arXiv:2606.05394v2 Announce Type: replace Abstract: nnAudio is an open-source audio feature extraction toolbox for deep learning, but its use in current environments is hindered by TorchScript incompatibilities, inverse-transform edge cases, and dependency drift. We present a targeted modernization for modern PyTorch and scientific Python. We resolve TorchScript compilation failures in STFT and iSTFT by removing dynamic state mutation and module construction from scripted code paths and tightening argument handling in inverse-related helpers. We clarify inverse-STFT behavior by restricting reliable inversion to the uniform-bin setting (freq_scale=`no') and raising explicit runtime errors for unsupported frequency scales, preventing silently degraded reconstructions. We restore CFP compatibility with modern SciPy and ensure VQT reduces to CQT when gamma = 0. Regression tests cover the new STFT/iSTFT behaviors, and the updated codebase passes the full repository test suite in a modern Python environment. These improvements provide a more robust foundation for differentiable audio analysis in research and deployment.
Science Journals
arXiv:2606.11891v1 Announce Type: new Abstract: Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a single policy. A natural design choice is whether to use a single (unified) critic that estimates the combined value of all objectives, or separate (dual) critics with disjoint reward signals. We present a controlled comparison on the Unitree G1 humanoid (23 active DoF) in NVIDIA Isaac Lab, training loco-manipulation policies through a sequential curriculum spanning 13 levels from stationary reaching to walking with variable-orientation targets. In standardized evaluation, dual-critic policies reach targets 3.5$\times$ faster (6.5 vs. 22.6 simulation steps), achieve 2$\times$ higher throughput (14.3 vs. 7.0 validated reaches per 1,000 steps), and attain higher validated reach rates (65.2% vs. 53.8%) compared to the unified-critic policy. Notably, additional anti-gaming reward mechanisms provide no further improvement beyond the architectural change alone (60.9% vs. 65.2%). These results have direct implications for the emerging paradigm of RL fine-tuning of imitation-learned policies: when refining a pre-trained manipulation policy with RL, a unified critic risks suppressing the learned behavior through competing locomotion gradients. These findings demonstrate that critic architecture is a primary - and often overlooked - design choice in multi-objective humanoid RL, with greater impact than reward engineering on reaching efficiency.
arXiv:2606.11913v1 Announce Type: new Abstract: We propose a new paradigm for long video understanding by treating a long video as a Neural Knowledge Representation (NKR). NKR represents video contents neither as a stream of tokens nor pre-organized databases, but as an individual small portion of network weights attached to the VLM backbone. The NKR weights are optimized to encapsulate the video's semantic content via a novel Agentic Knowledge Distillation (AKD) process, where an agent automatically synthesizes dense descriptions and question-answer pairs to distill the video's knowledge into the NKR. While AKD serves as a comprehensive, one-time encoding phase, the resulting NKR transforms the video into a portable, reusable asset. At inference, the lightweight NKR is mounted onto a frozen Vision-Language Model (VLM), enabling direct, query-based understanding without reloading or re-encoding the original video. This approach decouples video length from inference cost, offering high amortized efficiency for multi-turn video understanding. Experiments on the LVBench benchmark show our method achieves performance comparable to state-of-the-art approaches while reducing end-to-end latency by over two orders of magnitude, opening new possibilities for interactive long-video understanding.
arXiv:2606.11948v1 Announce Type: new Abstract: High-voltage direct current (HDVC) transmission systems based on modular multilevel converters (MMCs) have become a key topology in modern power systems. The dynamics of MMCs exhibit strong multivariable coupling, constraints, and uncertainties, motivating the use of model predictive control (MPC) to enhance current regulation performance. However, MPC tuning is nontrivial and does not inherently guarantee stability or robustness, particularly in the presence of model uncertainties. This paper proposes a MPC tuning method that ensures robust performance under bounded model uncertainties. This method solves a convex linear optimization problem to compute the optimal weighting matrices Q, R, and P ensuring optimality and reproducibility. As a result, robustness is enhanced without increasing the online computation burden. The effectiveness of the method is validated through testing on a real-time digital simulator (RTDS) model of a point-to-point HVDC system. Results demonstrate improved performance compared to conventional LQR-based MPC tuning.
