Papers

We prove a geometric hierarchy of Fourier layer energies for the weakly nonlinear cubic Schrodinger equation on $\mathbb T_\pi\times\mathbb T_1$, retaining its nontrivial resonant dynamics. For initial Fourier support in a rectangle, form nested rectangles with half-widths $(2j+1)$ times the initial ones; layers are the differences between consecutive rectangles. On $0\le t\le T\delta^{-1}$, the energy in layer $j$, measured by its squared $H^1$ norm, is at most $C_N\delta^{2j}$ for $1\le j\le N$; the energy outside the $N$th rectangle is at most $C_N\delta^{2N+2}$. These bounds hold at every fixed depth $N$ under a uniform $H^s$ bound, $s>2$, with constants depending on $N$. The Sobolev bound holds for every fixed $T$ in the defocusing case. We also obtain layer estimates for support bounded in one coordinate and for geometrically decaying initial Fourier tails. The proof uses a filtered Poincare-Dulac normal form: input layers select which nonresonant interactions are removed, while the same layer weights control the interactions left in the equation. Finite coordinate changes and stability estimates transfer this hierarchy to the exact solution.

Long-horizon agents consume external content, invoke tools, and modify persistent state. Indirect prompt injection can exploit task-specific context, propagate across causally connected stages, and alter a consequential action while the workflow continues; we term this staged prompt injection. We build an automated, feedback-guided attack generation pipeline and apply it to Claude Code and Codex in their native runtimes. The confirmed attacks span eight workflow scenarios, seven attack goals, and six injection surfaces, showing that production agents are vulnerable to context-aware, multi-step injection over long horizons. Stopping such attacks requires a decision before each consequential action: input screening and completed-run evaluation cannot locate the intervention point, and existing pre-action methods use incompatible units and labels. We therefore formulate boundary action auditing: given initial context, a trajectory prefix, and a fully specified pending message or tool call, an auditor predicts Pass or Block before its effect occurs. Pairing attacked and benign executions yields a 479-pair, 3,112-unit benchmark. We further propose Path-Aligned Attribution (PAA), a training-free auditor that decomposes pending actions into operative elements and traces what supplied each value and guided each decision. PAA blocks only when the model attributes an unwarranted, material effect on an element to an attacker-reachable source that either provides unqualified steering or conflicts with visible evidence. Under full-benchmark fail-open scoring with Claude Sonnet 5, PAA reaches 86% Block recall at a 6-8% false-block rate (FBR), whereas ARGUS reaches 44-47% recall at 16-33% FBR. Under the same backend, on the tool calls that all three auditors natively support, PAA has higher recall and lower FBR than VIGIL and ARGUS; all paired 95% confidence intervals exclude zero.

Long-term memory enables LLM-based agents to retain and reuse information across tasks and sessions, supporting personalization and long-horizon interactions. However, persistent memories can also induce sycophancy, causing agents to over-align with users' historical beliefs even when they are inaccurate, outdated, or inconsistent with objective evidence. Existing mitigation methods assume that memory-induced sycophancy originates from biased or incorrect memories and attempt to reduce this risk by filtering such memories at different stages of the memory pipeline. However, in the real world, objective and correct memories can still induce sycophancy, and the same memory can warrant different influence across different contexts. To this end, we propose MemAdapter, a novel framework that adaptively integrates retrieved memories to support objective and reliable reasoning. Specifically, MemAdapter consists of three components: (i) Counterfactual Induction, which leverages counterfactual reasoning to uncover the potential risk of retrieved memories; (ii) Context-Aware Reflection, which calibrates the inferential influence of each retrieved memory in light of the current task via self-reflection; and (iii) Evidence-Based Reasoning, which grounds the final response in appropriate evidence while preserving the legitimate influence of memory. Extensive experiments on three benchmarks demonstrate that MemAdapter consistently improves memory reliability across diverse scenarios. Our code is available at https://github.com/DEEP-JLU/MemAdapter.

