Papers

Suppose we are given an ordered sequence of independent data whose distribution changes $K$ times at unknown locations, for some unknown $K \geq 0$. In this paper, we study the problem of performing distribution-free inference on $K$. First, we show an impossibility result: any distribution-free upper confidence bound on $K$ must be trivial and uninformative. Then, using conformal $p$-values, and under only the assumption that the data segments induced by the changepoints are exchangeable (within themselves) and mutually independent, we construct a finite-sample valid lower confidence bound on $K$, which we call the Conformal LOwer bound on Changepoint Count (CLOCC). We show that CLOCC is the only feasible way to provide a lower bound on $K$ under the stated assumptions, a property we refer to as its universality. We provide practical guidelines for choosing score functions that yield efficient and tight lower bounds. We evaluate CLOCC in several synthetic and real-data experiments, where it provides informative lower bounds on $K$, demonstrating its practical applicability.

We study a resource-efficient approach for implementing logical fanout operations in fault-tolerant distributed quantum computing using transversal operations on quantum error-correcting code blocks. Logical fanout, comprising multiple controlled-NOT operations from a common control qubit to target qubits located at remote nodes, is an important primitive for distributed quantum computation but can require substantial non-local communication when implemented directly between encoded blocks. We exploit the structure of encoded blocks and the availability of transversal logical operations to construct distributed fanout circuits that reduce the required non-local operations while preserving the logical action of the fanout operation. The construction is developed for encoded quantum information and illustrated using Bivariate Bicycle (BB)-code blocks. We analyze the resulting physical gate, entanglement, circuit-depth, and ancilla requirements. The approach provides a systematic method for implementing large logical fanout operations across distributed error-corrected quantum processors. Also, we study a distributed implementation of the global gate GCZ involving logical qubits (encoded using BB-code blocks), exploiting the concurrency in transversal distributed fanouts.

Detailed routing remains a dominant runtime bottleneck in physical design due to increasing complexity of design rules. Modern routers can struggle to resolve persistent violations under dense operating conditions. While recent work leverages reinforcement learning (RL) to dynamically select costs for each routing iteration, we find that this technique struggles with high-density designs where routing solutions are significantly harder. To address this, we present a history-aware offline RL policy which predicts iterative cost weights in these dense regimes to improve convergence across placement densities by utilizing readily available features from the router. Our policy uses conservative Q-learning similarly to prior work; however, our key insight is that addition of a lightweight LSTM architecture and additional features can retain sequence context and improve routing convergence across multiple densities and route guide qualities. Our policy can be integrated into any cost-based router with minimal pipeline changes, as it does not interfere with the core search algorithm. We evaluate our policy on held-out density and adjustment settings, including difficult operating points induced by dense placement and low guide quality. Our policy reduces design rule violations (DRVs) by an average of 92% over the top public baseline while simultaneously reducing runtime by 10%.

Distributed-tensor systems specify where values reside, while collective systems optimize how requested operations execute. At a boundary between vendor runtimes that cannot share a native communicator, neither abstraction states what a remote consumer must observe. SemBridge fills this gap by compiling graph and runtime facts into a typed contract for the consumer-visible result and its delivery obligations. The contract captures provenance, substitutability, completion, authority, demand, and native-domain locality. A deterministic lowerer constructs backend-neutral communication plans, and a symbolic checker validates each plan before execution across CUDA/NCCL and CANN/HCCL. An independent layout-only planner handles all 72 structural transitions but establishes only 54 complete obligations; a byte-only minimizer proposes 40 semantically invalid candidates, all rejected by SemBridge. On nine real edges, SemBridge produces distinct observation-aware plans that reduce startups on all nine and payload bytes on the three result edges. A live CUDA/CANN run derives and executes full-logit reconstruction, source projection, and owner-token delivery from log-probability, token-only, and owner-scoped requests. On a measured two-host 1-GbE capacity-spillover deployment, source projection cuts result traffic by more than 99.97% and increases throughput by 8.92-80.20% across Dense, MoE, and MiniMax workloads. All 18 MiniMax restart pairs at concurrency 1, 8, and 16 favor source projection. A Qwen3-14B MLP slice additionally verifies bitwise activation-shard delivery and HCCL completion of row-parallel partials. These results establish consumer observation as a semantic layer between placement and collective execution.