arXiv:2606.11986v1 Announce Type: new Abstract: Traditional HCI interaction models assume a single monolithic interface and a stable sensorimotor loop. These models fit poorly with cross-device (XVA) and ubiquitous analytics (UA), where interactive data sensemaking unfolds across multiple devices, artifacts, and people in disparate settings from the office to the factory floor. In this paper, we show how interaction in ubiquitous analytics can be modeled using distributed cognition as propagation of representational state across substrates -- minds, speech, bodies, artifacts, and devices -- rather than as traffic through a single interface. On this basis we introduce input and output channels as generalizations of the visual channels from data visualization: just as visual channels carry data through properties of the visual substrate, input and output channels carry representational state through substrates whose availability, suitability, and preferability depend on context. We demonstrate the channels and substrates framework by reanalyzing several ubiquitous, immersive, and situated analytics systems.
arXiv:2606.05608v2 Announce Type: replace Abstract: For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into static code, and manually adapt that code as requirements evolve. This paper argues that the emergence of AI agents -- systems where large language models serve as the primary reasoning engine, dynamically generating and discarding code as an instrumental resource -- constitutes a fundamental restructuring of what software is, not an incremental tool improvement. We formalize the distinction between traditional deterministic software and agentic software: in the former, code is the carrier of pre-written decision logic; in the latter, the agent itself is the software, and its decision logic is generated at runtime. We trace the historical arc from licensed software to SaaS to Agent-as-a-Service (AaaS), showing that each shift transferred additional complexity away from end-users -- with the agentic shift transferring not just operational complexity but decision-making complexity itself. We introduce Agentic Engineering as an expansion of the software engineering discipline into a new paradigm, distinct in its core object of study (agent systems rather than static source code), its control model (LLM-driven rather than human-predefined), and its human role (intent architect rather than code author). Through analysis of recent benchmark evidence including SWE-bench Verified, EvoClaw, and LangChain's multi-agent coordination studies, we demonstrate both the transformative potential of the agentic paradigm and its current limitations. We conclude with a four-stage roadmap toward self-evolving agent ecosystems and concrete recommendations for practitioners navigating this transition.
arXiv:2606.05922v2 Announce Type: replace Abstract: AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improving this harness is essential for adapting to new tasks. However, existing optimization methods typically require ground-truth validation sets, yet such labeled data is difficult to acquire in practical deployment settings. To address this problem, we introduce Retrospective Harness Optimization (RHO), a self-supervised method that optimizes the agent harness using only past trajectories. Specifically, RHO selects a diverse coreset of challenging tasks from past trajectories and re-solves them in parallel. The agent analyzes these rollouts using self-validation and self-consistency, then generates candidate harness updates and selects the most effective one by its own pairwise self-preference. We evaluate RHO across three diverse domains, spanning software engineering, technical work, and knowledge work. Notably, a single optimization round improves the pass rate on SWE-Bench Pro from 59% to 78% without any external grading. Furthermore, our analysis demonstrates that RHO effectively targets prior failure modes. As a result, the optimized harness alters the agent's behavior patterns and sustains higher accuracy during long-horizon sessions.
arXiv:2606.12071v1 Announce Type: new Abstract: LLMs are increasingly used to generate and judge scientific ideas. This makes novelty evaluation a central problem. Full idea evaluation is difficult because it often requires judging a method, its feasibility, and its empirical promise. We therefore study a cleaner upstream object: the research question (RQ). RQ generation is a prerequisite for scientific ideation, and RQs can be compared against questions pursued in real papers. We introduce RQ-Bench, a benchmark built from recent arXiv papers. For each paper, we reconstruct author-anchored RQs from its cited background, gaps, and contributions. These RQs are not the only valid questions for the same background. They are author-anchored reference points for testing novelty judgments. We evaluate model-generated RQs with standalone LLM judging, comparative LLM judging, and human expert evaluation. LLM judges consistently rate model-generated RQs as highly novel, producing a novelty mirage; in comparative evaluations, this preference becomes even stronger. Domain experts, however, reach the opposite conclusion and prefer the author-anchored reference questions. We further find that many generated RQs are narrow or source-bound, a dimension that LLM judges often miss unless explicitly tested. Overall, the contradictory novelty evaluations between LLM judges and human experts raise a serious concern about the reliability of using LLMs to assess the scientific novelty of research questions.