Instruction following typically enforces discrete, response-level requirements, whereas an expert-authored skill prescribes procedural requirements spanning multiple phases and environment interactions. Given such a skill, we train the executor to execute all required phases instead of focusing solely on the final answer. We therefore introduce Grounded Skill-Following, which requires an agent to execute a fixed, expert-authored skill across its required phases by grounding decisions in environment observations. To achieve verifiable procedural execution, we formulate each skill as a skill contract combining visible skill instructions with an explicit contract runtime. The runtime specifies required phases, admissible actions, permitted transitions, and accepted termination. This structure provides a dense, verifiable training signal throughout execution. We leverage this by introducing Verified Progress Credit, which assigns rewards upon the initial completion of contract milestones and aggregates them into the trajectory return to guide policy optimization. During rollout, the contract runtime continuously tracks state transitions to provide Contract-State Feedback, which indicates whether the latest action is accepted and guides the agent toward valid next actions. To measure procedural compliance, we introduce the Protocol Completion Rate (PCR), defined as reaching accepted termination through all required phases, and decouple it from the final Task Outcome. Jointly trained with our framework, Qwen3.5-4B achieves Protocol Completion Rates of 99.27% on Math and 99.96% on Search, while slightly outperforming original baselines in Task Outcome (82.95% and 46.61%, respectively). Controlled studies examine how skill instructions, training signals, and contract-state feedback affect both metrics, while withholding interventions evaluate behavioral dependence on observation content.

Conventional large-language-model chat interfaces typically follow user-initiated turns: each request elicits a response, after which the system waits for further input. Human asynchronous communication instead unfolds over time through message bursts, delays, silence, resumed topics, and self-initiated contact. Proactive dialogue therefore requires not only deciding when to speak, but also managing pending conversational actions and allowing them to be revised as context evolves. We introduce Proactive AI, a framework for proactive dialogue built around replannable temporal message queues. The framework treats interaction as a continuous event timeline and unsent conversational actions as revisable state. A user event, dialogue-pacemaker event, or scheduled decision may yield silence, one or more immediate messages, or future conversational actions. The system may also observe a user message without an immediate visible response and defer the response decision. Before delivery, every planned message must be reconsidered against the current context; reaching a scheduled time does not itself authorize delivery. We provide a formal semantics that characterizes when future conversational actions may be revised, withdrawn, or executed as context evolves. The framework extends AI participation beyond responses to current requests, enabling self-initiated exchanges without new requests, sustained follow-up over time, and revisions of subsequent actions as context evolves. It provides an executable basis for long-term human-AI interaction in tutoring, scientific collaboration, and everyday companionship.

Gastric Adenocarcinoma is a leading cause of cancer mortality. Although "Inflamed/Non-Inflamed" subtypes have been proposed to predict immunotherapy response, their identification relies on a costly 10-gene RNA signature. We propose a Cross-modal Contrastive Multiple Instance Learning (CCMIL) framework for cross-modal retrieval, imputing these molecular signatures directly from standard Hematoxylin & Eosin (H&E) slides. By leveraging a supervised contrastive objective, CCMIL aligns visual morphological patterns with molecular phenotypes into a shared latent space. This establishes an interpretable search-by-case retrieval engine, enabling pathologists to query a whole slide image to surface transcriptomically coherent neighbors and approximate RNA signatures without genomic sequencing at inference. Our results demonstrate that this retrieval-first approach captures the continuous phenotypic spectrum of tumor inflammation and yields clinically interpretable attention heatmaps. Furthermore, the learned representation also supports competitive downstream classification, providing a practical molecular pre-screening strategy.

Geostationary satellite observations are important for wildfire detection and monitoring. The current study evaluates machine learning models for MTG FCI near-real-time fire detection in 1- and 2-km spatial configurations and compares them with threshold-based algorithms. The models were trained and evaluated using VIIRS fire reference data across diverse ecological regions in Europe, Africa, and the Middle East. The key results are that 1-km models significantly outperform both their 2-km variants and operational threshold products. The constructed 1-km models achieved F1 scores higher by up to 0.36 compared to baseline products. Importantly, the 1-km models detected small fires with higher probability compared to competing models. Finally, the models robustly detected fires up to 260 min earlier than baseline products. To support opensource applications, our trained models are publicly available.

