicz sequence space \(\ell_\psi\) embeds if and only if \(\psi\) is equivalent near zero to a member of \(\mathcal C_{\Phi,\tau}\); in particular, \(\ell^p\) embeds exactly when such a member is equivalent to \(t^p\). Assuming differentiability of the generators on a common interval near zero, we also derive the necessary bound \(p\leq b_{\Phi,(c_n),\delta}\), where the upper growth index incorporates the summable errors in the \(\delta_2\) condition. The same index yields cotype \(q\) for every \(q\geq2\) with \(q>b_{\Phi,(c_n),\delta}\). Examples with nonuniform growth and lacunary weights illustrate this bound. For alternating Nakano exponents, the explicit limiting family gives a sharper restriction than the index alone. For general Nakano exponents, we recover the known exact cotype criterion, including attainment of the optimal exponent. For weighted Orlicz spaces, we express the cotype criterion through summable scalar errors and recover the formula using the global upper growth index when \(w\in\mathcal A\).

This Article critically examines the contemporary regulatory framework and discourse surrounding data portability in the United States. Using recent regulatory developments in the European Union as an illustration, this Article suggests that although data access and portability are identified as vital issues in multiple policy instruments, in its current iteration, at least, legal conceptions of portability continue to reinforce the interests of service providers and data controller enterprises rather than individual end users. This Article argues that a paradigm shift toward a more human-centric data approach to data governance must occur, under which data would be recognized as fundamental to an individual's identity in a digital age. Therefore, it should be placed in the hands of individuals rather than service providers or data controller enterprises. This Article considers technical and market trends in the European Union that reveal and facilitate such a change. It suggests that regulatory frameworks should better align with these technological and market developments to encourage change-inducing trends among market actors. In short, this Article identifies a transformative approach to data portability that empowers individuals with the freedom and ability to aggregate their data in secure personal spaces under their control or dominion. Such a human-centric perspective on data portability is crucial in building Artificial Intelligence (AI)-powered applications for individual consumers that can pave the way for the human-centric, AI-driven data ecosystems of the future.

Android agents read content from applications and web pages and act on it with the user's authority, yet they cannot reliably tell where that content came from – its source, the application or document that supplied it. The WebView accessibility fields we inspected expose the host application but omit the document origins available inside the browser, so an agent reading through this interface cannot check which document supplied an object; a limited reproduction on an unmodified WebView yields the same finding. We build and separately evaluate two prototypes to examine how source information supports authorization. Our application-source monitor withholds side-effecting calls whose signed source record contains an untrusted application. With the source set derived from the OS accessibility log, it blocked every selected attack write in the tested runs, but it also withheld benign sends issued after reading untrusted content, flagged benign tasks that use external content, and carried source records into a later clean task. Our WebView source-reference gate uses records from a modified browser to check object origins and reference lifetime through direct calls; in a separate 24-trial evaluation, the live agent selected no disallowed object. Supporting benchmark and planner measurements characterize textual argument matches and attacker-target selection, without establishing causal dataflow or a controlled model ranking. The prototypes are not an integrated defense: the WebView gate still lacks authenticated browser delivery and atomic capture of selected bytes and origin. Together, the results show which source information the tested policies need and why it must stay linked to the object used in execution.

Large language models make decisions through parallel prefill and sequential decoding. Although effective, this approach incurs decoding costs and does not explicitly expose decision probabilities. Existing task-specific classifiers require per-task training and offer limited generalization to unseen decision schemas. We propose Large Decision Models (LDMs), repurposing language models to return explicit probabilities over labels specified at run time using one prefill forward pass. We first adapt models to this interface through Diverse Decision Supervision (DDS), covering varied domains, rules and labels. To further narrow the performance gap to a reasoning model, Self-Posed Reasoning Distillation (SPRD) adds tasks generated by a frozen teacher, filters them for answer consistency, and trains on label distributions obtained from repeated teacher reasoning. We evaluate on DecisionVista, pairing new-schema tests with held-out human-labelled sources. Across three base models, the recipe improves accuracy over a step-matched baseline by 1.8 and 1.5 percentage points, respectively, achieving a 182-fold speedup in latency over reasoning rollout on Gemma-4-31B. Reasoning remains stronger on the new-schema test, motivating a confidence router for uncertain decisions. On development sets, routing recovers a median 92% of reasoning's accuracy advantage while generating 27-58% of its tokens. Code is available at https://github.com/JianhuiWei7/LDM.