arXiv:2606.12162v1 Announce Type: new Abstract: Accurate modeling of tsunamis (such as those generated by landslides) requires capturing both wave dispersion in the deep ocean and wave breaking near the shore. The shallow water equations are often preferred for working with tsunamis, but neglect dispersion and may be inaccurate in scenarios where dispersive effects are significant. In this work, we develop an approach that seeks to incorporate the best aspects of both hyperbolic and dispersive models by combining either of two hyperbolic reformulations of the Serre-Green-Naghdi equations away from the shore with the non-dispersive shallow water equations near the shore. The model is discretized and implemented within the GeoClaw software, and incorporates adaptive mesh refinement as well as shared-memory parallelism. We validate it through comparison with benchmarks and real tsunami data. The results and performance compare favorably with the existing dispersive water wave solvers, including a speedup of about 2x relative to GeoClaw's existing dispersive solver for a large-scale tsunami simulation.
arXiv:2606.06904v2 Announce Type: replace Abstract: Vision-language-action (VLA) models have advanced rapidly across backbones, training recipes, and data scale, yet the action decoder, which converts the backbone's hidden state into a continuous control signal, has barely changed and remains a single-point predictor across the majority of current VLAs. Whether implemented via autoregressive token bins, L1 regression, or flow-matching denoising, the resulting decoder treats the action space as unstructured, leaving the geometric proximity of neighboring actions unexploited during training. To advance this, we introduce ActionMap, a voxel heatmap action head that drops into an existing VLA in place of its native action decoder. For each new action, the head predicts a voxel heatmap over the action space, where each voxel directly stores the probability of the corresponding action. Across LIBERO simulation and real-world Franka manipulation, our heatmap head surpasses two architecturally distinct backbones at matched training steps (e.g., +8.2% over OpenVLA-OFT's L1 regression head on the LIBERO four-suite average), converges at comparable or faster rates on both backbones, and remains markedly more data-efficient at low training data. The cross-backbone consistency indicates that action representation is a real lever for VLA performance, distinct from further backbone or recipe scaling. Project Page: https://showlab.github.io/ActionMap/.
arXiv:2606.08339v2 Announce Type: replace Abstract: Reduced-precision arithmetic offers significant opportunities to improve performance, memory usage, and energy efficiency in numerical applications, provided that numerical accuracy is preserved. This work investigates automated precision tuning through customized floating-point formats with user-defined exponent and significand sizes, enabling the emulation of emerging low-precision formats and the exploration of non-standard precision configurations within a unified mixed-precision framework. The proposed methodology, implemented in the PROMISE precision autotuning tool, combines numerical validation with a systematic search to generate program variants that satisfy user-defined accuracy requirements. To address the computational cost of this exploration, a containerized benchmarking framework supports parallel execution across multiple algorithms and parameter configurations. The approach is evaluated on a suite of numerical programs, including linear solvers and applications from the Rodinia benchmark. Results show that a substantial proportion of variables can be safely reduced to lower precision while preserving accuracy, indicating that standard double precision is often over-provisioned. These findings highlight the potential of automated precision tuning to derive efficient mixed-precision configurations tailored to application-specific accuracy requirements.
arXiv:2606.08972v2 Announce Type: replace Abstract: We analyze five-neighbor particle cellular automata whose conventional two-dimensional fundamental diagrams are multivalued, but whose mean flow is uniquely determined by introducing a second density. We first consider binary rules for which the second density is conserved, and then examine rules for which the second density is not conserved but converges asymptotically. These examples give three-dimensional fundamental diagrams in which the mean flow is determined by the particle density and the second density. We then investigate whether this single-valued structure is preserved under real-valued max-plus extensions. There are some rules where two different max-plus extensions are introduced, and numerical simulations show that both extensions preserve the same single-valued three-dimensional fundamental diagram. These observations imply that, in constructing real-valued max-plus extensions, it is important to choose the flux function and the second density consistently.
