# Research Papers — 2026-07 · bundle page 204 of 222 > Full-text markdown of papers #10151–10200 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/204 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/203.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/205.md) ### GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech Authors: Antonis Asonitis, Francesco Verdini, Aref Farhadipour, Vijeta Avijeet, Pierre-Edouard Honnet, Marzieh Razavi, Juan Pablo Zuluaga Gomez Published: 2026-07-02 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.02633v1 We present GRAFT, a per-word pronunciation conditioning mechanism for text-to-speech neural codec language modeling. Existing systems reach high intelligibility and naturalness but inherit the ambiguity of text and mispronounce rare proper nouns, loanwords and technical terms. Even phoneme-conditioned models offer no direct acoustic handle for per-word pronunciation. GRAFT controls the pronunciation of a chosen word from a short spoken sample of it, encoded with the model's own speech tokenizer and bound to the word's position in the prompt. Voice conversion during training-data construction disentangles the hint speaker from the target speaker, so the hint may come from any voice while the output stays in the target voice. In a blind English listening study, human raters rank GRAFT first by a clear margin, judging its rendering of the difficult word closest to a reference recording of that word. On a five-language objective benchmark, GRAFT reduces target-word phoneme error rate by 22-39% over the identical text-only backbone and outperforms competitive open-source zero-shot systems, both phoneme- and text-conditioned, on target-word pronunciation, while preserving speaker similarity and naturalness. --- ### QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting Authors: Shah Nawaz Haider, Steve Austin, Arnab Barua, Sarowar Morshed Shawon, Hadaate Ullah Published: 2026-07-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.02632v2 Time-series forecasting supports decisions in finance, en-ergy, transportation, public health, and industrial monitoring. Recent foundation models improve transfer across forecast-ing tasks, but many depend on centralized data and Trans-former attention, which restricts their use for long, high-di-mensional, and privacy-sensitive signals. This paper presents QuantFlow, a probabilistic forecasting framework that com-bines inverted sequence embedding, bidirectional Mamba state-space decoders, quantile regression, and federated learning. Each variable is embedded over the complete ob-servation window, processed in forward and reverse direc-tions, and projected to five conditional quantiles. TSMixup expands temporal diversity through Dirichlet-weighted inter-polation while preserving sequence structure. Experiments cover cryptocurrency, traffic, electricity, Electricity Trans-former Temperature, influenza, and weather data. QuantFlow obtains mean squared errors of 0.2834 on ETTm1 and 0.2218 on Weather, and a 20-client non-IID deployment retains use-ful accuracy after three communication rounds without cen-tralizing raw records. The results indicate that selective state-space modelling is a promising basis for scalable, uncer-tainty-aware, and privacy-conscious time-series prediction, while also revealing limitations on irregular epidemiological signals and long-horizon generalization. --- ### Fine-Grained Computation Offload for Off-the-Shelf Servers in Tens of Lines Authors: Bojie Li Published: 2026-07-02 Categories: cs.DC, cs.AI, cs.OS arXiv: https://arxiv.org/abs/2607.02630v1 Hardware accelerators now sit on the critical path of online serving. GPUs, FPGAs, and increasingly remote services such as hardware security modules, post-quantum KEMs, and inference servers. For fine-grained offloads (microseconds to a few milliseconds) the classic responses to the resulting stall both fail: a context switch costs as much as the offload, and a busy-wait burns the core. Overlapping the offload with other requests is the fix, and prior systems obtain it by adding concurrency: an async-framework rewrite, a new runtime or dataplane OS, or a hand-tuned point integration. We observe that the concurrency already exists: serving concurrent requests is suspending and resuming them, so every server ships the machinery overlap needs. Overlap is then a routing problem, not a rewrite problem: submit the offload to an executor, suspend the request with the server's own deferred-response primitive, resume it on completion. Across ten off-the-shelf servers spanning every production concurrency model, this recipe takes 22-138 lines added, at most one modified, and recovers 1.2-5.4x on real hardware; the server's concurrency model and the offload's weight predict both numbers in advance, and the win is bounded by device throughput and the server's own overlap capacity. At the limit, an LD_PRELOAD fiber runtime injects the reroute into an unmodified thread-per-connection binary (17.3x) within a characterized envelope. Rerouting suspends run-to-completion atomicity; a measured taxonomy confines the hazard to unlocked shared aggregates, and a transparent page-protection detector guards exactly those, validated on stock Redis. --- ### SE-UNet: Singular Equivariant Imaging for Real-World Constrained Generation Authors: Kanishk Awadhiya Published: 2026-07-02 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.02628v1 While diffusion models have revolutionized image synthesis, their application to real-world inverse problems is often hampered by the need for massive datasets and the difficulty of imposing strict physical constraints. In this work, we introduce \textbf{SE-UNet} (Singular Equivariant UNet), a framework designed to solve ill-posed imaging tasks without extensive pre-training. By treating generation as an optimization problem constrained by geometric equivariance ($D_4$ group) and singular value gating, SE-UNet effectively standardizes the solution space. We demonstrate that these strong inductive biases allow for state-of-the-art zero-shot inpainting results (80\% missing pixels) on CIFAR-10. Our method surpasses Deep Image Prior (DIP) baselines by over 4 dB in PSNR and exhibits a characteristic "singular snap" convergence -- rapidly locking into the signal manifold. SE-UNet thus offers a data-efficient pathway for constrained generation, aligning with the ReALM-GEN goal of bridging theoretical priors with practical deployment. --- ### Schedulable Job-Level Dependencies for Cause-Effect Chains via Graph Neural Networks Authors: Silviu S. Craciunas, Christian Hakert, Jian-Jia Chen, Zdeněk Hanzálek, Paul Pop Published: 2026-07-02 Categories: cs.SE, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2607.02624v1 Modern automotive software architectures comprise large sets of mixed-criticality functions executing on shared multi-core platforms with strict real-time and end-to-end timing requirements. Sensor-to-actuator data propagation in such systems is typically expressed via cause-effect chains with worst-case data-age budgets. Job-level dependencies (JLDs) have been introduced to provide a schedule-agnostic mechanism for bounding the data age independently of the underlying scheduler. The state-of-the-art methods for synthesizing JLDs, however, do not check whether the produced JLDs are enforceable under a concrete scheduling policy or jointly schedulable at the system level. In this paper we propose the first machine-learning-based JLD synthesis method, built around a two-level Graph Neural Network with temperature-controlled sampling that learns the structural patterns connecting cause-effect chain configurations to their JLD solutions. Since learned outputs may not be correct by construction, we embed the GNN in a novel Generate-and-Verify architecture in which a safe DP data-age checker, together with a per-chain EDF feasibility checker and a system-level demand-bound test, accept or reject each candidate. We show that the ML-based generator substantially outperforms the original greedy heuristic while achieving orders-of-magnitude lower synthesis time, demonstrating that learned structural priors can effectively replace exponential propagation-tree enumeration on this class of real-time scheduling problems. --- ### Evaluating Time Series Foundation Models for Electricity Price Forecasting: Contamination Risk, Distributional Shifts, and Covariate Dependence Authors: Zhenghua Pan, Ahmed Aziz Ezzat Published: 2026-07-02 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2607.02623v1 Time series foundation models (TSFMs) have shown strong zero-shot forecasting performance, but their generalization in covariate-driven, non-stationary settings is underexplored. Electricity price forecasting (EPF) presents a challenging testbed due to complex temporal dependencies, distributional shifts, and strong reliance on structural and contextual information. We propose a two-dataset-benchmarking framework for EPF to mitigate contamination risk and enable fair evaluation of TSFMs. We examine key aspects of EPF including point and probabilistic forecasting performance, tail behavior, price spikes, and comparisons against domain-specific methods. We find that TSFMs are highly competitive and often outperform general-purpose baselines. Yet, their performance depends critically on covariate support, and they do not consistently surpass domain-specific methods tailored to EPF. Interestingly, simple ensembles of TSFMs and domain-specific methods appear to have significant potential, suggesting that the two approaches capture complementary predictive information. --- ### COMET: Combinatorial Optimization for Multiplex Editing Targets Via Constraint-Preserving QAOA Authors: Priyansh Singhal, Sumit Maheshwari, Piyush Joshi Published: 2026-07-02 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2607.02622v1 Multiplex CRISPR-Cas9 gene editing requires selecting one guide RNA per target gene subject to cross-gene interactions: a constrained combinatorial problem that can be formulated as a Quadratic Unconstrained Binary Optimization (QUBO) and solved via the Quantum Approximate Optimization Algorithm (QAOA). The one-hot