Chunk-autoregressive video world models typically generate each chunk under one action. When an action changes during sampling, waiting until the next chunk delays the response, while directly switching the conditioning leaves the intermediate solver state shaped by the previous action. Restarting sampling under the revised action avoids this mismatch but repeats completed computation. We introduce ActionSplice, which edits the interrupted state through Counterfactual State Transport (CST). A lightweight corrector moves the interrupted solver state toward the matched counterfactual solver state induced by the revised action at the same solver step. The world model and sampler remain frozen, and sampling resumes without replaying completed evaluations. $\mathrm{CST}_{R}$ retargets the entire active chunk, while $\mathrm{CST}_{T}$ preserves the temporal prefix at the intervention step and corrects only the suffix. On minWM–Wan Action2V and HY-WM1.5, we measure fidelity against matched rollback references. Relative to condition swapping, $\mathrm{CST}_{R}$ reduces LPIPS by 61.5% and 75.9%, and $\mathrm{CST}_{T}$ reduces suffix LPIPS by 56.1% and 77.5%, respectively.

Source-to-observation operators provide reusable environment-level descriptions for multi-query electromagnetic (EM) prediction and communication-mode analysis. However, in practical multiple-scattering models, these operators are represented with finitely many angular modes, and agreement for selected excitations or between successive truncation orders does not establish uniform accuracy of the full map or reliability of its singular channels. To close this gap, we formulate the environment-induced response as a scattering Green operator on fixed continuous source and observation spaces and derive an exact trace-space factorization that reconstructs the Maxwell scattered field. For fixed, pairwise-disjoint enclosing trace spheres and a well-posed collective problem, nested vector spherical wave function (VSWF) realizations converge in operator norm. A structural bound separates external modal tails from collective-resolvent sensitivity, and operator-norm convergence guarantees uniform convergence of the singular values. We further construct a finite metric core that preserves the nonzero singular values of each finite-order operator and reconstructs matched orthonormal source–field channels without introducing external-support discretization degrees of freedom (DoF) into the spectral problem. Full-wave benchmarks verify the finite-order implementation. A controlled near-resonant two-sphere study shows that adjacent-order agreement can precede resolution of the dominant high-order collective direction. It further shows that only part of the internal amplification appears in externally accessible gains and that resonance promotes a distinct high-order channel pair above an otherwise preserved low-order family. The resulting framework provides a convergent, metric-consistent finite-modal representation of multiple-scattering source-to-observation operators and their accessible channels.

LLM agents use large libraries of reusable skills. At thousands of skill entries, retrieval becomes the bottleneck. Graph-of-Skills (GoS) retrieves dependency-aware bundles from a typed skill graph, and SkillDAG shows that such a graph can accumulate execution-backed structure online. Neither asks whether execution traces can be distilled into a better retrieval graph that generalizes to unseen tasks. We present Self-Evolving Graph-of-Skills (SE-GoS), which treats the retrieval graph as an index rather than a learned representation: the graph is maintained from execution traces while the retrieval pipeline, the skill library, and the model stay fixed. SE-GoS applies three updates: (1) topology, which induces relations from execution evidence and retracts an avoid edge only after repeated successful co-use; (2) edge-weight, which softly attenuates unsupported semantic edges and reinforces incoming edges to used skills; and (3) node-description, which updates retrieval-facing descriptions stored on graph nodes ranked too low. On SkillsBench, one evolution round lifts average reward from 52.4% to 59.4%, above full-library loading, vector retrieval, static GoS, and SkillDAG, and this ordering repeats on all three backbones. Retrieval over the evolved graph spends about two-thirds of the input tokens that loading the full library costs. Repeating the round does not help. The same graph improves a held-out split it never saw from 52.9% to 58.3%, so what it accumulates transfers rather than memorizes traces. Skill graphs can therefore be improved from execution experience without model training, retrieval-algorithm changes, skill-content modifications, or a model judging which skills are related.