In 2022 Dassow and Jecker started investigations on the operational complexity of the pumping constant w.r.t.~two pumping lemmata. Since then, the research on pumping lemmata emerged to several variants for regular as well as context-free languages. Within this work, we further investigate the witnesses of regular languages (firstly introduced by Rauch) w.r.t.~different pumping lemmata: For a language $L$ and a minimal pumping constant $K$, a witness of a language is a word that cannot be pumped by $K$ w.r.t.~the given pumping lemma. Here, the pumping constant is minimal if for all smaller numbers, the pumping lemma condition is not satisfied. Alongside combinatorial investigations on (unary) witness languages, we introduce and study the measure of scattered factor distance, which is related to minimal pumping constants. We present bounds on minimal pumping constants by the scattered factor distance and show that deciding, given two regular languages, whether one of them is equal to the witness language of the second is \coNP-complete.

Digital technologies can preserve records of wrongdoing indefinitely, and AI can give those records continuing influence over a person's future. We describe this condition as the eternal data present and argue that it threatens the possibility of forgiveness. In criminal justice, formal punishment has an end, whereas the harms caused by the continued use of criminal records may not. Drawing on Hegel's account of the "hard heart" and Arendt's account of the irreversibility of action, we distinguish two dangers that digital systems can combine. People may be permanently identified with what they have done, and acts that cannot be undone may continue to determine what happens to them. We propose a right to remain unfinished, supported by rights to limits on the weight given to older records, to re-evaluation in light of personal change, to reassessment of inferences that affect their lives, and to time limits on the use of records in specified decisions. These proposals extend the ethics of AI beyond accuracy, transparency, and non-discrimination to address how long past wrongdoing should be allowed to govern a person's life.

The theoretical elegance of Support Vector Machines (SVMs), grounded in statistical learning theory, establishes them as a reference for robust classification. However, in the era of Big Data, classical SVMs face two major bottlenecks: the prohibitive cubic complexity $\mathcal{O}(N^3)$ of training and the rigidity of static kernels. Traditional methodologies treat kernel selection as a discrete, "brute-force" GridSearch problem, effectively decoupling the learning of data representation from the optimization of the decision boundary. This paper proposes a paradigm shift with a so-called "Revisited SVM", a unified framework that recasts the learning process as a continuous %bi-level joint optimization problem. We derive a novel objective function $J(\alpha, \theta)$ that allows for the simultaneous optimization of dual Lagrange multipliers and kernel hyper-parameters. To solve this challenging non-convex problem efficiently, we introduce a hybrid Block Coordinate Ascent (BCA) algorithm, tightly integrated with Nyström-based low-rank approximation, which drastically reduces computational complexity to $\mathcal{O}(Nm)$. Extensive experiments conducted across four heterogeneous domains (Bioinformatics, Finance, Cybersecurity, and Computer Vision) demonstrate that our approach not only matches but often exceeds exhaustive GridSearch accuracy, while delivering training speedups of up to 100x. Notably, on the complex NSL-KDD intrusion detection dataset, our adaptive kernel approach achieves 96.25% accuracy compared to a mere 50% for standard baselines, proving its unique ability to model complex non-linear manifolds in high-dimensional spaces. We validate our results using rigorous statistical tests and provide a theoretical convergence analysis of the proposed algorithm.

Let $F(z)=zf(z)$, where $f$ is a normalized scalar holomorphic function on the unit ball $\mathbb B$ of a complex Banach space $X$ or on the unit polydisk $\mathbb U^n$ of $\mathbb{C}^n$. We establish sharp bounds for two Toeplitz determinants involving the second, third and fourth Fréchet derivatives of $F$ when $F$ is starlike of order $\alpha$, $0\leq\alpha<1$. The first bound is sharp for the full range $0\leq\alpha<1$, while the second is sharp for $0\leq\alpha\leq 2/3$. The extremal mappings are explicitly identified, confirming the sharpness of the estimates.