arXiv:2606.10401v2 Announce Type: replace Abstract: Spatial intelligence is a key frontier for multimodal large language models (MLLMs), enabling them to reason about the physical world from visual experience. Inspired by human spatial cognition, recent approaches construct grid-based cognitive maps from multi-frame visual inputs to maintain coherent spatial representations over time. However, limited context lengths still challenge spatial understanding, while existing methods, such as long-context modeling and external memory, often require architectural changes, memory modules, or finetuning, limiting their applicability to off-the-shelf pretrained MLLMs. This motivates a lightweight, model-agnostic method for preserving spatial information beyond the native context window. To this end, we propose a plug-and-play multi-agent framework that collaboratively constructs cognitive maps as structured spatial memory, enhancing the spatial understanding of arbitrary pretrained MLLMs without architectural modification or additional training. Our framework features local-global agent coordination, cognitive map construction with atomic commits, and cross-agent verification. Extensive experiments demonstrate that our method achieves superior performance on spatial understanding tasks while remaining fully training-free. Code will be released.
arXiv:2606.11198v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems inject external knowledge to improve LLM outputs, yet the format of injected content -- distinct from its semantic relevance -- can independently distort the model's attention distribution. We identify and formalise a phenomenon we term the structural attention tax: knowledge graph (KG) triples, due to their relational delimiters and repeated slot patterns, capture 2-3x more attention per token than semantically equivalent natural-language text ($\hat{o}$(KG) $\approx$ 0.70 vs. $\hat{o}$(neutral) $\approx$ 0.25), compressing demonstration attention by up to 42% -- regardless of whether the triples are relevant or noise. We develop a formal framework decomposing attention scores into semantic and structural components (Eq. 2), derive a compression bound (Proposition 1) connecting token-level format bias to demonstration attention loss, and show that the structural term governs how much attention is diverted while the semantic term governs whether this helps or hurts. This decoupling reveals two orthogonal axes for improving retrieval-augmented ICL: optimising retrieval quality (semantic axis) and reducing format-driven attention capture (structural axis). Empirically, across two model families (Mistral-7B, LLaMA-3-8B) and three QA benchmarks, we observe that source-task alignment dominates: task-matched BM25 retrieval achieves 58-62% on HotpotQA vs. ConceptNet's 25-27%, a >30 pp gap that dwarfs all gating strategies ($\leq$2 pp). We derive five structure-aware mitigation strategies from the framework, ranging from zero-cost prompt modifications to training-time regularisation; format flattening (S3) is validated by both accuracy and attention-level evidence from a verbalized-triple control, while structural dispersal (S1) yields mixed results that illuminate the challenges of format-level intervention.
arXiv:2606.12173v1 Announce Type: cross Abstract: Randomness amplification, the task of extracting uniform private bits from biased seeds that may be partly known by a malicious third party, is of central importance in cryptography. The highest security in this task is provided by a class of quantum protocols known as device-independent, which however are challenging to integrate into scalable devices. Semi-device-independent (SDI) protocols are a promising alternative that guarantees security under few natural assumptions, such as bounds on the amount of energy used by the devices. Here, we provide the first demonstration of SDI randomness amplification on an integrated silicon photonic chip, achieving a throughput rate of 20 Mbps suitable for practical applications. This rate is achieved through a novel technique for SDI entropy certification, which delivers strictly tighter von Neumann entropy bounds compared to existing methods and remains valid even if the preparation and measurement devices share quantum correlations. Overall, the methods developed in this work enable the integration of SDI technology into portable telecom devices, opening up a new generation of quantum cryptographic hardware.