Temporal graph learning models the evolution of dynamic systems, where both structural interactions and semantic states change over time. However, existing benchmarks primarily emphasize structural evolution via temporal link prediction (TLP), while support for semantic evolution remains limited. Although temporal node classification (TNC) is sometimes included, it is typically restricted to simplistic binary settings that fail to capture realistic semantic drift. Moreover, commonly used datasets exhibit high link repetition, leading to inflated performance estimates and obscuring true model capability. To address these limitations, we introduce TTGBench, a new benchmark that jointly evaluates structural and semantic evolution. TTGBench comprises six real-world, text-rich datasets characterized by Dual Volatility, enabling rigorous and fair evaluation of existing models. Notably, it is the first benchmark to support both multi-class and multi-label TNC, filling a critical gap in evaluating temporal semantic drift. We conduct a comprehensive evaluation of 17 state-of-the-art methods across Temporal Graph Neural Networks (TGNNs) and Large Language Model (LLM)-based paradigms. The results reveal a clear capability divide between the two paradigms: TGNN-based methods excel at structural prediction but fail at semantic tracking, whereas LLM-based predictors show the opposite trend. Through in-depth analysis, we uncover their fundamental limitations and provide insights for developing more comprehensive temporal graph models.

Intermediate representations are key to bridging the modality gap between generalizable manipulation policies and large-scale pretrained vision-language models (VLMs). Among these, trajectory-based representations compactly represent motion-relevant cues, yet most existing approaches predict trajectories in 2D image space, resulting in intrinsic 3D ambiguity. Moreover, using 2D trajectories with depth still leaves the free-space waypoints ambiguous, limiting reliable 3D reasoning. To address this, we propose predicting 3D consistent waypoints (3DWay) from multi-view images. By reformulating 3D waypoints prediction as generating multi-view consistent 2D waypoints followed by geometric triangulation, we enable explicit 3D motion specification while preserving the strong priors of pretrained VLMs. The predicted waypoints can guide existing VLA models for better generalization or be directly executed on simple tasks. Extensive experiments show that 3DWay substantially improves 3D spatial grounding and vision-language reasoning, demonstrating strong potential for generalizable robot manipulation. Codes will be released at https://github.com/ziqin-h/3DWay.

Micro-actions are subtle, low-intensity non-verbal behaviors that provide cues to fine-grained human states, including emotions and intentions. Recognizing them remains difficult because they are brief, contain weak visual changes, and often exhibit similar motion patterns across categories. This paper addresses these challenges with a fine-grained micro-action recognition method that combines full fine-tuning of InternVideo2.5, hierarchical soft fusion, and a lightweight candidate-label reranker. For the long-tailed label distribution in MA-52, we use class-balanced sampling and inverse-frequency reweighting to reduce the effect of frequent classes during training. We fine-tune InternVideo2.5 end to end and attach coarse and group-conditional fine-grained classification heads to the shared video representation, improving the consistency between coarse and fine predictions. For ambiguous samples, the candidate-label reranker uses hard samples and video-label matching to focus on easily confused fine-grained actions. Experiments validate the proposed method, which achieves a 79.99% F1-mean on MA-52 and ranks first in the 3rd Micro-Action Analysis Grand Challenge at ACM Multimedia 2026.

Large language models (LLMs) have recently emerged as a promising tool for automating robot design from high-level specifications, yet they remain ineffective for robots operating under complex physical interactions. This limitation stems from the gap between language-based reasoning and the physical consequences of embodiment, often resulting in designs with low physical validity. In this work, we propose a multi-layered framework, AID-SR, that establishes a closed loop by translating simulator-observed physical states into structured feedback for the LLM designer. Combined with semantic critique, human feedback, and iterative refinement, the framework promotes the generation of physically feasible and functionally meaningful robot designs. We evaluate our approach on tendon-driven continuum robots across a benchmark of 14 tasks spanning reaching, grasping, locomotion, and manipulation. The proposed framework achieves 96.2% rate for passing the simulation feasibility check and by applying a common reinforcement learning training, 26.7% robots can successfully fulfill the corresponding task. We then fabricate three designed robots of AID-SR that successfully complete the task in real-world. These extensive experiments across simulation and real-world environments demonstrate and break the wall of utilizing the LLMs for automated design of continuum robots. The source code and experimental resources are publicly available at https://github.com/UNITES-Lab/AID-SR.