Concepts are the basic units through which we navigate the world and communicate meaning. But do you and I really mean the same thing when we think or speak about a concept? The present study develops a measurement framework for modeling and analyzing interindividual variation in concept representations through sentence embeddings, dense vector representations mapping entire utterances into a shared geometric space. The framework is developed in a theoretical argument and validated, demonstrated, and subjected to robustness checks in a pre-registered study. Short personal definitions, elicited from $N = 125$ participants, are encoded as sentence embeddings and submitted pairwise to a crossed random effects model yielding two concept-level quantities: sharedness ($S_b$), the expected dissimilarity between two randomly drawn individuals, and idiosyncrasy ($I_b$), the person-specific share of total dyadic variance. Two validity tests support the approach: the embedding space fully recovers concept and domain organization from participant definitions even with the target word excluded, and a parameter-free classifier achieves 0.630 accuracy in a within-participant extensional prediction task against a chance baseline of 0.500 and a consistency ceiling of 0.893. The framework finds theoretically interpretable variation in $S_b$ and establishes $I_b$ as a reliable source of dyadic variance across concepts. Results replicate across three encoders varying in architecture and capacity, providing a reproducible and scalable instrument for the empirical study of meaning variation.

Rabin games have their roots in Michael Rabin's seminal work on automata over infinite trees and form a classical model for infinite-round games with ω-regular winning conditions. They play a central role in automata theory and temporal synthesis: translating an LTL specification into an equivalent deterministic Rabin automaton reduces synthesis to solving a Rabin game. In practice, however, Rabin games are typically solved indirectly, via parity games. One possible reason is that many direct algorithms have a factorial dependence on the Rabin index k, the number of Rabin pairs. In this work, we revisit Rabin's 1972 recursive algorithm. The algorithm is implicit in Rabin's proof and intertwined with finite-state determinacy. First, we "excavate" it as an explicit arena-based solver using standard reachability- and Büchi-game solving as basic building blocks, thus avoiding the exponential dependence on the alphabet in Rabin's original presentation. Second, we show that memoization removes the factorial term from the recursion-tree analysis. Finally, we introduce a variation that recurses on the Rabin index. These results provide a modern analysis of Rabin's recursive method and a basis for studying direct Rabin-game solvers for temporal synthesis.

Radio frequency fingerprinting aims to identify transmitters by exploiting small differences in the emitted signal waveform. Common approaches exploit hardware-dependent imperfections for that purpose. This work instead investigates whether differences between digital signal processing implementations of a transmitter can be identified from their radiated signals. As a practical case study, five different software-based DSP implementations for generating a 2-FSK RTTY communication waveform are considered. In a monitoring receiver, a classifier can identify these DSP implementations using convolutional neural networks that are trained on augmented software-generated signals represented as raw IQ, power spectrum or instantaneous frequency. The trained networks are evaluated on over-the-air recordings obtained using a shortwave transceiver and a software-defined radio receiver. The best neural network combines IQ and the power spectrum representation and achieves an accuracy of up to 90%. The study further examines the influence of the signal SNR and the observation bandwidth on the classification accuracy. The results demonstrate that DSP implementations leave distinguishable characteristics in the transmitted signals and suggest that DSP-dependent fingerprinting can provide complementary information for specific emitter identification systems.

The recent observation of an excess near the kinematic $t\bar{t}$ production threshold by the CMS and ATLAS collaborations suggests the existence of a color-singlet and $S$-wave quasi-bound state of top quark. Due to the non-relativistic nature of top and anti-top quarks in this threshold region, toponium production provides an ideal system to probe the anomalous dipole moments of the top quark. In this work, we investigate the impact of chromo-electric dipole moment (CEDM) in $t\bar{t}$-gluon vertex on toponium production at the LHC. We implement the enhanced near-threshold production of the spin-0 color-singlet toponium state $\eta_t$ via gluon fusion. The resonant toponium contribution is then combined with the continuum $t\bar{t}$ production amplitude, including the interference effects induced by the top CEDM. Furthermore, we construct a set of asymmetries based on the angular distributions of charged leptons in the leptonic decay channel of $t\bar{t}$. Finally, we derive the expected exclusion limit on the top quark CEDM parameter $d_t^g$ using these lepton angular asymmetries.

