Papers

Vision-language-action models (VLAs) inherit strong semantic grounding from pretrained vision-language backbones but are typically optimized for predicting actions rather than future observations. They can see and act, but they do not imagine the future before acting. World action models (WAMs) built on video diffusion backbones can imagine but treat language as frozen conditioning on a continuous latent space. Unified models bring these modalities into one architecture, but they either decode autoregressively, one token at a time, or keep video continuous with an auxiliary action head. In this work, we present SUAVE, a Single vocabulary Unified Action-Video modEl in which a masked diffusion transformer generates video and actions conditioned on language, with all three modalities represented as discrete tokens in a shared sequence. Choosing which tokens to mask at inference turns the same network into a world model, a robot policy, or a video-action model. For action-free co-training, the action positions of unlabeled video are filled with mask tokens and excluded from the loss. Simulation and real-world experiments demonstrate two findings. First, a single SUAVE model predicts long-horizon video and acts as a policy, competitive with dedicated world models and specialized action policies on static and dynamic manipulation tasks. On a real robot, our model generates subgoal images and an action chunk spanning one second of motion in 1,030 ms on an RTX 5090 GPU, sustaining closed-loop control at 2.5 actions per second. Second, pretraining on robot video and co-training on human video substantially improves policy performance and zero-shot robustness to distribution shift. Together, these results show that masked diffusion is a practical and versatile foundation for unified video-action modeling.

Executable Agent Skills combine natural-language instructions and scripts into reusable packages for LLM agents, and revising them requires fixing errors without breaking correct behavior. Existing benchmarks do not systematically distinguish documentation repair, script repair, and preservation when evaluating skill self-evolution. We introduce SkillScriptBench, a 350-task benchmark designed to evaluate these capabilities separately. From a survey of over 35,000 GitHub-hosted Skill roots, we select 100 packages and construct 150 repair tasks. Each task pairs a package containing injected script faults with a maintenance request and executable checks of the required behavior. A complementary controlled track contains 200 tasks from 50 packages, each evaluated under the same maintenance request in four states: clean, documentation faults, script faults, and faults in both. Across four LLMs, methods that edit both documentation and scripts can repair script faults but do not consistently outperform Markdown-only revision on documentation repair or preservation. We therefore introduce AST-Guided Skill Revision, which uses abstract syntax trees and calling relationships to link maintenance requirements to relevant code locations. It restricts script edits to these locations and updates the documentation to match the revised scripts. Averaged across models, this revision stage yields absolute gains in repair success of 21.9% for Raw Package and 27.7% for CoEvoSkills on faulty packages. Absolute gains in the proportion of tasks solved in all three runs reach 20.8% and 31.5%, respectively, indicating more consistent repair success across repeated runs.

We present VolS-GS, a relightable Gaussian splatting framework that reconstructs objects from one-light-at-a-time (OLAT) captures and renders them under novel lighting and viewpoints. Relightable Gaussian Splatting methods typically model appearance independently at each primitive, which makes non-local effects difficult to represent. This limitation is particularly apparent for subsurface scattering, where light entering the object at one location can emerge at another. Rather than modeling this effect solely with a neural network or a local kernel at each primitive, we use the spatial support of the Gaussian scene as the domain of a differentiable finite-volume transport solver, so that light can propagate through the object's interior. A small network predicts scattering and absorption coefficients for each Gaussian, and the solve redistributes incident light through the resulting field. The coefficients are fit to images rather than measured, so the solve supplies a transport-shaped path for aggregating per-primitive appearance, not a measurement of the material. To keep the learned shadow and specular terms from taking over the other components, our shadow term is predicted from visibility together with the transmittances and the scattering the solve produces, and a regularizer suppresses specular highlights in regions the shadow term predicts to be unlit. Experiments on three OLAT benchmarks show that VolS-GS consistently improves relighting quality on held-out lights and views.