per-gene constraint is conventionally enforced by adding quadratic penalty terms to the cost Hamiltonian, but penalty coefficient selection is heuristic and penalties amplify hardware noise. An alternative is to enforce the constraint structurally via the XY-mixer, which preserves feasibility by construction. We present COMET, a systematic comparison of penalty-based and XY-mixer QAOA on a three-gene, twelve-qubit multiplex editing instance targeting the immune-checkpoint genes PDCD1, LAG3, and HAVCR2. In simulation, the XY-mixer exceeds 95% probability of the optimum by QAOA depth p=3, while three penalty variants spanning an order of magnitude in penalty coefficient remain below 6% at every depth. On IBM's ibm_kingston (Heron r2) processor, the XY-mixer's simulator-hardware energy gap stays within |0.8| across all depths, while the worst-tuned penalty variant's gap reaches +53.9. We provide an honest account of where the structural guarantee partially breaks under gate-level noise. The twelve-qubit instance is classically trivial; our contribution is a methodological comparison of constraint-enforcement strategies in a biologically motivated domain, with real-hardware validation. --- ### WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory Authors: Hanlin Wang, Hao Ouyang, Qiuyu Wang, Wen Wang, Qingyan Bai, Ka Leong Cheng, Yue Yu, Yixuan Li, Yihao Meng, Zichen Liu, Yanhong Zeng, Yujun Shen et al. Published: 2026-07-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.02517v1 We present WorldDirector, a highly controllable video world model framework designed for persistent dynamic object memory and unrestricted viewpoint exploration. Unlike existing world models that entangle physical dynamics with pixel rendering and rely on continuous visual observation to sustain motion, our framework explicitly decouples semantic motion orchestration from visual generation. By leveraging an LLM to coordinate 3D trajectories with camera movements and subsequently employing these orchestrated trajectories as control signals for video generation, our approach ensures strict physical logic and appearance stability, successfully preserving the exact visual identities of dynamic entities even when they re-enter the scene after prolonged periods out of view. Experimental results demonstrate that our method supports the synthesis of complex and extended events with unprecedented controllability and persistent dynamic object memory. Project Page: https://worlddirector.github.io/ --- ### Alignment Is All You Need For X-to-4D Generation Authors: Qiaowei Miao, Kehan Li, Yawei Luo, Yi Yang Published: 2026-07-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.02516v1 Generative diffusion models excel at synthesizing high-quality images, videos, and 3D content under multimodal control. However, arbitrary user-defined modality-to-4D (X-to-4D) generation remains challenging due to the high cost of constructing diverse datasets and the limited scalability of existing methods. This paper presents Align4D, a flexible framework that translates any-modal input into coherent video-3D pairs, using video to guide 4D motion and 3D data to shape 4D geometry. Align4D introduces three key techniques: (1) Object Distance Alignment, which searches Video-Aligned and Multiview-Aligned Object Distances (VAOD/MAOD), respectively, to reconcile 4D renderings with video and the priors of multiview diffusion models; (2) Motion-Geometry Joint Alignment, which constrains known and unknown views through synchronized video and 3D inputs, ensuring consistent 4D generation; and (3) Asynchronous Optimization, which decouples Gaussian attribute and deformation network training to enhance motion and geometry fidelity. We further propose the X4D dataset, which integrates prompt, image, video, and 3D data for benchmarking. Experiments on X4D and Consistent4D demonstrate that Align4D achieves state-of-the-art quality and consistency in X-to-4D generation. Project page: https://miaoqiaowei.github.io/Align4D/. --- ### PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation Authors: Haofei Xu, Rundi Wu, Philipp Henzler, Nikolai Kalischek, Michael Oechsle, Fabian Manhardt, Marc Pollefeys, Andreas Geiger, Federico Tombari, Michael Niemeyer Published: 2026-07-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.02515v1 State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures and loss functions, or compress geometry into latent spaces in order to leverage pre-trained latent diffusion models. In this work, we show that such architectural overhead and intricate loss formulations are unnecessary. We introduce a minimalist pixel-space Diffusion Transformer, built on a plain ViT, that operates directly on raw 3D point map patches and is conditioned on image tokens from a pre-trained DINOv3. Unlike existing latent diffusion approaches, we train our diffusion backbone entirely from scratch, eliminating the need for point map tokenizers. Despite its simplicity, our approach surpasses complex latent-based diffusion models while remaining significantly simpler than hybrid alternatives. Notably, it produces sharper geometric structure and is more robust in highly ambiguous regions, such as transparent objects. --- ### Distributed Attacks in Persistent-State AI Control Authors: Josh Hills, Ida Caspary, Asa Cooper Stickland Published: 2026-07-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.02514v2 As AI coding agents become more autonomous, they increasingly ship code iteratively, with the codebase persisting across sessions. This persistence creates a new attack surface: a misaligned or prompt-injected agent can distribute attacks across pull requests (PRs) and time its payload for the PR with the best natural cover. To study the resulting dynamics, we introduce Iterative VibeCoding, a setting for AI control, the study of safely deploying capable but potentially untrusted AI. In Iterative VibeCoding, a coding agent builds software over a sequence of PRs in a persistent codebase while pursuing a covert side task. Our benchmark includes two task families: CLI tools and Flask web services, across 20 total task variations. We use Claude Sonnet 4.5 as the attack agent and GPT-4o as the monitor. We compare gradual attacks, which distribute the side task across PRs, against non-gradual attacks concentrated in a single PR. No single monitor is robust to both: which strategy evades best (success while evading the monitor) depends on the monitor type, so a defender cannot close off both gradual and non-gradual attacks with any one monitor. High evasion (>= 65%) generalizes across model attack agent backends (Sonnet 4.5, Gemini 3.1 Pro, Kimi K2.5), confirming this is a property of the persistent-state attack surface rather than a single model's capability. Evasion also remains high across state-of-the-art monitor models and the gap between gradual and non-gradual evasion widens for more capable models. We introduce a stateful link-tracker monitor that tracks suspicious buildup across PRs. On both task families, it detects gradual attacks substantially better than diff monitors that merely see more accumulated history. Combining this stronger monitor with trajectory monitors in a four-monitor ensemble reduces gradual-attack evasion from 93% under the weakest standard diff monitor to 47%. --- ### LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning Authors: Matteo Boglioni, Thibault Rousset, Siva Reddy, Marius Mosbach, Verna Dankers Published: 2026-07-02 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.02513v2 LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal methods. Unlearning has emerged as a promising solution, with state-of-the-art (SOTA) methods often following a localize-first, unlearn-second paradigm that targets specific model parameters. However, existing benchmarks evaluate unlearning solely at the output level, leaving open the question of whether unlearning truly erases knowledge from a model's parameters or merely obfuscates it, a concern reinforced by the success of resurfacing attacks. To bridge this gap, we introduce LACUNA: the first unlearning testbed with ground-truth parameter-level localization. LACUNA injects PII of synthetic individuals into predefined parameters of 1B and 7B OLMo-based models via masked continual pretraining, enabling direct evaluation of whether unlearning targets the weights responsible for knowledge storage. We use LACUNA to benchmark current SOTA unlearning methods and find that, despite strong output-level performance, existing methods are highly imprecise and susceptible to resurfacing attacks. We further show that when localization is successful, even a simple gradient-based unlearning method achieves strong erasure and robustness to resurfacing attacks, highlighting the importance of precise unlearning. We release LACUNA to complement behavioral evaluations and drive further advances in robust, localization-based unlearning. --- ### LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning Authors: Matteo Boglioni, Thibault Rousset, Siva Reddy, Marius Mosbach, Verna Dankers Published: 2026-07-02 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.02513v1 LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal methods. Unlearning has emerged as a promising solution, with state-of-the-art(SOTA) methods often following a localize-first, unlearn-second paradigm that targets specific model parameters. However, existing benchmarks evaluate unlearning solely at the output level, leaving open the question of whether unlearning truly erases knowledge from a model's parameters or merely obfuscates it, a concern reinforced by the success of resurfacing attacks. To bridge this gap, we introduce LACUNA: the first unlearning testbed with ground-truth parameter-level localization. LACUNA injects PII of synthetic individuals into predefined parameters of 1B and 7B OLMo-based models via masked continual pretraining, enabling direct evaluation of whether unlearning targets the weights responsible for knowledge storage. We use LACUNA to benchmark current SOTA unlearning methods and find that, despite strong output-level performance, existing methods are highly imprecise and susceptible