Neural networks acquire internal representations through learning. In this work, we formulate stochastic gradient descent (SGD) as a Markovian stochastic process and derive a Fisher-information flow speed limit that bounds the rate at which trainable parameters can acquire information about data-generating parameters. The resulting inequality decomposes the upper bound on the information flow into drift and noise contributions, thereby quantifying the roles of deterministic learning forces and SGD-induced fluctuations from an information-theoretic perspective. We verify the bound in analytically tractable basis-function linear regression, where the information budget predicted by the bound reproduces the ordering and characteristic time scales with which different data-generating parameters are encoded in the learned parameters. These results establish Fisher-information speed limits as a quantitative framework for understanding which properties of the data-generating process are acquired, in what order, and how rapidly they can be encoded in the trainable parameters.

This paper explores stabilizing traffic flow using a minimum number of autonomous vehicles (AVs) under control constraints. In contrast to most studies, we consider a heterogeneous parameter setup scenario for human-driven vehicles (HVs) to reflect real-world differences in driving behavior. While current literature uses an H-Infinity based sufficient condition to ensure the string stability of traffic flow, this often yields a conservative lower bound on the AV penetration rate to stabilize traffic flow. To reduce such conservativeness and obtain a less conservative lower bound, we ensure the string stability of traffic flow by directly imposing the possession of no growing eigenmodes. We also systematically find a minimum number of required AVs and solve for the optimal control parameters via nonlinear optimization. We finally assess the intended conservativeness reduction via numerical simulations. Quantitatively, applying our algorithm to the homogeneous HV baseline in the literature (the result built upon an H-Infinity based sufficient condition) reduces (improves) the AV penetration rate by 17.14% while ensuring the string stability of traffic flow. We observe a trade-off between the stabilization/performance degradation and the number of utilized identical AVs. Quantitatively, our last numerical simulation corroborates that the AV penetration rate can be reduced by 61.54% at the expense of 27.66% higher position difference deviation from the equilibrium and a 92.47% degradation in the real stability radius (RSR)—a metric to measure the stability robustness under the perturbation/uncertainty—associated with the aggregated linearized dynamics while ensuring the string stability of traffic flow. This trade-off helps engineers/operators make better traffic control decisions.

VLMs have shown promise for autonomous driving, yet still suffer from hallucination, weak spatio-temporal perception, and limited generalization. Recent methods improve reasoning and decision-making through CoT explanations, retrieval-augmented generation or the static injection of tool outputs. Although these mechanisms enrich the context, the model neither proactively perceives scene information nor accumulates experience after answering. To overcome these limitations, we present, to our knowledge, the first synergistic framework that tightly couples hierarchical memory with proactive tool invocation in a closed reasoning loop. Our contributions are threefold. (i) Hierarchical Driving Memory: a scene-level short-term memory maintains the dynamic scene state, and an evolving long-term memory retrieves reusable experience and tool strategies. (ii) Memory-Tool Synergistic Reasoning Framework: guided by the scene state and retrieved experience, the model adaptively invokes tools to refine its reasoning at inference time and consolidates reusable experience into a long-term memory pool offline. (iii) Data Generation and Two-stage Training Pipeline: verified memory-tool trajectories built by multi-step teacher rollout are used to train with SFT and GRPO. Our 7B model reaches an overall reasoning score of 80.03 and MCQ accuracy of 79.09% on DriveLMM-o1, surpassing the strongest baseline by 7.74 MCQ points and generalizes strongly across benchmarks. Notably, ablation and analysis studies validate the effectiveness of each component and further reveal the complementary roles of hierarchical memory. Short-term memory strengthens spatio-temporal understanding, improving STSBench accuracy by 24.2 points, while offline long-term memory consolidation yields an additional 3.57-point MCQ gain with all parameters frozen, demonstrating continual self-evolution through accumulated driving experience.