arXiv:2606.10490v2 Announce Type: replace Abstract: A systematic comparison between VMEC and HINT equilibrium calculations has been carried out for Large Helical Device plasmas to clarify the influence of the assumption of the nested flux surfaces at finite beta. Three vacuum magnetic-axis configurations, $R_{\rm axV} = \SI{3.53}{\, m}$, $\SI{3.60}{\, m}$, $\SI{3.85}{\, m}$, are examined for the beta values on the axis in the range $\beta_0 \in [0.0\%, 5.0\%]$. The magnetic-axis position, the rotational transform on the axis, and the plasma volume enclosed by the last closed flux surface are compared between the two codes. At low-$\beta_0$, VMEC and HINT give consistent equilibria, indicating that the nested flux surfaces are largely preserved. Above a configuration-dependent critical $\beta_0$, however, the two solutions begin to diverge, indicating that the nested flux surfaces assumption is compromised. In HINT, the enclosed plasma volume decreases at higher beta because the stochastic magnetic field evolves near the plasma edge, whereas VMEC cannot represent this flux surface breaking due to its assumption of nested flux surfaces. These results show that the 3D equilibrium responses in LHD equilibria become increasingly important from inward- to outward-shifted configurations, mainly through Pfirsch-Schl\"uter current-driven perturbations of the magnetic field and the resulting edge stochasticity.
arXiv:2606.10508v2 Announce Type: replace Abstract: Internet of Things (IoT) deployments combine heterogeneous, resource-constrained devices with weak security configurations, exposed services, limited logging, patching constraints, and long lifecycles. Signature- and threshold-based controls remain useful baselines, but they are insufficient as standalone mechanisms in dynamic IoT networks. Likewise, offline artificial intelligence (AI) benchmark performance alone does not establish operational deployability. This article presents a conceptual framework and research agenda for a Linux-based IoT edge gateway that combines resource-aware flow-level AI-assisted risk scoring, event-level explainability, and bounded mitigation through eBPF/XDP. The controller applies reversible, time-limited actions subject to critical-device safeguards, updates packet-level enforcement state, and records structured logs. The architecture separates complex reasoning and policy control in user space from concise packet-handling decisions in the kernel. It also defines a future hardware-aware evaluation pathway covering detection quality, resource cost, response timing, rollback behaviour, and legitimate-traffic preservation. The paper does not report new experimental measurements or claim measured superiority or completed real-time performance.
arXiv:2606.10615v2 Announce Type: replace Abstract: Collaborative computation across organizations is often constrained by the need to process sensitive data and proprietary code without exposing them to untrusted infrastructure or participants. Cryptographic approaches such as fully homomorphic encryption and secure multi-party computation provide strong confidentiality but remain impractical for general workloads due to their extreme computational cost. We present the Two-Way Confidential Virtual Machine (2cVM), a two-layer architecture that pairs a hardware trusted execution environment with an intra-workload isolation layer. Unlike regular Confidential Virtual Machines, 2cVM enforces mutual isolation between co-resident workloads, ensuring that participants retain control over their data and code. All computation in 2cVM is governed by a Commitment Manifest that enumerates participants, component composition, permitted data channels, and authorized outputs; the manifest is locked to the VM and incorporated into attestation evidence, making the policy immutable and independently verifiable throughout the VM's lifetime. A proof-of-concept realization combines AMD SEV-SNP for hardware protection with the WebAssembly Component Model for fine-grained sandboxing of participant code. Evaluation on commodity hardware across four benchmark classes shows that the two isolation layers do not accumulate linearly: once a workload executes inside the WebAssembly sandbox, the marginal cost of enabling hardware memory protection is small. Overhead is workload-dependent, governed primarily by memory access pattern, ranging from negligible for sequential workloads to approximately 2x for irregular, pointer-chasing access patterns. These results indicate that 2cVM provides a practical and verifiable foundation for privacy-preserving collaborative computation.