to resurfacing attacks. We further show that when localization is successful, even a simple gradient-based unlearning method achieves strong erasure and robustness to resurfacing attacks, highlighting the importance of precise unlearning. We release LACUNA to complement behavioral evaluations and drive further advances in robust, localization-based unlearning. --- ### Program-as-Weights: A Programming Paradigm for Fuzzy Functions Authors: Wentao Zhang, Liliana Hotsko, Woojeong Kim, Pengyu Nie, Stuart Shieber, Yuntian Deng Published: 2026-07-02 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.02512v1 Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking search results by intent, and are increasingly outsourced to large language model APIs at the cost of locality, reproducibility, and price. We propose fuzzy-function programming: compiling such a function from a natural-language specification into a compact, locally-executable neural artifact. We instantiate this paradigm with Program-as-Weights (PAW), in which a 4B compiler trained on FuzzyBench, a 10M-example dataset we release, emits parameter-efficient adapters for a frozen, lightweight interpreter. A 0.6B Qwen3 interpreter executing PAW programs matches the performance of direct prompting of Qwen3-32B, while using roughly one fiftieth of the inference memory and running at 30 tokens/s on a MacBook M3. PAW reframes the foundation model from a per-input problem solver into a tool builder: invoked once per function definition, it produces a small reusable artifact whose subsequent calls per function application are cheap and offline. --- ### Online Safety Monitoring for LLMs Authors: Mona Schirmer, Metod Jazbec, Alexander Timans, Christian Naesseth, Maja Waldron, Eric Nalisnick Published: 2026-07-02 Categories: cs.AI, cs.CL, cs.LG, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2607.02510v1 Despite alignment training, LLMs remain prone to generating unsafe outputs at deployment time. Monitoring outputs online and raising an alarm when safety can no longer be assumed is therefore critical. We study a simple real-time monitor that turns a verifier signal from an external model into an alarm decision by thresholding, with the threshold calibrated via risk control. In experiments on mathematical reasoning and red teaming datasets, we show that this simple design is competitive with more advanced monitors based on sequential hypothesis testing. --- ### ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning Authors: Yanjun Zhao, Ruizhong Qiu, Tianxin Wei, Yuanchen Bei, Zhining Liu, Lingjie Chen, Ismini Lourentzou, Hanghang Tong, Jingrui He Published: 2026-07-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.02509v1 Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications. Although recent LLMs support increasingly long context windows, they often fail to use relevant evidence that is already present in the input, revealing a gap between context access and effective context utilization. In this work, we propose Recursive Evidence Replay as LLM Harness for Long-Context Reasoning (RECONTEXT), a training-free inference method for improving long-context reasoning. RECONTEXT uses model-internal relevance signals to construct a query-conditioned evidence pool and replays it before final generation while preserving the full original context. This recursive selection process separates evidence organization from answer generation without training, external memory, or context pruning. We also provide a theoretical analysis based on associative memory, which characterizes the context as a memory store, the question as a retrieval cue, attention as cue-trace association, and replay as trace reactivation. Experiments on eight long-context datasets with 128K context length show that RECONTEXT consistently improves evidence utilization across Qwen3-4B, Qwen3-8B, and Llama3-8B, achieving the best average rank on all three backbones. Code is available at https://github.com/Yanjun-Zhao/ReContext. --- ### From SRA to Self-Flow: Data Augmentation or Self-Supervision? Authors: Dengyang Jiang, Mengmeng Wang, Harry Yang, Jingdong Wang Published: 2026-07-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.02508v1 Representation alignment has become an effective way to accelerate diffusion transformer training and improve generation quality. Recent self-alignment methods, such as SRA and Self-Flow, further remove the dependency on external pretrained encoders by constructing alignment within the diffusion model itself. However, the mechanism behind the improvement from SRA to Self-Flow, dual-time scheduling, remains under-examined: Self-Flow attributes its gain to interactions between tokens at different noise levels, where cleaner tokens help infer noisier ones. In this work, we revisit this explanation and ask whether the gain instead comes from data augmentation along the noise dimension. To disentangle these factors, we introduce Attention Separation, which preserves the same dual-timestep input as Self-Flow while blocking attention between tokens assigned to different noise levels. Surprisingly, removing such interaction does not degrade performance and can even improve it, suggesting that the improvement from SRA to Self-Flow mainly comes from data augmentation. Furthermore,We show that Attention Separation itself provides an augmentation effect by splitting a single image into multiple effective training parts to expand the training data. Based on these observations, we combine self-representation alignment with dual-timestep and attention-separation augmentation, and demonstrate the effectiveness of this design on ImageNet. --- ### What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates Authors: Arman Ghaffarizadeh, Danyal Mohaddes, Aliakbar Izadkhah, Shahriar Noroozizadeh Published: 2026-07-02 Categories: cs.AI, cs.CL, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2607.02507v1 LLM agents will increasingly act in socially structured settings where role, audience, and relational context can shape what is advantageous or costly to say. We study whether such social structure, without any explicit objective in the prompt, changes what an agent expresses publicly relative to an off-the-record (OTR) channel elicited under the same condition. We introduce a dual-channel debate framework in which agents produce public utterances that enter the shared history alongside OTR responses that are recorded but never shown to the other participant. Across 10 models, 3 scenarios, and 5 variations within each scenario, alignment-inducing settings produce systematic public-OTR divergence in the targeted agent, with its decision divergence rising from a $\sim$3% baseline to roughly 40%. The effect is consistent across four aggregate analyses: stance, semantic similarity, natural language inference, and survey responses. In some cases, the OTR response explicitly attributes public accommodation to relational pressures, such as career risk or sponsorship obligation. The findings suggest that agent evaluation should extend beyond explicit goals and detect emergent objectives. We present a dual-channel evaluation framework and complementary behavioral measures that operationalize this assessment. --- ### Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas Authors: Yuxuan Li, Lingxi Xie, Xinyue Huo, Jihao Qiu, Jiacheng Shao, Pengfei Chen, Jiannan Ge, Kaiwen Duan, Qi Tian Published: 2026-07-02 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.02504v1 Long-form TV dramas present a formidable challenge for comprehensive video understanding, where deciphering complex storyline often relies on \textbf{speaker recognition}, the task of accurately attributing each spoken utterance to its respective character. In this paper, we advance this field through two primary contributions. (1) We introduce \textbf{DramaSR-532K}, a large-scale benchmark comprising 532K annotated dialogue lines across more than 900 unique characters, necessitating the integration of auditory, linguistic, and visual cues for speaker recognition. (2) We propose \textbf{DramaSR-LRM}, a robust approach built upon a large reasoning model (LRM). DramaSR-LRM is designed to autonomously aggregate contextual evidence via multimodal tool-use, synthesizing diverse inputs to achieve high-fidelity attribution. Experimental results demonstrate that DramaSR-LRM significantly outperforms existing baselines, particularly on short utterances where acoustic biometrics are inherently unreliable. \textit{All the data and code will be made publicly available at the project page: https://www.github.com/198808xc/DramaSR-LRM.} --- ### DemoPSD: Disagreement-Modulated Policy Self-Distillation Authors: Yunhe Li, Hao Shi, Wenhao Liu, Mengzhe Ruan, Hanxu Hou, Zhongxiang Dai, Shuang Qiu, Linqi Song Published: 2026-07-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.02502v3 On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access. However, recent studies have found that the teacher's dense token-level supervision, conditioned on privileged information, can lead to overfitting to in-domain patterns, suppress exploration, and hurt cross-domain generalization, while also introducing a more fundamental issue: *privileged information leakage*, where the student encodes answer-dependent shortcuts that are unavailable at test time. We introduce **DemoPSD**, a novel framework that resolves such problems through the idea of *selective adoption of teacher guidance*. Instead of fitting the full teacher distribution, DemoPSD steers the student toward a *reverse-KL barycenter target*, a weighted geometric combination of the teacher and student distributions, that naturally balances learning from the teacher with preserving the student's own reasoning capacity. We measure the difference between their distributions and use such a discrepancy to adaptively control the blending at each token position. We provably show that DemoPSD achieves **(1)** *leakage attenuation*, i.e., effective mitigation of privileged information leakage; and **(2)** *exploration preservation*, i.e., preservation of exploration capacity under dense token-level distillation. Extensive experiments on SciKnowEval across four scientific fields show that DemoPSD outperforms both GRPO and SDPO while maintaining higher training entropy and robustly generalizing to out-of-distribution GPQA benchmarks. --- ### Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots Authors: Ling Xu, Borui Li, Hao Wu, Chuyu Han, Xiangyu Li, Mohan Hua, Shiqi Jiang, Ting Cao, Chuanyou Li, Sheng Zhong, Shuai Wang Published: 2026-07-02 Categories: cs.RO, cs.CV, cs.OS arXiv: https://arxiv.org/abs/2607.02501v3 Embodied AI models now span vision-language-action (VLA) models and world-action models (WAMs), but practical deployment remains fragmented across model-specific Python stacks, backend assumptions, and robot-side glue code, especially on heterogeneous edge devices. Existing inference runtimes are designed mainly for request-response serving and therefore do not satisfy the runtime contract of embodied deployment: multi-rate execution inside closed-loop control, latency-first batch-1 inference on heterogeneous hardware, and extensible embodied interfaces beyond fixed token I/O. We present Embodied$.