Visuomotor policies can execute familiar tasks yet lack the corrective behavior needed after their own mistakes. We present a framework for recursive self-improvement through local recovery supervision. Each round audits the current policy, generates corrective demonstrations at supported failure states, and uses them to update the policy that drives the next round of collection. An offline auditor locates unresolved failures using coarse and dense temporal evidence and specifies observable repair goals. A fixed multimodal agent acts as a tool-using teacher, generating recovery actions through observation, computation, execution, and feedback. The frozen student tests whether each teacher endpoint supports further progress. If continuation fails, the system restores that endpoint and extends the demonstration. Action-level quality assessment then defines continuous training windows with aligned observations, quality weights, and validity masks. Only the student is deployed. In a preliminary LIBERO-Goal study, recovery-augmented post-training achieves 88 successful episodes out of 100 validation scenes, compared with 78 for original-data continuation from the same $\pi_0$ checkpoint. An earlier BC-RNN study on robomimic Can improves success from 102/130 to 112/130 using 26 local recovery segments. Both comparisons match 2,000 additional optimization steps.

Recovering three-dimensional human geometry from electromagnetic measure?ments in a complex static environment is difficult because strong multipath responses from walls, floors, and other objects obscure the weak target per?turbation. We propose R1A-PC, a physics-guided method that reconstructs a 2048-point human cloud from paired complex fields measured with and without the target. Complex background subtraction emphasizes target-induced ampli?tude and phase changes, while the background field remains available as an environmental condition. A frequency-balanced discrete Born adjoint produces a three-dimensional spatial knowledge map. At each of two bounded deformation stages, the decoder combines complex measurement features, background fea?tures, and multiscale physical features queried at the current point coordinates; the second stage queries again after the first coordinate update. We analyze the residual of paired subtraction, the weighted normal-operator structure of the raw adjoint, and the feasible set of the predicted cloud. In a held-out background generated by full-wave simulation under a fixed acquisition geometry, R1A-PC obtains a squared Chamfer distance of 0.001434 m2 and an F-score of 0.963080 at 0.05 m. Compared with TopNet, the Chamfer distance decreases by 70.28%. Removing physical guidance or background subtraction increases the Chamfer distance by 242.06% or 241.18%, respectively. Experiments across background layouts and poses support the complementary roles of paired subtraction and position-dependent adjoint features.

Reinforcement learning (RL) policies can deteriorate under out-of-distribution (OOD) magnitude shifts. Starting from soft actor-critic (SAC) and its Bayesian Amnesic Piecewise-Robust (BAPR) predecessor, we study the causal-symbolic BAPR (CS-BAPR) family. The practical method combines six training-stabilization settings with alternative actor heads: a Neural Addition Unit (NAU) with a Neural Multiplication Unit (NMU)-inspired quadratic correction, a Kolmogorov-Arnold Network (KAN), or a multilayer perceptron (MLP) with rectified linear unit (ReLU) or hyperbolic-tangent activations.

Controlling the camera relative to a moving subject in an existing video is challenging: behaviors such as maintaining a frontal view require the camera to adapt to the subject's changing position and orientation, making the desired trajectory difficult to specify in advance. Existing camera-controlled video-to-video methods typically rely on explicit trajectories or reference motions, which do not directly express these dynamic camera–subject relationships. We introduce semantic camera motion control, a novel video-to-video task in which a reference video and a target motion label specify the desired subject-relative camera behavior without an explicit target trajectory. Our method, SemCam, learns to realize this behavior while preserving source content. It combines shared-basis low-rank adaptation with motion-conditioned modulation, while a background-consistency loss encourages fidelity in regions visible in both reference and target videos. We construct 661 paired videos covering eight semantic camera behaviors and evaluate on a separate 109-scene benchmark using subject-relative motion metrics, appearance measures, and a user study. SemCam achieves a semantic-motion success rate of 68.6%, compared with 45.3% for Vista4D, the strongest evaluated baseline, while maintaining comparable subject identity preservation.