Skill internalization aims to convert externally specified procedural skills into persistent model capabilities, allowing language-model agents to execute them without retrieving or reinjecting skill descriptions at inference time. Yet when new skills are learned continually, whether previously internalized skills remain usable is still poorly understood. We study forgetting in continual skill internalization and uncover a clear hierarchical structure. Early in subsequent training, a model may lose the ability to invoke an old skill from the raw request, while supplying only the correct canonical skill name substantially restores the learned behavior; with further optimization, this conditional execution also degrades. We call these two stages skill-addressing forgetting and skill-execution forgetting. Guided by this finding, we introduce Factorized Skill Memory (FSM), which separates continual skill memory into a plastic Address Memory and a stable Execution Memory. At each stage, FSM trains a new LoRA executor using only current-stage data, freezes it after acquisition, and appends it to Execution Memory; in parallel, Address Memory incrementally learns to map current requests to executors without replaying historical requests or execution trajectories. At inference time, Address Memory selects one executor from the raw request, and only that frozen executor performs a single language-model generation. On a five-stage benchmark built from 100 TaskBench skills, FSM achieves 65.95% mean exact match and 93.38% addressing accuracy across two task orders, improving over the strongest replay-free parameter-isolation baseline by 14.3 percentage points while remaining within 1.9 points of Replay, which retains historical training examples.

Active debris removal requires a servicer spacecraft to approach a non-cooperative tumbling object, capture it, and arrest its rotation. This sequence is conventionally divided among phase-specific controllers, each depending on knowledge of the target's inertia, a dedicated grappling fixture, or a hand-designed switch at the contact-rich seam where such pipelines are most fragile. We show that a single constrained reinforcement learning policy can execute the entire mission, driving a dual-arm free-flying servicer from free-space closing through friction-based fixture-free capture to full detumbling of a target whose mass and inertia are unknown and whose state is observed only through noisy estimates. The enabling mechanism is a smooth proximity gate applied at three loci of a constrained Markov decision process. In the reward it induces the phase structure rather than imposing it; in the action space it forecloses a degenerate grab-and-pull exploit as a hard guarantee; and in the constraint set it resolves a normalization failure of constraint-based learning, in which a constraint spanning phases that load it unequally is rendered nearly inert in the phase where precision matters most. Both the failure mode and the remedy apply to any multi-phase problem of this kind. Over 1000 randomized trials the policy succeeds in 99.5% while holding its contact-force, actuator, base-reaction and collision limits throughout, transfers zero-shot to unseen geometries and centre-of-mass offsets, and extrapolates across a tenfold range of target mass.

Designing a massive multiple-input multiple-output (MIMO) detector that is tailored to each specific deployment site can improve detection performance, yet most existing detectors, including deep-unfolding methods, adapt mainly within human-prescribed algorithmic structures. This letter proposes SiteEvo, a site-adaptive agentic discovery framework that extends adaptation from parameter tuning to detector-algorithm discovery. Rather than selecting or recombining predefined architectures, the large language model (LLM) agent synthesizes complete executable detector programs under a common design contract by combining its pretrained communication knowledge, site-specific wireless evidence, and experience accumulated during the search. Each proposal defines its own processing structure and trainable parameterization, and the parameters are optimized by a communication-system backend. The resulting high-performance detector is further structurally refined to reduce block-level computational cost under a bit error rate (BER)-preservation constraint and is finally frozen for deployment without online LLM inference. Simulations across three sites demonstrate BER reductions by factors of 2.6 to 6.0 over the best-performing competing detector at each site at 6 dB, while structural refinement reduces block-level computational cost by 16.7-34.1% under a validation-BER constraint.

We complete the classification of hypersurfaces with constant sectional curvature of dimension greater than or equal to three in the product of two space forms.

Formulaic alpha mining seeks interpretable expressions that rank assets by future returns. The task is challenging because it demands simultaneous processing of unstructured market descriptions, historical data, and quantitative evaluation of candidate factors, yet most existing methods exploit only a subset of these signals. We introduce AlphaPilot, a reinforcement-learning framework that trains multi-turn tool-using LLM agents for adaptive alpha mining. The agent conditions on market descriptions, proposes factor expressions, queries real-data evaluator feedback, and updates a retained factor pool across turns. This design jointly leverages market text, LLM financial knowledge, real data, and evaluation feedback. At inference time, AlphaPilot performs day-by-day search and pool updates to adapt to shifting market regimes. Across three independent runs in out-of-sample rolling backtests on CSI300 and CSI500, AlphaPilot achieves mean total returns of 42.93% and 54.19%, with mean Sharpe ratios of 2.46 and 2.86, respectively. It attains the highest mean total return, Sharpe, and RankIC among the evaluated methods on both universes.