$cpp, a portable C++ inference runtime for embodied models. Based on an architectural analysis of representative VLA models and WAMs, Embodied$.$cpp captures a shared execution path and organizes it into five layers: input adapters, sequence builders, backbone execution, head plugins, and deployment adapters. The runtime provides modular multi-rate execution, latency-first fused inference, and extensible operator and I/O support, enabling deployment across heterogeneous devices, robots, and simulators through one backend abstraction. We evaluate Embodied$.$cpp on three VLA and two WAM models, using normalized comparisons across Python and C++ quantization configurations. Overall, Embodied$.$cpp achieves 1.05x-2.70x inference speedups and 7\%-77\% lower VRAM relative to Python baselines, while maintaining near-baseline success for most configurations. These results show that Embodied$.$cpp improves deployment efficiency while preserving high control quality across diverse embodied model architectures. Project Link: https://github.com/SEU-PAISys/Embodied.cpp --- ### Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots Authors: Ling Xu, Chuyu Han, Borui Li, Hao Wu, Shiqi Jiang, Ting Cao, Chuanyou Li, Sheng Zhong, Shuai Wang Published: 2026-07-02 Categories: cs.RO, cs.CV, cs.OS arXiv: https://arxiv.org/abs/2607.02501v2 Embodied AI models now span vision-language-action (VLA) models and world-action models (WAMs), but practical deployment remains fragmented across model-specific Python stacks, backend assumptions, and robot-side glue code, especially on heterogeneous edge devices. Existing inference runtimes are designed mainly for request-response serving and therefore do not satisfy the runtime contract of embodied deployment: multi-rate execution inside closed-loop control, latency-first batch-1 inference on heterogeneous hardware, and extensible embodied interfaces beyond fixed token I/O. We present Embodied$.$cpp, a portable C++ inference runtime for embodied models. Based on an architectural analysis of representative VLA models and WAMs, Embodied$.$cpp captures a shared execution path and organizes it into five layers: input adapters, sequence builders, backbone execution, head plugins, and deployment adapters. The runtime provides modular multi-rate execution, latency-first fused inference, and extensible operator and I/O support, enabling deployment across heterogeneous devices, robots, and simulators through one backend abstraction. We evaluate Embodied$.$cpp on two VLA models, HY-VLA and pi0.5, and on a preliminary WAM benchmark using a LingBot-VA Transformer block. The VLA deployments achieve successful closed-loop execution with 100.0% and 91.0% task success rates, respectively. The WAM benchmark reduces block memory from 312.2 MiB to 88.1 MiB. These results show that Embodied$.$cpp improves deployment efficiency while preserving high accuracy across diverse embodied model architectures. --- ### Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials Authors: Gil Harari, Yoel Zimmermann, Ola Tangen Kulseng, Laura Zichi, Chuin Wei Tan, Marc L. Descoteaux, Boris Kozinsky Published: 2026-07-02 Categories: cs.LG, cs.AI, physics.chem-ph, physics.comp-ph arXiv: https://arxiv.org/abs/2607.02499v1 Machine learning interatomic potentials (MLIPs) have become a hallmark of AI for scientific simulation. While efforts on new architectures and datasets have led to increasingly accurate and general models, the choice of optimizer for training has largely remained unexplored, defaulting to Adam and its variants in the community. Here, we implement and systematically compare a class of recently proposed matrix-structured optimizers, including Muon, SOAP, and the hybrid SOAP-Muon, for training NequIP and Allegro MLIP models. We find that these optimizers can substantially outperform Adam in both convergence speed and final accuracy. SOAP and SOAP-Muon emerge as robust and consistently strong methods, while Muon only provides partial gains relative to Adam. The improvements are particularly pronounced under partial force supervision. Our results indicate that optimizer choice is an overlooked yet impactful design axis for MLIPs. --- ### Seek to Segment: Active Perception for Panoramic Referring Segmentation Authors: Song Tang, Shuming Hu, Xincheng Shuai, Henghui Ding, Yu-Gang Jiang Published: 2026-07-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.02497v1 Existing referring segmentation models passively process static images captured from fixed perspectives, limiting their applicability in Embodied AI, where agents must perform active perception in the continuous 360$^\circ$ environments. To bridge this gap, we introduce a novel task: Active Panoramic Referring Segmentation (APRS). In this setting, an agent is required to adjust its viewing direction ($Δθ, Δφ$) to explore the 360$^\circ$ environment, seeking the object specified by a user instruction for segmentation. To tackle this challenging task, we propose PanoSeeker, a memory-augmented agent for efficient APRS. Rather than relying on heuristic scanning, PanoSeeker integrates a Vision-Language Model (VLM) with EgoSphere, an explicit spatial visual memory. By progressively integrating sequential local observations into a unified 360$^\circ$ representation, EgoSphere enables the agent to plan efficient and non-redundant search trajectories. Once the target is found, the agent performs active viewpoint alignment and outputs the segmentation mask. Furthermore, we curate an expert-annotated search trajectory dataset with memory timelines for Supervised Fine-Tuning, followed by Reinforcement Learning post-training to explicitly optimize PanoSeeker's exploration efficiency. Extensive experiments on our newly established APRS benchmark demonstrate that PanoSeeker achieves superior search efficiency and segmentation accuracy, significantly outperforming adapted state-of-the-art baselines. --- ### Controllable Sim Agents with Behavior Latents Authors: Juanwu Lu, Junyu Zhu, Ziran Wang Published: 2026-07-02 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2607.02496v1 Realistic traffic simulation requires agents that imitate logged behavior and can also be steered along interpretable axes. Such controllability enables engineers to isolate variables, reproduce specific edge cases, and test autonomous systems without real-world risk. We introduce Controllable Neural Variational Agents (CNeVA), a controllable simulated-agent framework that learns to infer a per-agent Gaussian behavior latent from per-channel discounted returns via a closed-form conjugate variational update, conditioning a rectified-flow trajectory generator trained on a mixed channel-mask curriculum for classifier-free guidance. To tackle scarcity in reward signals, we propose soft eligibility gates that replace hard binary thresholds with smooth exponential decay, preserving the gradient signal for near-threshold agents. On the Waymo Open Motion Dataset, CNeVA attains competitive realism on the benchmark while exposing per-channel controllability that the higher-ranked imitation models lack. Speed- and acceleration-based steering produces monotone responses without stall-induced reward hacking. Safety controllability is monotone and substantial with the introduction of soft eligibility. We manage to achieve steerable map compliance under a context-residual return measure. Furthermore, our experiment demonstrates that steering metrics must be read alongside physical-plausibility guardrails to avoid reward-hacking confounds. --- ### Towards Robustness against Typographic Attack with Training-free Concept Localization Authors: Bohan Liu, Wenqian Ye, Guangzhi Xiong, Zhenghao He, Sanchit Sinha, Aidong Zhang Published: 2026-07-02 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2607.02494v1 Models trained via Contrastive Language-Image Pretraining (CLIP) serve as the foundational vision encoders for most modern Large Vision Language Models (LVLMs). Despite their widespread adoption, CLIP models exhibit a critical yet underexplored failure mode: irrelevant text appearing within images confounds visual representations, biasing them toward lexical meaning rather than true visual semantics. This robustness issue, commonly described as a Typographic Attack (TA), exposes a vulnerability that poses a significant risk to safety-critical applications such as autonomous driving. To achieve interpretable and effective robustness against TA, we propose a novel, training-free mechanistic interpretability method. Our method provides sampling-based interpretations of hidden state representations and quantitatively attributes semantic versus lexical focus to individual attention heads. Through probabilistic analysis and circuit mining, we isolate specific Vision Transformer (ViT) components that disproportionately encode lexical information, thereby identifying the mechanistic source of TA. We further show that simple interventions applied directly to the identified circuits, without any additional training, can substantially improve robustness against Typographic Attacks in object classification. These interventions, such as