As agents rapidly evolve, existing benchmarks can become saturated, limiting their ability to distinguish capabilities and reveal remaining failure modes. Particularly in scientific domains, constructing and updating benchmarks requires substantial time, labor, and domain expertise, making it difficult to keep evaluation aligned with advances in agent capabilities. We address this challenge by investigating whether scientific-agent benchmarks can be automatically generated and iteratively adapted as agent capabilities evolve. We introduce AutoSciBench, a framework that represents each task as a high-level concept specifying the scientific domain, data modality, and required reasoning approach, together with a low-level recipe specifying how the question, environment, and ground-truth answer are constructed and verified. Agents attempt to solve each task, producing solver trajectories and corresponding judge feedback which AutoSciBench uses to revise the recipe or concept, closing observed shortcuts and shifting tasks toward raw-data re-examination, interpretation of intermediate results, and evidence integration. Experience distilled from completed refinement trajectories further guides new concept generation, allowing lessons from earlier task refinement to inform subsequent benchmark construction. Starting from existing benchmarks, we evaluate AutoSciBench across computational biology, materials science, and clinical imaging. Generated benchmarks reduce average solver accuracy by 22.4 and 25.5 percentage points relative to the human-curated benchmarks in computational biology and materials science, respectively, while generated tasks receive higher average quality ratings across all three domains, suggesting that scientific-agent evaluation can adapt as agent capabilities advance.

Code large language model (Code LLM) assistants generate code from heterogeneous development contexts, including open files, imported modules, pasted snippets, and comments, much of which may originate from untrusted sources. We investigate whether insecure instructions embedded in such contexts can steer Code LLMs toward vulnerable code without access to model weights or training data. We evaluate ten open-weight Code LLMs spanning 3B–13B parameters, including four base and six instruction-tuned models, across ten web-application weakness classes. We compare completion tasks containing insecure instructions embedded as code comments with benign tasks without malicious instructions. Attack-condition completions contained a medium-or-higher weakness in 77.4–92.3% of cases, compared with 1.7–5.1% in the benign condition. Base and instruction-tuned models averaged 86.5% and 84.5% vulnerable outputs, respectively; equivalence testing and three matched model pairs indicated reductions of at most 8.1% after instruction tuning. Susceptibility showed no clear association with model scale or specialization. Among vulnerable attack outputs, 86.2–91.0% were rated high or critical, and the effect persisted without the pattern-based detector. Post-generation screening reduced but did not eliminate the risk, the strongest screen leaving roughly one-third undetected. These findings identify inference-time context injection as a substantial attack surface and motivate provenance-aware training objectives.

We construct secure cyclic multi-access coded caching schemes by re-encoding the caches of a secure single-access scheme and reusing its multicast message unchanged. For a library of $N$ files, each of $K$ users reads $L<K$ consecutive shared caches and must recover its requested file while learning no information about the other files. Starting from a parent scheme with a cyclic representation of its cached symbols, the transformation lets each access window recover the corresponding parent-cache symbols and, conditioned on them, learn nothing about the remaining symbols. A deterministic Pascal-window encoder handles symbols whose consecutive appearances span at least $L$ users. A randomized complement-dual encoder handles shorter spans. Over a suitable finite field, these encoders attain the exact minimum per-block storage for every input length in the block-separable, parent-preserving class. Applying the transformation to two secure single-access schemes gives an achievable memory-rate family for $N,K\ge2$ and $1\le L<K$, including the exact rate-one cache size $(N-1)(K-1)/L$. Using converse bounds for arbitrary secure multi-access schemes, we prove approximation guarantees for the achievable family and give a proof of the exact $L=K-1$ tradeoff.

Under a fixed physical law, the visible geometry of a scene determines how motion must change. We ask how video generators realize this relationship. We fix the law and the initial state and change only the geometry drawn in the first frame, within matched families of tracks and deflectors, and compare each generated trajectory with the simulator prediction for that geometry. Paired interventions change one thing at a time: a local bump, the height of a barrier, the words of the prompt, the length of the clip. Across nine image-to-video models, geometry is preserved and shapes the motion: the speed of the ball follows the drawn undulation of a track. A physical state would carry this response forward, and here the generated motion parts from the law. The mean slope barely accelerates the ball, successive contacts fail to compose through a consistent state, an edit ahead of the ball alters its motion before it arrives, and the ball climbs over barriers higher than its release point. Two global conditions organize the global trajectory: text strongly controls the destination, while clip length strongly controls timing in the open-weight models tested. The pattern persists with photographed first frames. Current video generation thus behaves as geometry-conditioned motion synthesis whose evolution of state differs systematically from that of a fixed physical law.