Agentic AI systems built on large language models fail in two persistent ways that scaling does not fix: they break under distribution shift, and they cannot explain the decisions they make. We argue these are co-symptoms of one structural deficiency in the data lifecycle that governs how agents are trained, evaluated, and deployed. Observational interaction logs record what an agent did, not what it would have done otherwise. They encode spurious correlations without controlled variation, so they lack the counterfactual structure needed to separate causal signal from coincidence or to validate an explanation. No model-centric method can recover invariances the data never contained. We present Data-Centric Anchoring: robustness and interpretability should be engineered into the data environment, not extracted from models after training. Our central contribution is the Data-Centric Agentic Loop, a four-stage framework of Curate, Augment, Constrain, and Attribute. The ordering is structural, not stylistic. Curation precedes augmentation because generative models amplify whatever bias they are trained on. Augmentation precedes constraint because invariance objectives are vacuous without variation across environments to be invariant to. Attribution closes the loop, converting observed failures into targeted data interventions for the next iteration. Each stage manufactures the preconditions of the next, which makes the loop self-correcting rather than merely sequential. We ground the framework in a failure-driven taxonomy that links four core failure modes to the data lifecycle: spurious feature reliance, distribution-shift fragility, uncertainty miscalibration, and explanation unfaithfulness. We close with the limits of this approach and the open problems that stand between it and practical deployment at scale.

Video generation models have recently attracted substantial attention for their ability to generate visually compelling videos, yet ensuring physically consistent and plausible dynamics still remains a fundamental challenge, driving a growing line of research on physical realism in video generation. To address this challenge, motivated by the fact that physical regularities are primarily encoded in motion patterns, we propose PhysFlow, a novel two-stage framework for improving the physical plausibility of generated videos by decomposing video generation into motion-aware optical flow generation followed by motion-conditioned appearance synthesis. Specifically, PhysFlow consists of a physics-aware optical-flow video generator called PA-Flow and a flow-guided video generator called FlowRender. During the first stage, PA-Flow employs a physics-aware attention module to model how motion attributes and material properties influence global motion and local deformation, respectively, and generates an optical flow video as an explicit representation of motion. In the second stage, FlowRender leverages the decoupled motion representation as guidance to synthesize realistic textures and appearances, ultimately producing the final physically plausible video. To further support model training with explicit physical supervision, we construct PhysVideo, a physics-based video dataset generated with a physics engine and 3D-GS rendering, containing 10K foreground objects and 50K realistic video sequences with annotations of motion and material properties. Extensive experiments demonstrate that our proposed PhysFlow generates videos with superior physical plausibility while maintaining high visual fidelity compared with existing methods.

TacClip is a minimally encumbering wearable device for recording fingertip deformation caused by contact forces and vibrations. It can be combined with vision- or glove-based hand tracking systems that leave the fingertips uncovered and provides a measure of dynamic contact interactions, while leaving the finger pads exposed so that the user retains natural sensitivity to texture, friction, temperature, and fine surface features. The signal is produced by a Fiber Bragg Grating (FBG) embedded on a small plastic clip mounted over the fingernail. Optionally, for use with vision-based tracking, additional FBGs on polyimide strips can complement camera-based pose estimation. In finger pressing tests, TacClip estimates the force magnitude with typical errors below $0.5~\mathrm{N}$ over a $0$–$8~\mathrm{N}$ range. In tests of cloth handling and tape edge finding, we show that it captures the vibrations and dynamic events generated during exploratory sliding. With no electronics, TacClip can also be used submerged in water, while preserving bare finger contact.

Diffusion watermarking embeds verifiable signals into the generative process and commonly verifies them by recovering trajectory-dependent evidence, making the marks robust to conventional pixel-space distortions. Existing removal attacks either regenerate along deterministic trajectories, which often preserve the watermark-bearing latent structure, or optimize every image separately. We identify the reliance on a recoverable generative trajectory as a common attack surface among the schemes we study. Based on this observation, we propose DRIFT, a black-box attack that combines partial forward diffusion with stochastic reverse resampling. Forward re-noising limits source information available to a fixed-depth recovery pipeline, while stochastic reversal supplies alternative noise-driven paths whose removal benefit we isolate through matched sampler comparisons. Adaptive DRIFT searches a selected ladder for each image's first verifier-rejected rung and refines fidelity while retaining only updates rejected by the same verifier. At fixed depth, we derive information-theoretic and Wasserstein source-dependence bounds; under realized-ladder monotonicity, the first rejected rung is least distorted among rejected rungs on that ladder, and verifier-gated refinement preserves rejection. Across nine watermarks spanning three paradigms, DRIFT achieves 98-100% attack success and the best image quality among the compared attacks, without secret keys, verifier internals, or per-image gradient optimization.