selective adjustment of attention weights, also outperform both supervised and training-free defense methods. Our experiments demonstrate that applying the proposed intervention to the vision encoders of several state-of-the-art LVLMs yields substantial gains in Visual Question Answering accuracy under Typographic Attack interference on RIO-Bench. These results confirm both the efficacy and the generalizability of our mechanistic approach. Code is released at https://github.com/Liu-524/SamplingTAR. --- ### G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models Authors: Timo Bertram, Sidhant Bhavnani, Richard Freinschlag, Erich Kobler, Andreas Mayr, Günter Klambauer Published: 2026-07-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.02491v1 In this work, we focus on SE-RRMs, a symbol-equivariant instantiation of RRMs that exhibits improved extrapolation to larger problem sizes. We propose a neuro-symbolic approach, ``Guiding with Recurrent Reasoning Models'' (G-RRM), which integrates SE-RRMs with symbolic solvers for constraint satisfaction problems. SE-RRMs act as neural solvers that generate full solution proposals and guide classical symbolic solvers, such as backtracking or SAT-based methods like Glucose 4.1 and CaDiCaL 3.0.0, that produce globally correct solutions. Centrally, we investigate when neural guidance with G-RRM improves the search efficiency of symbolic solvers. % Our experiments show that the efficacy of G-RRM depends on two conditions: first, the problem instances must have an expansive combinatorial search space to expose potential gains, and second, the solver architecture must be capable of dynamically overwriting its branching choices to recover when neural hints are imperfect. When these conditions hold, guidance drives median conflict counts to zero and yields significant wall-clock speedups: on $9\times9$ Sudoku, where the SE-RRM correctly solves $91.1\%$ of instances, backtracking accelerates by $33.3\times$ and Glucose 4.1 by $1.70\times$ (median, $p<0.001$), with Glucose 4.1 retaining a $1.17\times$ speedup on perfect-hint $25\times25$ grids. In contrast, CaDiCaL 3.0.0, whose runtime is overhead-dominated and which always respects the injected branching hints rather than overwriting them, shows no significant speedup (median $1.02\times$, n.s.) and even a small significant mean slowdown ($0.90\times$) on $9\times9$. These results delineate the regimes in which neural guidance translates into practical speedups. --- ### Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learning Authors: Liyan Tang, Fangcong Yin, Greg Durrett Published: 2026-07-02 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2607.02490v1 Large vision-language models can reason over multimodal inputs by generating textual chains of thought (CoT). A key capability exhibited in CoT reasoning is self-reflection: revisiting earlier decisions and correcting previous errors. However, existing LVLMs often fail to properly attend to visual inputs during reflection, limiting their ability to translate feedback into grounded corrections, especially for out-of-distribution images. To address this issue, we propose a novel reinforcement learning training framework VRRL, with two components explicitly designed to elicit visually grounded self-reflection. First, we randomly mask trajectory prefixes during training to emphasize recovery from incorrect intermediate predictions rather than making early mistakes. Second, we introduce buffered roll-ins from an experience replay buffer to expose the model to diverse failure states that it must learn to correct. We evaluate our approach on visual grounding tasks involving tables and charts, as well as spatial navigation benchmarks. While off-the-shelf and conventionally fine-tuned models degrade substantially under distribution shift, our method substantially improves average out-of-distribution accuracy over standard RL and reflection-oriented fine-tuning baselines by using self-reflection effectively. --- ### GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training Authors: Yejun Zhang, Xinjue Wang, Zihan Wang, Esa Rahtu, Juho Kannala Published: 2026-07-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.02486v2 Descriptor-free visual localization eliminates high-dimensional descriptor storage, preserves scene privacy, and simplifies map maintenance, yet its accuracy still lags far behind descriptor-based pipelines. We identify this gap to insufficient geometric discriminability in geometry-only matching. Without visual appearance, current methods underutilize local geometry cues, lack the global context among keypoints, and overfit to a single keypoint detector. We further observe that descriptor-free matching naturally enables multi-detector training, as heterogeneous keypoints can be optimized in a shared geometry-only space without aligning descriptor spaces. Building on these insights, we propose GeoMix, a descriptor-free 2D-3D matching framework that strengthens geometric discriminability at three levels. Locally, directional and distance-aware embeddings enrich neighborhood aggregation with fine-grained spatial structure. Globally, learnable context nodes aggregate and redistribute scene-wide information via cross-attention to resolve ambiguities beyond local receptive fields. At the training level, Mix-Training exploits this detector-agnostic geometry space to learn representations across multiple keypoint detectors. Extensive experiments on MegaDepth, Cambridge Landmarks, 7Scenes, and Aachen Day-Night show that GeoMix sets a new state of the art among descriptor-free methods, reducing 75th-percentile rotation error by 89\% and translation error by up to 90\% over the previous best, while generalizing zero-shot to unseen detectors and narrowing the gap to descriptor-based pipelines. Code is available at $\href{https://github.com/YejunZhang/Geomix}{\text{this links}}$. --- ### GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training Authors: Yejun Zhang, Xinjue Wang, Zihan Wang, Esa Rahtu, Juho Kannala Published: 2026-07-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.02486v1 Descriptor-free visual localization eliminates high-dimensional descriptor storage, preserves scene privacy, and simplifies map maintenance, yet its accuracy still lags far behind descriptor-based pipelines. We identify this gap to insufficient geometric discriminability in geometry-only matching. Without visual appearance, current methods underutilize local geometry cues, lack the global context among keypoints, and overfit to a single keypoint detector. We further observe that descriptor-free matching naturally enables multi-detector training, as heterogeneous keypoints can be optimized in a shared geometry-only space without aligning descriptor spaces. Building on these insights, we propose GeoMix, a descriptor-free 2D-3D matching framework that strengthens geometric discriminability at three levels. Locally, directional and distance-aware embeddings enrich neighborhood aggregation with fine-grained spatial structure. Globally, learnable context nodes aggregate and redistribute scene-wide information via cross-attention to resolve ambiguities beyond local receptive fields. At the training level, Mix-Training exploits this detector-agnostic geometry space to learn representations across multiple keypoint detectors. Extensive experiments on MegaDepth, Cambridge Landmarks, 7Scenes, and Aachen Day-Night show that GeoMix sets a new state of the art among descriptor-free methods, reducing 75th-percentile rotation error by 89\% and translation error by up to 90\% over the previous best, while generalizing zero-shot to unseen detectors and narrowing the gap to descriptor-based pipelines. Code is available at $\href{https://github.com/YejunZhang/Geomix}{\text{this links}}$. --- ### Combating Textual Noise and Redundancy: Entropy-Aware Dense Visual Token Pruning Authors: Xuehui Wang, Xuankun Yang, Wei Shen Published: 2026-07-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.02484v1 Visual token pruning is a crucial strategy for accelerating VLMs by compressing redundant image patches, yet existing methods often fail to preserve critical cues under dense instructions and fine-grained queries. In this paper, we investigate this failure and identify two underlying bottlenecks: the widespread dispersion of textual noise that corrupts dense cross-modal scoring, and the feature fragmentation inherent to standard token selection. To address these issues, we propose Entropy-Aware Dense Pruning (EADP), a framework that reformulates pruning as a structured compression problem. EADP first leverages statistical entropy to quantify and filter out textual noise, yielding a robust, fine-grained instruction relevance score. Subsequently, instead of naive Top-K selection, EADP casts token selection as a submodular maximization problem with a spatial prior, explicitly ensuring a holistic and non-redundant visual representation. Extensive experiments demonstrate that EADP improves the accuracy-efficiency trade-off of VLMs, robustly preserving fine-grained visual cues under strict token budgets while achieving SoTA performance on challenging multimodal benchmarks. --- ### EAGLE-360: Embodied Active Global-to-Local Exploration in 360$^\circ$ Authors: Jingtao Xu, Zizhuo Lin, Jianwen Sun, Yi Yang, Yawei Luo Published: 2026-07-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.02479v1 While Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in standard visual understanding, adapting them for active visual search in 360$^\circ$ panoramic environments exposes fundamental limitations. Specifically, standard MLLMs struggle to effectively model inherent panoramic properties, such as severe polar distortion and continuous cylindrical topologies, which significantly degrades target detection accuracy. Consequently, existing panoramic search methods attempt to compensate by relying heavily on fragmented local viewpoints. Burdened by rigid initialization and a lack of global panoramic priors, these approaches suffer from myopic, inefficient exploration and struggle with robust error recovery when targets are out of view. To overcome these challenges, we propose