Formal specifications are essential for deductive program verification, providing semantic abstractions for compositional verification of complex software. However, manually constructing specifications is labor-intensive, motivating automated synthesis. Despite recent advances in large language models (LLMs), existing approaches often rely on forward-only workflows and localized repair, limiting their effectiveness on real-world programs with complex dependencies among functions and loops. Verification failures may stem from previously generated specifications, causing cascading failures that local refinement cannot resolve. To address these challenges, we present SpecAgent, an agentic framework for synthesizing high-quality ACSL specifications for real-world C programs. SpecAgent integrates four components: dependency-aware planning to identify specification targets, retrieval-augmented generation (RAG) to provide relevant specification patterns and program context, agentic repair to diagnose defects and revisit dependent specifications, and agentic critique to assess and refine semantic strength beyond proof success. We evaluate SpecAgent on specification synthesis and program verification tasks. On 50 programs from 14 real-world repositories, SpecAgent with DeepSeek-V4 achieves 96.82% precision and 88.95% recall in synthesizing correct and strong specifications, outperforming all baselines. On 811 real-world verification targets, it successfully discharges 604, also surpassing existing baselines. These results demonstrate SpecAgent's effectiveness in synthesizing high-quality specifications and facilitating real-world program verification.

Intermediate-layer features from multimodal large language models have shown strong potential for video anomaly detection (VAD), yet the origin of their discriminative power remains unclear. We study this question using sparse mixture-of-experts (MoE) models, whose explicit expert structure and sparse activation make their internal computation easier to inspect. With a fully frozen backbone and no additional training, we find that anomaly-related evidence is concentrated in a small set of experts. These experts recur across layers, spontaneously specialize in different anomaly types, and together form a dynamic routing subnetwork. We further show that the output channels most strongly influenced by these experts are also the hidden dimensions that contain the most anomaly-relevant information. Routing statistics can therefore serve as an internal anomaly cue that complements semantic features.Based on these findings, we propose RoMod, an efficient VAD framework trained with only \(5\%\) of weakly labeled videos. RoMod includes a Routing-Modulated Fusion module, RoMF, and a Routing-aware Temporal Network, RoTN. RoMF uses routing signals to adaptively recalibrate hidden semantic channels. Its design also prevents the routing branch from bypassing semantic features and making predictions on its own. RoTN captures the temporal evolution of anomalies from onset to persistence and termination. Experiments on three benchmarks show that RoMod achieves state-of-the-art performance while running substantially faster than dense backbones of comparable size.

An electromagnetic inversion scheme that integrates stochastic optimization (STO) and plug-and-play (PNP) regularization into contrast-source inversion (CSI), termed STO-PNP-CSI, is developed. Standard CSI solves for the contrast source vector of every transmitter at each iteration, which is expensive in a multi-transmitter configuration. STO instead solves for only one randomly selected contrast source vector per iteration, which reduces the per-iteration cost and can help the inversion escape poor local minima and saddle points. The resulting loss of information, however, increases the ill-posedness of the inversion. To counter this, the Swin-Conv-UNet (SCUNet) denoiser is plugged into the CSI scheme as an implicit regularizer, supplying a learned prior that is stronger than conventional hand-crafted ones and stabilizes the reconstruction. The proposed STO-PNP-CSI is applied to both synthetic and experimental data. The results show that it yields accurate reconstructions at substantially lower computational cost than CSI, including under strong nonlinearity and measurement noise.

Multimodal Large Language Models (MLLMs) provide a natural way to make video anomaly detection more explainable. However, their final decisions do not always fully use the discriminative information contained in their hidden states, an issue we refer to as representation–behavior misalignment. We decompose this gap into a capacity component that measures discriminative information never aggregated into the readout position, and a directional component that measures the angular mismatch between the optimal and the native normal–abnormal axis at that position. Across multiple video anomaly detection benchmarks and MLLM backbones the directional component dominates, and residual-stream tracing shows that native-axis separability rises sharply in several mid-to-late attention layers. Because both components are governed by attention rather than MLP updates, we propose Representation–Behavior Alignment (RBA), a parameter-efficient method that adapts those layers using video-level labels alone while updating about 0.012% of the backbone parameters. Experiments on three benchmarks show that RBA improves native-readout performance and better aligns the model's decision direction with discriminative representations, and it produces anomaly decisions and explanations through a single generative process.