Limited training data diversity constrains generative modeling of 3D human bodies: conservative models remain close to observed examples, whereas exploratory models often violate basic body proportions. We introduce a verifier-guided augmentation framework that uses global and mode-local PCA to generate inexpensive candidates, screens them using correspondence-derived skeletal proportions and body-part geometry, and retrains a diffusion model on accepted candidates. Elastic registration provides both the modal structure used by distributed PCA and the dense anatomical correspondence needed for scalable screening without per-candidate body-model fitting. A blinded human study supports the verifier as a conservative gatekeeper, favoring verifier-accepted over rejected outputs. We evaluate full-pool verifier acceptance separately from the coverage and departure of accepted samples and combine them through EAUC. On 4,498 registered DFAUST surfaces, distributed-PCA augmentation achieves 86.32% acceptance, the highest CP-AUC (0.871), and the highest EAUC (0.752), improving EAUC by 32% over real-only and self-augmented diffusion. These results show that mode-local, verifier-guided proposals broaden diffusion generation while maintaining high agreement with calibrated body measurements.

Large Audio Language Models (LALMs) are prone to hallucinating and over-relying on text priors when simultaneously presented with audio and text inputs. To mitigate these hallucinations, we propose utilizing the multimodal Direct Preference Optimization (mDPO) objective, which forces the model to ground its generation in the acoustic input by contrasting intact and distorted audio counterparts. We extend this preference learning framework to the audio domain by applying a variety of acoustic perturbations. Evaluating the Qwen2-Audio backbone across the DCASE 2025 Challenge and AH Existence datasets, we demonstrate that extending mDPO to LALMs significantly enhances temporal reasoning in the complex DCASE dataset, and improves performance on basic existence verification in the AH benchmark. We identify temporal reversal, frequency masking, and random noise as the most effective perturbations. Ultimately, our approach achieves an absolute accuracy improvement of 14.0% on the DCASE 2025 dataset and 27.4% on AH Existence.

Few-Shot Class-Incremental Learning (FSCIL) requires models to continuously learn new classes from limited samples while retaining prior knowledge, under strict constraints on compute and memory. Existing approaches lie along a difficult trade-off: simple fine-tuning is computationally efficient but suffers from catastrophic forgetting, replay-based methods mitigate forgetting at the cost of substantial compute and memory, and exemplar-free methods often reduce forgetting by freezing most of the backbone, improving efficiency at the expense of adaptability. We propose Selective Backpropagation (SBP), a deterministic parameter budgeting framework that bridges this gap. SBP restricts gradient updates to a pre-allocated subset of network parameters, freezing past knowledge and preserving unbiased capacity for future learning, enabling rapid adaptation without costly mask optimization. We show that SBP achieves strong performance across standard FSCIL benchmarks while requiring training time close to that of naive fine-tuning and substantially lower training time than prior SOTA methods. Crucially, our experiments expose a limitation of standard FSCIL evaluation: performance on short, distribution-consistent benchmarks does not necessarily predict behavior under distribution shift or over substantially longer learning horizons. We therefore evaluate FSCIL methods in cross-domain settings and over an 80-session ImageNet-1K stream. SBP remains strong across these regimes while maintaining low training cost, providing a favorable stability-plasticity-efficiency trade-off. Our code is available at https://github.com/PaInt-Lab/sbp-main-public.

A trainable input embedding table assigns each vocabulary item an independently adjustable vector. We investigate whether this token-specific parameterization is required for substantial language-modeling capability, or whether a shared Transformer can learn from fixed token identities. We compare three decoder-only language models trained from scratch with the same tokenizer, contextual backbone, untied output-head architecture, and training recipe, with a target budget of 100 billion prediction tokens per model. Their input interfaces are a learned table, canonical 16-bit token-ID codes, and one fixed invertible recoding over GF(2). The fixed codes are repeated to model width without an additional trainable input projection. Both fixed-code models acquire substantial capabilities: canonical codes achieve 52.40% HellaSwag normalized accuracy, 70.51% PIQA accuracy, and 42.75% LAMBADA accuracy. The learned-input control performs better on several evaluations, including HellaSwag and LAMBADA, so these results establish viability rather than performance parity. The fixed interfaces remove 100.7 million trainable parameters, yielding 1.711B-parameter models, but parameter reduction is not the central result. These single-run experiments distinguish architectural necessity from empirical utility: independently trainable token-specific input vectors are not required for the observed capabilities. A fixed identity interface also provides a controlled setting for studying representation learning downstream of an immutable input, without establishing where particular capabilities are localized.