EAGLE-360, a novel Embodied Active Global-to-Local Exploration framework. Rather than performing exhaustive local searches, EAGLE-360 leverages global priors to establish an initial holistic perspective, iteratively reasoning and progressively narrowing the search space. Architecturally, we adapt RoPE Rolling, a coordinate-shifting positional encoding mechanism, to seamlessly model the continuous topologies of panoramas. To facilitate this paradigm, we construct the large-scale EAGLE-360 dataset, comprising 14,000+ 4K panoramas and 70,000+ rounds of high-quality VQA dialogues. By employing a training pipeline that integrates Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), we effectively elicit complex spatial reasoning and tool-calling capabilities. Extensive experiments demonstrate that EAGLE-360 establishes a new state-of-the-art for 360$^\circ$ visual search, achieving nearly an 8-fold increase in accuracy over the base model while significantly enhancing exploration efficiency. --- ### Audio-Based Understanding of Audiobook Narration Appeal Authors: Shahar Elisha, Mariano Beguerisse-Díaz, Emmanouil Benetos Published: 2026-07-02 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2607.02473v1 Narration is central to the audiobook listening experience, shaping how listeners engage with and understand the content. This work explores how narration qualities shape an audiobook's appeal, noting that their effects can vary by genre, title, and audience. We extract vocal and acoustic features (e.g., tone, pace, loudness) from LibriVox using pre-trained audio models and analyse their relationship with consumption data (specifically, view-rate) and their interplay with genre and title. Despite limited consumption data, we find that acoustic information alone has a robust association with appeal, even after accounting for title effects. We further validate these findings using more nuanced proprietary engagement metrics. To our knowledge, this is the first systematic computational study linking narration qualities, genre, title, and audiobook consumption, highlighting the potential of data-driven insights to improve audiobook personalisation and narrator casting. --- ### Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment Authors: Ziyao Wang, Maonan Wang, Yucheng He, Xianping Ma, Ziyi Wang, Hongyang Zhang, Yirong Cheng, Man-on Pun Published: 2026-07-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.02471v1 Cloud removal (CR) is essential for optical remote sensing, serving as a prerequisite for reliable downstream interpretation, such as semantic segmentation and change detection. However, existing CR approaches often prioritize visual realism while overlooking their impact on subsequent analytical tasks, leading to semantic drift and degraded downstream performance. To address this issue, we propose Geo-Anchored Cloud Removal (GACR), a unified framework that jointly ensures faithful reconstruction and robust interpretability. At its core, GACR incorporates Observation-Anchored Residual Flow (OAR-Flow), which reformulates CR as a physically grounded residual inversion process. By anchoring the generative trajectory to the cloudy observation rather than pure noise, OAR-Flow enables fast, stable, and faithful reconstruction. To further preserve semantic structures critical for downstream interpretation, GACR integrates Geo-Contextual Prior Alignment (GCPA) to constrain the reconstruction within a semantic manifold induced by a Vision Foundation Model (VFM). Consequently, GACR strictly maintains the spatial-semantic integrity of complex landscapes. Extensive experiments across six CR datasets and twelve downstream tasks demonstrate that GACR produces superior reconstruction quality while consistently improving downstream task accuracy. The code is available at https://github.com/wzy6055/GACR. --- ### TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution Authors: Jiale Amber Wang, Kaiyuan Wang, Pengyu Nie Published: 2026-07-02 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.02469v1 Software tests and code evolve together: a code change should be followed by new or updated tests that record the new software behavior. Yet existing test generation and update benchmarks often isolate the test from the code change, and rely on static metadata that does not verify whether a test is executable or semantically tied to the code change. This makes it difficult to evaluate whether a test automation agent understands how a code change should propagate into the test suite. We introduce TestEvo-Bench, a benchmark of test and code co-evolution tasks mined from software repositories, with two tracks: in test generation, the agent shall write new tests to capture the new software behavior; in test update, the agent shall adapt failing existing tests to the changed software behavior. Each task is anchored to a real commit history and packaged with environment configuration to support execution-grounded metrics such as pass rate, coverage, and mutation score. TestEvo-Bench is also a live benchmark: each task records the timestamp of the test and code changes, and new tasks are periodically mined by our automated pipeline, so evaluation can be restricted to tasks postdating a model's training cutoff to reduce data leakage risk. The current snapshot contains 746 test generation and 509 test update tasks, curated from 59,950 candidate co-evolution records across 152 open-source Java projects. We experiment with four state-of-the-art agents that combine strong harnesses (Claude Code, Gemini CLI, and SWE-Agent) with strong foundation models (Claude Opus 4.7 and Gemini 3.1 Pro). Results show that they achieve up to 77.5% success rate on test generation and 74.6% on test update. However, success rate is materially lower on the most recent benchmark tasks and drops significantly under limited per-task cost. --- ### Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting Authors: Vivienne Ming Published: 2026-07-02 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.02467v1 Whether pairing people with AI helps or hurts is usually reported as a single average effect. Using a real-money prediction market (Polymarket) as an objective, externally resolved benchmark, this pilot shows that the value of human-AI collaboration depends on a specific, measurable form of human capital. Analyzed at the level of the individual forecaster, hybrid performance is trimodal: most people either deferred to the model (matching it) or used it to rubber-stamp a prior guess (performing worse than the model alone), while a minority engaged in genuine complementary reasoning and reached accuracy matching or even exceeding (i.e., lower error than) the market itself. Collaborative traits (perspective-taking, intellectual humility, and curiosity) rather than raw cognitive ability or model benchmarks, distinguished who reached that mode. The results are preliminary but statistically robust, and motivate a pre-registered replication now in preparation. --- ### Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs Authors: Junhao Shi, Siyin Wang, Xiaopeng Yu, Li Ji, Jingjing Gong, Xipeng Qiu Published: 2026-07-02 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.02466v1 Vision-Language-Action (VLA) models are fundamentally bottlenecked by the scarcity of expert demonstrations -- triplets of observations, instructions, and actions that are costly to collect at scale. We argue that this bottleneck stems from conflating two distinct learning objectives: acquiring physical competence (how to move) and acquiring semantic alignment (what to do). Crucially, only the latter requires language supervision. Building on this Decomposition Hypothesis, we propose Task-Agnostic Pretraining (TAP), a two-stage framework that first learns transferable motor priors from cheap, unlabeled interaction data -- including discarded off-task trajectories and autonomous robot play -- via a self-supervised Inverse Dynamics objective. A lightweight second stage then grounds these priors in language using minimal expert data. On the SIMPLER benchmark, TAP matches models trained on over 1M expert trajectories while using orders of magnitude less labeled data, yielding a 10% absolute gain over standard behavior cloning. On a real-world WidowX platform, TAP retains 25% success under camera perturbations where internet-scale baselines collapse to 0%, demonstrating that task-agnostic pretraining produces robust, transferable physical representations and offers a scalable path forward for Embodied AI. --- ### Will Scaling Improve Social Simulation with LLMs? Authors: Caleb Ziems, William Held, Su Doga Karaca, David Grusky, Tatsunori Hashimoto, Diyi Yang Published: 2026-07-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.02464v2 Large Language Model (LLM) social simulations are a promising research method, but they are not yet faithful enough to be adopted widely. In this work, we investigate whether the current scaling paradigm in language modeling is likely to close these gaps, or whether simulation fidelity is orthogonal to general capabilities and therefore deserving of more research attention. We use scaling laws to study the relationship between LLMs' compute scale, general capability benchmarks, and the fidelity of social simulation in three representative sub-domains: opinion modeling, behavioral simulation, and longitudinal forecasting. Surprisingly, we discover strong compute scaling in all three settings, using a suite of 85 transformer LLMs with the Qwen3 architecture pre-trained on the DCLM web text corpus under fixed-compute budgets from $10^{18}$ to $10^{20}$ FLOPs. Then we evaluate 35 larger and more capable open-weight models up to 70B parameters, allowing us to predict downstream accuracy from loss. This reveals that the majority of behavioral and opinion simulation tasks will rapidly improve with scale, particularly when they involve populations that are well-represented in English web corpora. Longitudinal forecasting and underrepresented opinions scale more slowly, especially when they are less correlated with general knowledge and reasoning benchmarks like MMLU. In behavior simulation, scaling fails to improve model