arXiv:2606.10639v2 Announce Type: replace Abstract: Autonomous visual interception of agile aerial targets is challenging due to unpredictable target motion, limited sensing, and the strong coupling between target visibility and interceptor maneuverability. Most existing strapdown-camera interception methods preserve visibility using conic line-of-sight (LOS) constraints that keep the target near the image center. While safe, such symmetric constraints unnecessarily restrict maneuverability and can significantly reduce the usable thrust for pursuit. Motivated by the observation that aggressive FPV pilots do not maintain equal visibility margins in all image directions, this paper proposes a Planar-Sector Line-of-Sight (PS-LOS) guidance framework for autonomous interception using a lifting-wing quadcopter equipped with only a strapdown monocular camera. PS-LOS tightly constrains lateral image error while relaxing longitudinal image error within a safe field-of-view margin, preserving visibility while releasing maneuverability for acceleration-intensive pursuit. Under the lifting-wing quadcopter model, PS-LOS provides nearly 50% more available thrust near the LOS direction than conventional conic LOS constraints. To realize LOS-only interception without direct depth measurements, a delay-compensated state-estimation framework and a nonlinear guidance-and-control architecture are developed for lifting-wing quadcopters. Extensive outdoor flight experiments demonstrate autonomous interception of agile targets exhibiting large-amplitude, high-frequency, and unpredictable motion under real wind disturbances. The proposed system achieves successful interceptions at ranges up to 138 m while maintaining continuous visual tracking throughout the engagement. The results validate PS-LOS as a visibility-preserving, maneuverability-aware guidance framework for long-range visual interception of agile aerial targets.
arXiv:2606.10775v2 Announce Type: replace Abstract: Unsupervised building change detection aims to learn building-change masks from unlabeled bi-temporal remote sensing images. Existing label-free methods often follow a discrepancy-to-mask paradigm, directly using temporal differences, frozen foundation-model responses, prompt-based outputs, or post-processing results as final change maps. Although these strategies provide annotation-free cues, they do not learn a task-specific building-change detector and remain vulnerable to the gap between generic temporal discrepancies and building-defined structural changes. In practice, such discrepancies are often noisy and task-irrelevant, as appearance shifts, registration errors, and non-building modifications can produce strong but misleading responses. To address this problem, we propose SST-CD, a spatially selective self-training framework that reformulates fully label-free building change detection as end-to-end detector learning under noisy pseudo supervision. SST-CD uses temporal discrepancies as candidate pseudo labels and trains the detector only on spatially reliable pixels, whose reliability is estimated by a local consistency criterion that filters inconsistent regions from supervision. To further stabilize noisy self-training, a lightweight feature adapter recalibrates bi-temporal features, while a prototype-based decoder produces compact change and no-change representations. Experiments on LEVIR-CD, WHU-CD, and DSIFN-CD show that SST-CD achieves F1 scores of 83.08%, 91.69%, and 86.60%, respectively, outperforming existing unsupervised and label-free baselines.
arXiv:2606.10848v2 Announce Type: replace Abstract: Data-driven modeling shows significant promise for faster-than-real-time forecasting of fluid flows. For real-world engineering applications (e.g., flow control), models must contend with limited, imperfect, and incomplete experimental measurements. In this work, we present an analysis of data-driven surrogate models trained to forecast the time-evolution of experimentally measured cylinder wakes in the subcritical vortex shedding regime. Using a dataset of two-dimensional, two-component particle image velocimetry measurements, we train fully convolutional neural networks, U-Nets, Fourier neural operators, and dynamic mode decomposition-based models to forecast the development of experimentally measured velocity fields. To characterize data-driven approaches contending with transient flow features and limited, imperfect observations, the development of predictions over extended forecast horizons is examined at a fixed Reynolds number (Re = 590). Next, models are trained at a range of Reynolds numbers (Re = 230 to Re = 2920) to investigate the impact of increasingly turbulent and three-dimensional flow phenomena, and the challenges associated with measuring them, on forecast quality. We find that experimentally trained surrogate models can provide meaningful predictions over short time horizons, propagate low-frequency dynamics over longer forecast periods, and achieve faster-than-real-time evaluation. However, the data-driven models struggle to preserve transient flow features and high-frequency energy content when faced with noisy measurements and incomplete state observations. This emphasizes the underlying challenges that remain for data-driven modeling approaches to effectively contend with fluid dynamics in real-world engineering applications, where observations are often imperfect and limited.