This work considers to numerically solve three kinds of reaction-diffusion equations with free boundaries. First, the popular front-fixing method is used to transform the considered free boundary problems into fixed boundary problems. Then, by employing the finite difference method, numerical schemes with $\mathrm{M}$-matrices as their coefficient matrices are developed for these transformed fixed-boundary problems. Next, for the developed numerical schemes, we establish numerical theory involving positivity preservation, monotonicity preservation, and stability. It is noteworthy that, unlike some existing works that impose tight restrictions on the time step-size to discuss the numerical theory, the proposed numerical schemes require only a mild restriction. Finally, numerical examples are provided to test the developed numerical schemes and to confirm the theoretical results.

Real-world Multi-Objective Reinforcement Learning (MORL) often suffers from sparse rewards, reward conflicts, and late-stage reward tug-of-war, causing traditional linear scalarization to experience severe metric oscillations. To address optimization conflicts among multiple objectives in real-world deployment scenarios, we propose Multi-Marginal Preference Optimization (MMPO), a fine-grained framework that intervenes at the data, gradient, and constraint levels rather than relying on coarse-grained global scalarization. Specifically, MMPO performs exposure debiasing to mitigate sparse and biased rewards, applies priority-aware orthogonal projection to decouple conflicting gradients, and introduces self-prompted gradient constraints to prevent dominant objectives from overwhelming weaker ones. Experiments on real-world e-commerce datasets show that MMPO improves training stability and consistently achieves better performance across conflicting metrics. Moreover, it generalizes robustly to broader tasks such as ToolRL and code generation, demonstrating its effectiveness as a practical paradigm for multi-objective alignment.

Learning from Observation (LfO) is a fundamental robotic capability that replicates how humans and animals socially learn from each other. Beyond its biological parallels, this modality provides a practical solution for data scaling in sample-inefficient and data-starved domains like robotics. Recent work has demonstrated promising results in learning manipulation skills from human videos, yet progress in this area remains difficult to assess. Existing methods vary widely in assumptions, hardware choices, and environment setups making it difficult to draw meaningful comparisons and identify advances in the field. To address these challenges, we introduce RoboReel: a unified benchmark for evaluating models that learn policies from human videos. RoboReel consists of bundled real-world human demonstration videos, simulated robot trajectories, and evaluation environments on ten manipulation tasks. We develop four test suites to evaluate the models' performance on multiple axes, including the robustness to visual distractors and the ability to complete long-horizon tasks. We further validate RoboReel by recreating a subset of its tasks in the real world, showing that relative performance trends observed in simulation are preserved in the real world. Our benchmark covers learning-from-observation models from different categories, and studies the effectiveness of multiple representation choices in our benchmark evaluation that covers over seven state-of-the-art algorithms (including our VLA based variants) in the field of LfO. Finally, we present an analysis of the different types of algorithms showing that long-horizon tasks and tasks with low tolerances are still challenging for current models. Webpage: https://roboreel.github.io

Instruct-TTS systems expand structured style labels into natural-language training instructions through LLM rewriting, yet we find that over 40% of unconstrained rewrites contain semantic drift that corrupts supervision and weakens generalization. We formalize this problem as instruction supervision instability and propose a data-centric stabilization recipe that jointly improves coverage and fidelity through three mechanisms: controllable instruction diversification for systematic expansion, LLM-based drift filtering for quality control, and attribute-aligned supervision that grounds prosody control in acoustic perturbations. On the Chinese split of InstructTTSEval, our recipe raises instruction-following from 34.5% without fine-tuning and 51.0% with naive fine-tuning to 56.4%, while constrained rewriting reduces drift from 40.4% to 15.4%. Ablations confirm the three mechanisms are complementary, and the drift taxonomy may generalize to instruction-driven generation beyond TTS.