calibration with human cognitive biases like risk aversion, as well as human heuristics like learning correlated rewards from related tasks. On these tasks, even fine-tuned models fail to noticeably scale up performance from 0.5B to 8B parameters. Taken together, we conclude that scale will improve social simulations in most settings, but outliers exist, and improvements will be less reliable in low-resource domains. --- ### OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers Authors: Donghyun Lee, Jitesh Chavan, Duy Nguyen, Sam Huang, Liming Jiang, Priyadarshini Panda, Timo Mertens, Saurabh Shukla Published: 2026-07-02 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.02461v1 Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training quantization (PTQ) is the natural remedy, yet DiT activations shift across timesteps, prompts, and guidance branches, forcing prior methods to re-fit calibration data for every new checkpoint or modality. We present OrbitQuant, a data-agnostic weight-activation quantizer that bypasses range estimation by quantizing in a normalized, rotated basis. In this basis, a randomized permuted block-Hadamard (RPBH) rotation concentrates each coordinate around one fixed, known marginal regardless of the input, so a single Lloyd-Max codebook serves all timesteps, prompts, and layers of a given input dimension. We extend the same quantizer to weight rows offline, absorbing the rotation into the weights so that it cancels inside each linear layer and only a forward rotation on the activations remains at runtime. The same recipe transfers from image to video with no per-modality tuning. Across FLUX.1, Z-Image-Turbo, Wan 2.1, and CogVideoX, it sets the state of the art for PTQ at several low-bit settings. It also pushes PTQ of image diffusion transformers to W2A4 with usable generation quality. --- ### Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation Authors: Zhuowei Chen, Xiang Lorraine Li Published: 2026-07-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.02460v1 Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain. Recent annotation-free self-evolution methods address this by using the model's own outputs as supervision signals, constructing a teacher via additional context and aggregating predictions across multiple rollouts through majority voting to produce pseudo-labels. However, these approaches are not without drawbacks: SFT- and GRPO-based variants suffer out-of-domain performance degradation, while reward-based on-policy RL inflates calibration error. In this paper, we propose Neuron On-Policy Self-Distillation (Neuron-OPSD), a data-centric framework for annotation-free self-distillation that leverages internal neuron activations to guide both training-data selection and teacher context construction. The model is then trained via on-policy distillation from the teacher distribution, requiring no ground-truth labels at any stage. Across specialized-domain benchmarks, Neuron-OPSD improves in-domain task performance while preserving cross-domain generalization and mitigating calibration collapse over prior annotation-free baselines. This framework is particularly relevant to settings where online interaction or external supervision is costly or infeasible, and is conceptually distinct from offline RL approaches that rely on logged, reward-labeled trajectories. --- ### Language Models as Measurement Apparatus for Culture Authors: Kent K. Chang Published: 2026-07-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.02459v1 Language models are increasingly used to quantify cultural phenomena, but what makes such measurement distinctively cultural? This paper argues that NLP work on culture is a material-discursive practice: the apparatus -- model, data, annotation, evaluation -- participates in constituting the cultural reality it measures, rather than passively recording it. Drawing on Karen Barad's concept of the agential cut -- the contingent boundary between phenomenon and instrument -- I show that the apparatus's substantive design choices draw such boundaries, and that the boundary is entangled from the start because language models have already internalized much of the cultural material they measure. I illustrate this through three case studies on television and film dialogue (measuring structure, interaction, and deviation) and three examinations of the apparatus itself (erasure of cultural markers, attunement to historical material, and agency in an agentic workflow). This big picture analysis proposes a research program that is theory-driven, empirically rigorous, and culturally contingent, treating each agential cut as a conscious commitment, at once methodological and ethical. --- ### Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data Authors: Xuanyu Chen, Nan Yang, Shuai Wang, Dong Yuan Published: 2026-07-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.02447v1 Recent research has introduced distributed self-supervised learning (D-SSL) approaches to leverage vast amounts of unlabeled decentralized data. However, D-SSL faces the critical challenge of data heterogeneity, and there is limited theoretical understanding of how different D-SSL frameworks respond to this challenge. To fill this gap, we present a rigorous theoretical analysis of the robustness of D-SSL frameworks under non-IID (non-independent and identically distributed) settings. Our results show that pre-training with Masked Image Modeling (MIM) is inherently more robust to heterogeneous data than Contrastive Learning (CL), and that the robustness of decentralized SSL increases with average network connectivity, implying that federated learning (FL) is no less robust than decentralized learning (DecL). These findings provide a solid theoretical foundation for guiding the design of future D-SSL algorithms. To further illustrate the practical implications of our theory, we introduce MAR loss, a refinement of the MIM objective with local-to-global alignment regularization. Extensive experiments across model architectures and distributed settings validate our theoretical insights, and additionally confirm the effectiveness of MAR loss as an application of our analysis. --- ### Optimal Stabilizer Testing and Learning with Limited Quantum Memory Authors: Srinivasan Arunachalam, Louis Schatzki Published: 2026-07-02 Categories: quant-ph, cs.CC, cs.DS, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2607.02444v1 We study stabilizer state testing and learning with limited coherent quantum memory. Here an algorithm sequentially receives copies of an unknown $n$-qubit state, but may keep only $k$ qubits of coherent quantum memory between measurements. With unrestricted memory, seminal work of Gross, Nezami and Walter showed how to test $n$-qubit stabilizer states using $6$ copies, which is dimension independent, unlike the learning complexity of $Θ(n)$. We show that this testing-vs-learning separation is lost under memory constraints. More concretely we show that (1) The sample complexity of testing stabilizer states in the $k$-qubit memory framework is $Θ(n-k)$. Our upper bound goes via a novel connection to the hidden shift problem and the lower bound is proven using a novel approach to average case bounds on likelihood ratios via combinatorics of the stochastic orthogonal group. (2) The sample complexity of learning stabilizer states with $k$ qubits of memory, in the non-adaptive framework, is $Θ(n^2/k)$. As a further application of our techniques, we prove an exponential lower bound for purity testing even when the memory may be left coherent throughout the protocol. Our main results identify coherent quantum memory as the resource enabling the usual separation between stabilizer testing and learning. In particular, even with $k=0.99n$ qubits of memory, there is no constant-copy stabilizer tester; furthermore for $k=cn$ qubits of memory (for $0< c < 1$), stabilizer testing is as hard as learning, with both requiring $Θ(n)$ copies. --- ### EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments Authors: Zhilin Wang, Han Song, Runzhe Zhan, Jusen Du, Jiacheng Chen, Tianle Li, Qingyu Yin, Yulun Wu, Zhennan Shen, Tong Zhu, Yanshu Li, Guanjie Chen et al. Published: 2026-07-02 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.02440v1 Autonomous agents are increasingly expected to improve executable policies through feedback, yet existing evaluations often collapse this process into a final score or confound it with open-ended software-engineering progress. We introduce Autonomous Policy Evolution, a controlled evaluation setting in which a harness-model agent repeatedly edits an executable policy system under a fixed interaction budget. We instantiate this setting in EvoPolicyGym, a benchmark built from compact interactive RL environments that evaluates how agents iteratively improve explored policies. On the EvoPolicyGym suite, GPT-5.5 achieves the strongest aggregate rank score and top-two performance on all 16 environments. Beyond leaderboard results, EvoPolicyGym also provides trajectory-level diagnostics that distinguish how agents allocate budget, convert feedback into parametric tuning. These analyses show that strong autonomous policy evolution depends not only on isolated task wins, but on discovering task-appropriate mechanisms and refining policies under bounded feedback. --- ### Extreme Adaptive Transformer for Time Series Forecasting Authors: Sanjeev Shrestha, Hui Liu, Yifan Zhang Published: 2026-07-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.02437v1 Time series forecasting remains challenging when the underlying data contain rare but critical extreme events. This issue is particularly important in hydrologic forecasting, where streamflow distributions are often highly skewed and extreme peaks can have substantial impacts on flood monitoring, water resource management, and early warning systems. Although Transformer-based forecasting models have achieved strong performance by modeling long-range temporal dependencies, they typically treat all time points uniformly and may therefore underrepresent rare extreme patterns. In this paper, we propose the Extreme-Adaptive Transformer (Exformer), a forecasting framework