Variational quantum algorithms (VQAs) generally rely on classical optimization to train parameterized quantum circuits. This training seeks to minimize an objective function, and its efficiency is central to the practical success of these algorithms. However, globally minimizing such training objectives over the circuit parameters is known to be $\mathsf{NP}$-hard, limiting the prospect of general guarantees for efficient training. In this Letter, we prove that even the weaker task of finding a local minimum of such VQA training objectives is strongly $\mathsf{NP}$-hard, including when the objective admits efficient classical evaluation. Moreover, we show that this hardness persists even for the task of finding a parameter vector within $\ell_p$-distance strictly less than $\pi/2$ of some local minimizer, for every $p\geq 1$. Our central technical result is that approximating a local minimizer of a Hermitian trigonometric polynomial is strongly $\mathsf{NP}$-hard. By explicitly constructing quantum circuits whose training objectives reproduce these hard instances, we obtain a polynomial-time reduction to VQA training. Our results establish a fundamental computational barrier to variational quantum training: even reaching the vicinity of a local minimum remains hard in the worst case.

Physics-informed neural network (PINN) training minimizes a weighted combination of partial differential equation (PDE), boundary-condition, and initial-condition losses. Because adaptive methods modify these weights during training, their weighted total losses are not always directly comparable. We compare fixed-weight PINN, gradient-normalized PINN (GNPINN), and a rule-based adaptive controller (AgenticPINN) under matched settings on a heat-equation benchmark and a simplified Czochralski-oriented thermal-fluid problem. In the crystal-growth MLP experiment, adaptive control reduced the PDE residual from the order of $10^{-5}$ to $10^{-6}$, while the boundary-condition loss increased from the order of $10^{-5}$ to $10^{-2}$. On the heat-equation benchmark, GNPINN achieved the lowest relative $L_2$ field error (0.054), whereas AgenticPINN obtained the smallest PDE residual but a relative $L_2$ error of 1.368. Gaussian-process surrogates were additionally evaluated using case-wise holdout tests on corrected Czochralski CFD parameter sweeps. The temperature-field error for the temperature sweep was approximately 6%, whereas the axial-velocity error for the crystal-rotation sweep was approximately 42%. These findings show that adaptive control can improve equation satisfaction while weakening other physical constraints. PINN training should therefore be evaluated using separate PDE, boundary-condition, and solution-error metrics rather than weighted total loss alone.

The repetition count that works best for a small language model may not remain best at a larger scale. We study this effect in pretraining with a finite target corpus mixed with generic data at a fixed target fraction. On Wikipedia-derived data and Proof-Pile-2, the ranking of measured repetition counts changes with model size, and a 520M Proof-Pile-2 experiment confirms that reducing repetition from sixteen to eight improves loss while using fewer training tokens. We use loss curves from several smaller models to retain a short list of promising repetition counts for evaluation at a larger scale. On PubMed and Caselaw, candidate sets fixed before target-model training retain the lowest-loss measured count on the original evaluation grids at both 200M and 520M. This supports candidate retention as a practical alternative to exact point prediction. We also relate the pruning regression to an empirical scaling model with two opposing repetition-dependent loss terms. A first-order expansion in log model size yields the linear form used by the selection rule, providing a scaling-based interpretation of the candidate-selection procedure.

Masked Diffusion Language Models (MDLMs) generate sequences by iteratively replacing masked tokens with model predictions. At each denoising step, the decoder chooses which positions are sufficiently confident to commit. Existing decoding methods typically rely on softmax confidence, which can be miscalibrated. We introduce BayesER (BAYESian Entropy-based Reordering), a post-hoc Bayesian decoding framework that uses predictive uncertainty to guide token commitment. In BayesER, we construct a lightweight approximate posterior centered at the pretrained checkpoint, similar to Laplace-LoRA but without training LoRA adapters. We average predictions over posterior samples and use predictive entropy to prioritize reliable positions. We examine how posterior predictions affect position ordering and token selection across benchmarks spanning code generation, mathematical reasoning, planning, and molecular generation. We show that BayesER reduces sequence-level calibration error while preserving or improving accuracy relative to common decoding schemes, including confidence-threshold decoding. Additionally, a posterior fitted on one code-generation dataset reduces calibration error on another without refitting, suggesting that Bayesian uncertainty may provide a transferable signal for more reliable MDLM decoding.