arXiv:2606.10968v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning. However, existing PPO-style trust-region mechanisms remain position-agnostic by enforcing uniform thresholds across all tokens independently. This pointwise treatment conflicts with autoregressive generation in two critical ways. First, uniform thresholds ignore autoregressive asymmetry. Early-stage deviations produce compounding sequence-level drift, causing static thresholds to under-regulate early divergence and excessively constrain late-stage exploration. Second, evaluating token-level divergence in isolation overlooks cumulative prefix drift, granting the same divergence allowance regardless of how far the conditioning history has already deviated from the rollout policy. To address this limitation, we propose CPPO (Cumulative Prefix-divergence Policy Optimization), a token-level masking rule that aligns updates with a finite-horizon policy-improvement bound via two coupled mechanisms. First, a position-weighted threshold imposes stricter limits at early positions whose effects persist longer, relaxing constraints for late-stage tokens. Second, a cumulative prefix budget tracks historical deviations, dynamically restricting further token-level deviation to prevent compounding errors along the prefix. Empirically, CPPO enhances training stability and significantly improves reasoning accuracy across various model scales.
arXiv:2606.11021v2 Announce Type: replace Abstract: In academic publishing, names connect scholars to their work. When scholars change their names, including for marriage, academic recognition, or gender transition, they may lose credit for past publications. However, despite significant impacts on citation accuracy and researcher well-being, no existing studies examine how naming policies in computer science serve researchers who change their names. We use a mixed-methods approach combining surveys, interviews, and large-scale citation analysis of papers from eight major computer science venues from 2019-2025. We document the multi-year advocacy effort that established the first name change policies, identify implementation barriers including incomplete publisher updates and months-long processing delays. Researchers continue being cited with misparsed and incorrect names despite publisher updates. When these citation errors happen, interviewees report significant mental health impacts, including stress, anxiety, and safety risks. Empirically, we find that venues with accessible and visible name change policies have significantly fewer citation errors compared to inaccessible policies (899 vs. 996 errors per 1,000 papers). Our annotation analysis shows that deadnaming of transgender researchers in citations decreased by 92% from 2019 to 2024. Our findings demonstrate the importance of inclusive publishing policies, for which name change policy advocacy led by trans researchers has been a significant driver. We recommend that venues adopt proactive visible name change policies, support queer advocacy groups, and improve publication infrastructure to build an inclusive publishing landscape. The accompanied toolkit to check errors in bibliographic latex file is available here https://github.com/pranav-ust/cite-updater.
arXiv:2606.11074v2 Announce Type: replace Abstract: With the widespread deployment of Multimodal Large Language Models (MLLMs) in social interaction, understanding and controlling their behavior under complex personality conditions is essential. This paper introduces explicit personality conditioning and establishes a systematic evaluation framework encompassing single-personality induction, multi-personality induction, and personality switching. Experiments show that personality induction improves image captioning performance but can impair performance on tasks requiring precise reasoning, such as visual question answering (VQA). Balancing and residual effects are observed during multi-trait composition and dynamic switching, indicating that model behavior is co-modulated by both previous and current personality constraints. Existing prompt-based personality induction methods show limited transferability to multimodal settings. Our work reveals the dynamic and complex nature of personality modeling in MLLMs and underscores the need for robust, tailored methods for personality induction and evaluation. The code will be released when the paper is accepted.
arXiv:2606.11118v2 Announce Type: replace Abstract: We study a dynamic assortment problem on a two-sided service platform with incomplete information and heterogeneous customers in a discrete-time setting. In each period, a customer arrives seeking service, and the platform chooses an assortment of sellers to display. The customer then proposes a transaction to at most one seller in the assortment according to a multinomial logit choice model. After a fixed number of periods, sellers review the proposals they have received and each chooses at most one customer according to another multinomial logit choice model, after which the cycle repeats. A key challenge is that the platform does not know the choice-model parameters of either customers or sellers in advance. To our knowledge, this is the first study of a dynamic assortment problem in which both sides' choice parameters are unknown. We develop a data-driven algorithm that learns these parameters while optimizing the platform's objective over time. We evaluate performance using regret, which measures revenue loss relative to a clairvoyant benchmark that knows all parameters and customer arrivals in advance. We show that the algorithm's worst-case regret grows polylogarithmically over time, and we derive a matching lower bound, establishing its rate optimality.