Let k be a field and X be a geometrically rational variety over k. We investigate the Kontsevich moduli spaces of genus zero, stable maps with curve classes of low degree on X over k, and define their twisted Galois descents. We study the k-rationality of these spaces in detail when X is a projective space/Severi Brauer variety and when X is moduli of genus zero n-marked points. When X is a homogeneous variety over the field of complex numbers, this is a well-known theorem of Kim-Pandharipande.

Robotic systems for lunar surface operations must act autonomously and preserve their own integrity in an environment where failures are unrecoverable and continuous supervision is impossible. This paper presents a Constrained Reinforcement Learning framework for quadrupedal mobile manipulators that learns a single whole-body policy for tracking a 6D end-effector pose specified in task space, with operational limits enforced during learning through a constrained learning mechanism. We introduce a reward formulation in which the transition between locomotion and manipulation emerges from the reward geometry rather than from an explicit gating mechanism, a stability term derived from the Gravito-Inertial Inclination Margin and motivated by the reduced-gravity dynamics of the lunar surface, and a design rule for reward regularization that follows from the multiplicative structure of the termination-based objective. The framework is evaluated in a lunar-analog simulation spanning three terrain morphologies at five difficulty levels under lunar gravity, with regolith contact properties calibrated to the JSC-1a simulant and varied from loose to dense. The learned policy attains mean position and orientation errors of 3.22 cm and 6.83 deg. under nominal conditions, retains this precision across regolith densities and over the operationally representative range of terrain difficulty, and reduces soft-constraint violation time by up to an order of magnitude relative to an unconstrained baseline while incurring no hard-constraint violations.

Let $\{f_i(x)=M_ix+a_i\}_{i\in I}$ be an affine iterated function system on $\mathbb{R}^d$ with attractor $\Lambda$, and let $\mu$ be an associated self-affine measure. Assume that the $M_i$ generate a Zariski dense subgroup of $\mathrm{GL}_d(\mathbb{R})$. Under the strong open set condition, we show that $\dim_{\mathrm{H}}\Lambda$ equals the affinity dimension and that $\dim_{\mathrm{H}}\mu$ equals the Lyapunov dimension. The above results are consequences of the following projection theorem, which requires no separation condition. For every $1\leq n\leq d$ and for Furstenberg measure a.e. $(d-n)$-dimensional subspace $V$, \[ \dim_{\mathrm{H}} (P^V)_*\mu=\min\{n,\,\dim_{\mathrm{H}}\mu\}. \] This projection theorem in fact holds under hypotheses weaker than Zariski density: simplicity of the Lyapunov spectrum and a mild transversality condition (the Oseledets non-concentration property). The source of dimension increment in our proof is the positive dimension of the fiberwise conditional measures, exploited through Wu's one-dimensional entropy increase theorem. A key ingredient in reducing the higher-dimensional problem to this setting is a new structural result: a slab-filling property of the measure.

Multimodal recommender systems effectively alleviate data sparsity and cold-start problems by integrating heterogeneous information, yet complex cross-modal representations and model decision-making processes also introduce new interpretability challenges. Despite the rapid growth of research on the interpretability of multimodal recommendation in recent years, relevant methods and evaluation criteria remain relatively fragmented, lacking a unified conceptual framework. To address this gap, this paper categorizes existing methods into modality explanation and post-hoc explanation based on the timing and manner of explanation generation, and further constructs a progressive system for each category. Building on this foundation, this paper synthesizes four categories of evaluation metrics from both objective quantitative and subjective perceptual perspectives, and reviews relevant datasets along the dimensions of application domain and data source. Through a comprehensive analysis of existing research, we further propose future research directions. This paper aims to establish a unified analytical perspective across multimodal representation, recommendation decision-making, and user preferences, providing a research foundation for building transparent and trustworthy multimodal recommender systems.