designed to explicitly model temporal dependencies involving both normal and extreme events. Exformer introduces an extreme-adaptive attention mechanism composed of three sparse components: Local, Stride, and Extreme. The Local and Stride components capture short-term and periodic temporal dependencies, respectively, while the Extreme component selectively models event-aware dependencies between normal and extreme streamflow patterns. Experiments on four real-world hydrologic streamflow datasets show that Exformer achieves superior 3-day forecasting performance compared with state-of-the-art baselines. Our findings demonstrate that explicitly incorporating extreme-aware attention improves the forecasting capacity of Transformer models on imbalanced time series with rare but consequential events. --- ### Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study Authors: Achint Mehta Published: 2026-07-02 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.02436v2 Agentic coding assistants are increasingly given extra capabilities, such as browser based testing tools and design oriented system prompts, on the assumption that more capability yields better software. This study tested that assumption directly. Ninety independent agent runs built the same application, a real time retrospective board, from one detailed specification, each scored on a fixed 14 criterion functional rubric (42 point maximum) and a visual quality review. The runs spanned several model generations, two agent harnesses, two reasoning effort levels, a testing tool, and two design oriented prompts. Capability tier dominated: frontier models clustered near the ceiling while a low cost local model fell to 24 to 37 points. A criterion level analysis revealed what run totals conceal. Container deployment was the dominant defect, failing first try in 44 percent of runs, with its failure rate shifting sharply across model generations while mean totals moved less than a point. The testing tool raised cost by 42 to 68 percent without improving functional score or reliability, even on interface visible criteria. Raising reasoning effort from High to xHigh lifted first try perfect runs from 28 percent to 89 percent and cut corrective prompts about five fold, for 9 to 29 percent more cost. A design oriented prompt raised visual quality, 4.5 versus 3.0 on a 5 point scale, without lifting function, and a one paragraph paraphrase of its directive reproduced the entire lift. The practical lesson is to match the fix to the failure: most first run failures came from weak reasoning, which a stronger model or more effort prevents, not from visible flaws a checking tool would catch. --- ### Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study Authors: Achint Mehta Published: 2026-07-02 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.02436v1 Agentic coding assistants are increasingly given extra capabilities, such as browser based testing tools and design oriented system prompts, on the assumption that more capability yields better software. This study tested that assumption directly. Ninety independent agent runs built the same application, a real time retrospective board, from one detailed specification, each scored on a fixed 14 criterion functional rubric (42 point maximum) and a visual quality review. The runs spanned several model generations, two agent harnesses, two reasoning effort levels, a testing tool, and two design oriented prompts. Capability tier dominated: frontier models clustered near the ceiling while a low cost local model fell to 24 to 37 points. A criterion level analysis revealed what run totals conceal. Container deployment was the dominant defect, failing first try in 44 percent of runs, with its failure rate shifting sharply across model generations while mean totals moved less than a point. The testing tool raised cost by 42 to 68 percent without improving functional score or reliability, even on interface visible criteria. Raising reasoning effort from High to xHigh lifted first try perfect runs from 28 percent to 89 percent and cut corrective prompts about five fold, for 9 to 29 percent more cost. A design oriented prompt raised visual quality, 4.5 versus 3.0 on a 5 point scale, without lifting function, and a one paragraph paraphrase of its directive reproduced the entire lift. The practical lesson is to match the fix to the failure: most first run failures came from weak reasoning, which a stronger model or more effort prevents, not from visible flaws a checking tool would catch. --- ### MARVEL: Margin-Aware Robust von Mises-Fischer Expert Learning for Long-Tailed Out-of-Distribution Detection Authors: A. S. Anudeep, Vaanathi Sundaresan Published: 2026-07-02 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2607.02435v1 For clinical deployment, it is essential that automated diagnostic systems remain reliable when confronted with previously unseen cases, yet deep models routinely misclassify out-of-distribution (OOD) inputs with high confidence, underscoring the need for more robust OOD detection methods. Although substantial effort has been devoted to improving model robustness, most of the existing literature assumes balanced datasets, evaluates OOD detection on coarse or non-clinical OOD sources, or lacks comprehensive assessment across diverse OOD scenarios. To address the gaps, we propose a novel methodology trained on diverse and imbalanced medical datasets and evaluated across a clinically reflective OOD spectrum. Our framework comprises three key components: (1) a Nonlinear von Mises-Fisher (NvMF) classifier capable of learning non-linear decision boundaries, with theoretical proof of its asymptotic connection to cosine classifiers; (2) a multi-expert framework in which margin-aware NvMF classifiers specialise in different regions of label distribution to better handle imbalance; and (3) an outlier expert trained explicitly to distinguish inlier from outlier data, thereby strengthening OOD detection. Evaluation on RFMiD, ISIC2019, and NCTCRC datasets demonstrates consistent improvements over state-of-the-art methods, achieving mean FPR95 reductions of 8.45%, 13.02%, and 36.90% respectively. These gains are further supported by comprehensive ablations that validated the contributions of each component. This enables reliable identification of unfamiliar cases for deferral to clinicians, supporting safer AI-assisted diagnosis in real-world workflows. Our code is available at https://github.com/redboxup/MARVEL. --- ### Automated grading of Linux/bash examinations using large language models: a four-level cognitive taxonomy approach Authors: Manuel Alonso-Carracedo, Ruben Fernandez-Boullon, Pedro Celard, Francisco J. Rodriguez-Martinez, Lorena Otero-Cerdeira Published: 2026-07-02 Categories: cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2607.02432v1 Scalable and reliable grading of command-line examinations remains a challenge in computing education, where rising enrolments make manual marking difficult and rule-based autograders cannot handle partial credit, equivalent solutions, or syntactic variation. This paper evaluates whether four frontier Large Language Models (GPT, Claude Opus, Gemini, and GLM) can approximate expert judgment when grading short Linux/bash command responses. The study adopts a four-level cognitive taxonomy that combines cognitive complexity and operational impact, ranging from information retrieval (L1) and basic file manipulation (L2) to structural operations (L3) and advanced system management (L4). The models were tested with two prompt variants, a minimal baseline and a rubric-enhanced version, on 1200 real responses from second-year Computer Engineering students independently graded by three expert instructors. Gemini~3.0 Pro with rubric-guided prompting achieved the highest human-AI agreement (ICC(3,1) = 0.888, MAE = 0.10, Bland-Altman bias = -0.014). Agreement declined consistently as taxonomy level increased, with the largest discrepancies at higher levels. Across all models, rubric quality had a larger effect than provider choice, with structured prompts consistently improving agreement. These results show that question complexity is a reliable predictor of the difficulty LLMs face in grading accurately, and they establish a principled, taxonomy-based framework for determining which questions are suitable for AI-assisted grading and which require human review, while also providing a transferable evaluation protocol and prompt templates. --- ### WorldSample: Closed-loop Real-robot RL with World Modelling Authors: Yuquan Xue, Le Xu, Zeyi Liu, Zhenyu Wu, Zhengyi Gu, Xinyang Song, Bofang Jia, Ziwei Wang Published: 2026-07-02 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.02431v1 Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing robots to improve through trial-and-error interaction beyond the states observed in demonstrations. However, deploying RL on real robots remains constrained by high interaction costs, since each physical rollout is costly and reflects only one realized action-outcome path. To address this challenge, we propose WorldSample, a physically grounded data augmentation framework for real-robot RL that closes a real-synthetic loop between physical rollouts, world-model generation, and policy improvement. Grounded on real rollouts, WorldSample generates high-fidelity synthetic transitions through a post-trained world model, which greatly lowers the visual hallucination. Specifically, rather than simply using these transitions as real-world experience, WorldSample introduces Policy-Paced Learning (PPL) to regulate the training process through sample selection and scheduling, balancing useful augmentation against value overestimation and mitigating the hallucination-induced noise. Experiments on robot manipulation tasks involving contact-rich and precise tasks show that WorldSample improves policy success rate by 28% while reducing training steps by 59% compared with baselines. Furthermore, WorldSample improves world model visual fidelity by 19.4dB in PSNR and 0.47 in SSIM over demonstration-only post-training, validating the effectiveness of the real-synthetic loop for both policy and world model performance. ---