Persistent memory for Large Language Models (LLMs) has matured rapidly: systems such as MemGPT/Letta, Mem0, and Zep now provide agents with tiered, temporally-aware, model-agnostic external storage, while the Model Context Protocol (MCP) standardizes access to memory servers. A less addressed problem is that an identical stored memory object, retrieved by two different LLMs under otherwise identical conditions, may not be interpreted the same way, factually or emotionally. This paper proposes memory canonicalization: a write-time pipeline that detects ambiguity, conditional structure, and emotional loading in a raw memory object and rewrites it into an explicit, structurally disambiguated canonical form, with emotional valence represented as a separate field rather than inferred from tone. We formalize the pipeline, define a companion Cross-Model Semantic Drift / Emotional Consistency Score benchmark (CMSC-E), and report results from a three-arm pilot using 176 synthetic memory objects and three downstream model families. We find an uncorrected improvement in cross-model emotional consistency for fully canonicalized memory relative to raw memory (+0.050, 95% bootstrap CI [0.013, 0.086], paired t-test p = 0.010), but this result does not survive Bonferroni, Holm, or Benjamini-Hochberg correction across the six comparisons tested. None of the factual-drift (CMSD) comparisons reach significance at any correction level. We report these results as exploratory rather than confirmatory and outline needed follow-up work, including larger samples, independent judge models, human-validated rendering, and preregistration.

Mixture-of-Experts (MoE) inference is increasingly deployed in local and on-premise environments, where expert parameters often exceed GPU memory capacity. In latency-sensitive, low-concurrency settings, repeatedly staging routed-expert weights from CPU memory to the GPU can be prohibitive, leaving routed-expert feed-forward networks (FFNs) on the critical path of multi-socket CPUs. Existing CPU accelerations often rely on intrusive, hardware- or topology-specific requirements, such as AMX-specific weight layouts or manual NUMA-aware placement. These requirements reduce portability and complicate integration with standard CPU-GPU offloading pipelines. We present HiNa-MoE, a high-performance, non-intrusive operator library for MoE inference on CPUs with Intel AMX. HiNa-MoE (1) exploits AMX with an optimized micro-kernel that keeps expert weights in standard layouts and instead fuses lightweight layout transforms into token gathering and stores; (2) applies NUMA-aware task partitioning under a simple page-interleaved policy without modifying the framework allocator; and (3) converts decode-phase memory matrix-vector operations into small matrix-matrix execution to utilize AMX. Across multiple MoE models, HiNa-MoE achieves up to 3.37x speedup for FFN kernels and up to 2.09x end-to-end inference speedup over state-of-the-art baselines, while remaining plug-and-play with existing frameworks and deployment workflows.

In recent years, Unmanned Aerial Vehicles (UAVs) or drones have been increasingly adopted in urban environments for applications such as parcel delivery, infrastructure inspection, emergency response, and drone light shows. A non-negligible issue is how to manage the increasing number of drones operated by different entities, to enable them to cooperatively avoid potential collisions and determine conflict-free short-term flight paths in urban airspace. This paper presents a Prediction-Based Short-Term Decentralized Greedy (PB-STDG) guidance algorithm for a structured Drone Road System (DRS). PB-STDG extends the original STDG algorithm by introducing a prediction mechanism that enables drones to anticipate the decisions of neighboring drones using additional information shared in beacon packets, aiming to address the over-conservative behavior observed in the STDG algorithm. Several simulation scenarios are conducted to evaluate and compare the proposed algorithm with STDG. The results show that PB-STDG improves traffic efficiency while maintaining a safety level comparable to that of STDG.