For each level of the Clifford hierarchy from the third level onward, we construct explicit asymptotically good binary CSS codes for which a strongly transversal diagonal rotation, followed by a correction from the preceding level, implements the corresponding logical rotation. We achieve this using algebraic geometry codes over binary extension fields and performing an alphabet reduction that translates orthogonality conditions over the extension field to binary overlap conditions. In particular, we obtain the first asymptotically good family of binary triorthogonal codes. We also give a stronger construction with worse parameters for which the strongly transversal physical rotation implements the desired logical rotation, with no subsequent correction. Finally, adapting an error-correction-based distillation protocol, our binary $T$-gate families yield direct constant-overhead $T$-state block distillation from noisy $T$-state inputs under sufficiently weak input noise and ideal stabilizer operations.

Token-level text anomaly detection, as an emerging trend of text anomaly detection, moves beyond coarse-grained document-level detection by localizing anomalous tokens within text. By providing fine-grained abnormality prediction, token-level text anomaly detection plays a critical role in various real-world applications, such as spam filtering and fake news detection. However, existing methods still rely on the global distance calculation for scoring, during which the local anomaly signals are severely diluted by numerous redundant normal feature dimensions. Moreover, pre-trained language models used in these methods inevitably smooth out surface anomalies, further limiting their effectiveness in token-level anomaly detection. To address these limitations, we propose a Subspace Interaction-based Method (SIM for short) for token-level text anomaly detection. To prevent local signal dilution, SIM adopts a subspace interaction-based anomaly detector, which decouples high-dimensional token embeddings into multiple low-dimensional ones, amplifying localized anomaly signals hidden within specific dimensions. To counteract the over-smoothing effect, we design a hard pseudo-anomaly generation module to construct pseudo-anomalous tokens, simulating the subtle anomalies obscured by semantic smoothing. Also, a probabilistic boundary loss is developed to standardize anomaly scores into statistical distances, effectively enforcing anomalous instances to deviate significantly from the normal distribution center. Extensive experiments on multiple benchmark datasets verify the effectiveness of SIM and demonstrate its remarkable efficiency, robustness, and interpretability. The source code is available at: https://github.com/yankehan/SIM-TAD.

Quality-of-service (QoS)-aware random access requires adaptive allocation of a finite random access channel (RACH) preamble budget across heterogeneous traffic and access procedures. This paper proposes QP-BD3QN-RACH, a quota-projected branching deep reinforcement learning controller for mixed two-step (2RA) and four-step (4RA) contention-based random access. Four action branches correspond to the delay-sensitive and delay-tolerant 2RA/4RA preamble pools. A branching dueling Double DQN selects pool-specific multipliers, and deterministic quota projection converts them to nonnegative integer allocations that preserve the preamble budget. With five actions per branch, the controller represents 625 pre-projection branch-action tuples using 20 branch-action outputs. Evaluation covers five arrival loads, cross-method comparison under nominal seed 42, six-seed sensitivity of QP-BD3QN-RACH, and targeted ablations. Across the five-load grid, its mean direction-aligned differences relative to four comparators are positive: 5.74 to 8.21 percentage points for success/collision, 1.23 to 1.92 percentage points for fallback, 0.35 to 0.68 percentage points for blocking, and 0.128 to 0.456 decision intervals for successful-access delay. Load-wise results exhibit metric-dependent tradeoffs, particularly under intermediate and overload conditions.

This report analyzes Qiushi Engine v0.8 across all 40 test tasks in AstaBench E2E-Bench-Hard, a benchmark that requires autonomous agents to carry a research question through experimental design, code implementation, actual execution, result analysis, and report delivery. Qiushi Engine is model-configurable; this evaluation selected DeepSeek deepseek-v4pro-preview as the model backend. The official AstaBench leaderboard records a score of 0.816 and an average benchmark cost of USD 15.209 per task, while the full-precision local recomputation is $81.59 \pm 1.87$. Four tasks satisfied every rubric item, yielding a full-task completion rate of 4/40 = 10% – 7 percentage points above, and about 3.3 times, the approximately 3% best rate reported for AstaBench's official agents. Across 507 required rubric items, 416 were satisfied (82.1%). Official scoring archives and 40 Meta-Trace records show sustained production and verification of reports, code, and experimental artifacts; the principal gaps lie in repeated runs, external dependencies, specified metrics, and ablation studies. The report explains the benchmark, system workflow, aggregate results, representative cases, and limits of interpretation.

For two distinct binary words of length $n$, the separating words problem asks for a small deterministic finite automaton that accepts exactly one of them. Chase proved a $\widetilde O(n^{1/3})$ upper bound using a complex-analytic estimate for sparse polynomials. We replace that estimate by a finite-difference argument and a second-order real recurrence cutoff. The resulting elementary proof gives an explicit bound of $O(n^{1/3}(\log n)^{7/3})$ states.

A finite set of unit vectors is $k$-irreducible if every signed sum of between two and $k$ distinct elements has norm greater than one. Let $\mathcal{R}_k$ be the maximal asymptotic rate of such sets, and let $\kappa(\alpha)$ be the maximal asymptotic rate of spherical codes with pairwise inner products at most $\alpha$. For $k \ge 2$ we show: \begin{align} \mathcal{R}_k \le \min_{1 \le r \le \lfloor k/2 \rfloor} \frac{1}{r} \, \kappa\!\left(1 - \frac{1}{2r}\right) \, . \end{align} Combining this with standard sphere packing bounds, for large $k$ we obtain an almost-tight asymptotic comparison with the known lower bounds: \begin{align} \left(\tfrac{1}{2}-o(1)\right) \, \frac{\log_2 k}{k} \le \mathcal{R}_k \le (1 + o(1)) \, \frac{\log_2 k}{k} \, . \end{align}

Dynamic layer routing reduces the inference cost of Large Language Models (LLMs) by learning to skip layers for individual tokens. Existing methods, however, treat each routing decision as a local operation conditioned solely on the current hidden state which is a formulation that overlooks the sequential, path-dependent nature of routing across depth: earlier decisions shape the representations seen by downstream routers, and the layer-usage objective couples all decisions jointly. We propose History-Aware Routing (HeRo), a dynamic routing framework that resolves this mismatch by introducing a router memory mechanism to maintain an explicit routing state across model depth. The memory is constructed via linear attention, incrementally aggregating preceding routing scores and their induced residual updates into a compact history representation. At each routed layer, the router conditions jointly on this accumulated state and the current hidden representation to select the executed branch. Instantiated for token-wise FFN routing, HeRo trains only lightweight routers and adapters on a frozen backbone, requiring no modification to pretrained parameters. Across Llama 3.1-8B, Llama 2-7B, and Llama 2-13B, HeRo consistently achieves the highest aggregate performance retention among ten baselines. On Llama 3.1-8B, it bypasses 26.87% of model parameters while achieving 100.24% of dense model performance across seven benchmarks, and retains 97.01% while bypassing 38.82% of model parameters under a tighter computation budget. Ablation studies confirm that removing routing history consistently degrades performance, most notably on multistep reasoning and code generation, validating that explicit routing memory enables more accurate and adaptive dynamic routing than solely conditioning on hidden state.

Vision-language models (VLMs) augmented with retrieval-augmented generation (RAG) benefit from access to external evidence. However, standard retrievers and rerankers optimize for semantic similarity rather than answer utility, creating a preference gap: documents that appear relevant may not help the generator produce a correct answer. Motivated by this, we propose a two-stage generator-in-the-loop alignment framework that closes this gap without human document-level relevance annotations. Our framework consists of two stages: in Stage 1, a VLM generates a hypothetical text passage from the image-query pair, which is used as the retrieval query for dense text search, bridging the image-to-text modality gap. In Stage 2, a cross-encoder reranker adapted with low-rank adaptation (LoRA) is fine-tuned using answer-supervised preference pairs mined from the frozen VLM: given the dataset answer label, a candidate document is labeled positive if the VLM produces the correct answer when given that document as context, and negative otherwise. This generator-guided signal is compatible with multiple alignment loss functions, including contrastive (triplet) loss, pairwise direct preference optimization (DPO), and supervised fine-tuning (SFT), and supports periodic re-mining to refresh preference pairs as the reranker improves. Experiments on VQA-X and A-OKVQA with Qwen3.5-2B and Qwen3-VL-4B-Instruct show that our proposed framework consistently outperforms rank-order, random, and REPLUG-style likelihood baselines under various alignment losses and pool size settings, suggesting that answer-level generator feedback is an effective supervision signal for preference alignment.