Deep search agents tackle complex knowledge tasks through iterative retrieval, multi-hop reasoning, and evidence synthesis across multiple sources. Existing approaches typically assume relatively stable retrieval systems and operate over short-horizon tool interaction. However, when retrieval is sensitive to query formulation, even a semantically appropriate query may fail to surface critical evidence because of mismatched entity names, aliases, or keyword combinations. Recovering from such failures requires repeated query reformulation and longer interaction trajectories. This setting poses a distinct training challenge, as the policy must sustain long-horizon query exploration while managing an expanding volume of retrieved content. We propose LexiHorizon, a framework for training search agents over long horizons that expands the trajectory context budget, manages accumulated retrieval content using a window over recent tool observations while preserving the reasoning history, and introduces an outcome-gated search-effort reward that provides a bounded bonus for tool invocations to trajectories with nonzero answer reward. Experiments on XBench, WebWalkerQA, and BrowseComp-ZH show that the resulting 9B model consistently outperforms both its base model and MiroThinker-1.7-mini, with maximum absolute gains of 8.7 and 23.8 percentage points, respectively. These results suggest that combining an extended context budget with reasoning-preserving context management benefits long-horizon deep search agents.

Small targets occupy few patches in a vision-language encoder, so spatial features often mix object appearance with surrounding content. We propose Prototype Contrast and Local Magnification (PCLM), a support-conditioned localization method that uses a frozen CLIP encoder. Five masked support images per class define foreground and background prototypes through equally weighted regional features. Their difference provides a shared scoring direction for query patches, explicitly comparing target evidence with the demonstrated background. Nine overlapping query windows are enlarged and encoded independently to sample small targets more densely. Reprojection and coverage averaging combine their scores into a continuous localization map. The class direction occupies 2 KiB regardless of support count and transfers unchanged across datasets with mapped categories. On 5,047 small-target queries from VOC, COCO, ADE20K and Oxford-IIIT Pets, PCLM achieves higher mean pixel AP than every evaluated text-conditioned localization baseline on each dataset under our evaluation protocol. Gains over the strongest scene-dataset baselines range from 5.63 to 13.23 percentage points. At comparable measured latency, local magnification improves scene small-target AP by 4.51 to 5.68 points over whole-canvas enlargement. Factorial experiments show that prototype contrast increases the benefit of local observation, including under matched image-coordinate filtering. Support-budget experiments show that additional examples refine category estimation without increasing representation size or query-time scoring cost.

Large language models (LLMs) progressively revise their predictions across Transformer layers, yet we typically observe only the final output, discarding the trajectory through which it is formed. We introduce Belief-Trajectory Energy(BTE), a model-grounded measure that characterizes an input through the layerwise predictive revisions it induces in a model. By mapping intermediate states into a shared predictive space, BTE provides a principled measure of belief change that can be summarized as either a scalar or a structured depth profile. Theoretically, we show that local BTE corresponds to predictive revision under the Fisher-Rao geometry, while the sequence of revisions captures information beyond the initial-to-final belief change. Empirically, scalar BTE provides a model-relative signal of difficulty across diverse reasoning tasks, while richer BTE representations support human-LLM review detection and fine-grained generator attribution, reaching up to $0.998$ macro-AUROC and $95.6\%$ eight-way attribution accuracy. Further analysis shows that BTE develops throughout pretraining and is selectively reshaped by targeted training, demonstrating that the resulting measurement reflects what the scoring model has learned. Together, our results establish belief trajectories as a principled model-grounded signal and suggest a broader perspective in which learned models can themselves serve as instruments for characterizing the data they process. More demonstrations can be found at https://yingjiahao14.github.io/BTE-web/.

Asynchronous circuits have some benefits over their synchronous counterparts, such as lower idle power consumption, potentially lower latency, absence of clock distribution issues, among others. However, industry-scale electronic design automation (EDA) support, particularly for high-level synthesis (HLS) of asynchronous systems from imperative programs, remains limited. We present an approach to synthesize asynchronous circuits from imperative programs using the AHIR HLS framework. The framework models the control path in the form of a restricted form of Petri nets that are 1-safe and live by construction. In this work, we start with this representation in AHIR and generate asynchronous circuits with a delay insensitive controller, a single-rail data path with bundled-data interaction between the controller and the data path that resembles the micropipelines architecture. We formalize the timing constraints required for correct functioning of the generated circuit and show that those constraints are one sided (feasible), necessary and sufficient. We have also developed a static timing analyzer to check that the circuit meets these constraints. Our flow integrates seamlessly with off-the-shelf ASIC toolchains and standard synchronous cell libraries. To demonstrate our approach, we show an end to end implementation of an AES encryption algorithm and use post layout circuit simulation to verify the correctness and estimate the performance of the resultant circuit.