Large language models (LLMs) offer a flexible approach to network intrusion detection, but direct classification of numerical flow records can be unreliable without traffic- specific decision boundaries. Retrieval-augmented generation (RAG) enables LLMs to leverage external experience; however, free-form textual experience requires the model to infer the numerical conditions that distinguish traffic classes. We propose SERA-IDS, a Structured Experience Retrieval-Augmented Intru- sion Detection framework that learns decision knowledge from classification errors. A Small Language Model (SLM) analyzes misclassified flows and generates structured rules containing behavioral descriptions, feature conditions, class-confusion infor- mation, tool-derived confidence, and provenance. A confidence gate admits supported rules into the Experience Library. During testing, the library is frozen, and retrieved class-diverse rules are condition-matched to the query flow and provided as evidence to the decision SLM. The same library is evaluated with three small, locally deployable SLMs, namely Llama 3.1, Phi-4:14B, and Qwen2.5:7B, without fine-tuning or paid hosted inference. On the test sets, SERA-IDS improves macro F1 on NF-BoT- IoT from 11.66%, 9.26%, and 7.83% to 86.46%, 69.50%, and 83.51%, respectively, and on NF-ToN-IoT from 3.82%, 6.17%, and 1.94% to 84.16%, 87.66%, and 83.37%. These results show that structured experience retrieval enables small, free, and locally deployable SLMs to achieve strong intrusion-detection performance, including performance exceeding that of the re- ported existing work used in our comparison.

Large language models (LLMs) are increasingly used as synthetic personas representing survey respondents. Their validity as substitutes for particular respondents depends on whether they reproduce individuals' decisions. We examine what information helps synthetic respondents predict each individual's later choices, using five conditions that add progressively richer information: no personal information, demographics, personality traits, cognitive scores, and finally the respondent's earlier survey choices as behavioral history. We use a two-wave panel of 845 US adults who completed measures of 14 behavioral biases (spanning risk, time preferences, overconfidence, and reasoning), so each respondent's earlier answers provide a human test-retest benchmark; in the behavioral-history condition, all items that score the target bias are withheld. At the population level, the average number of biases per respondent in every condition is close to the human average (7.1-8.1 biases, against 7.1 for humans). This aggregate similarity masks differences in variance: persona descriptions recover only 53-67% of human between-person variation, whereas adding behavioral history restores it to approximately the human level. At the individual level, description-based personas achieve only 7-12% of the informedness observed in human test-retest responses, while adding behavioral history raises this to 28%. The condition including behavioral history has the highest estimated informedness in all 17 demographic groups, whereas description-based conditions provide little or no information for some groups. Synthetic responses also exhibit stronger education- and income-related differences than human responses. For LLM synthetic personas, a respondent's past answers add more to individual-level prediction than a description of who they are.

Robots can acquire bad habits from a few defective moments in otherwise useful teleoperation. In mixed-quality robot data, normal and problematic demonstrations share most task behavior and differ only at a local action continuation. Full retraining is costly, while fine-tuning on clean data alone offers limited recovery under a small update budget. We ask whether the local difference can instead be fixed with only 1% of the full-training sample-backward budget. Using only episode-level retained/problematic labels, REDIRECT localizes the branch, assigns a coherent retained continuation to the original observations around it, and anchors shared behavior, without frame-level annotations or additional interaction. Across three randomized ManiSkill tasks and three seeds, REDIRECT raises the mean success rate from 68.2% to 90.3%, recovering 88.8% of the clean-retraining gap versus 22.1% for matched-compute fine-tuning. On a PiPER arm, it recovers 86.7-92.9% of the clean-only gap across cup insertion and towel folding. Local robot habits can therefore be repaired by spending the update budget on the behavioral difference rather than relearning shared behavior.

Crossing-based selection is well-studied, yet past research has overlooked multi-object and attribute selection with crossing gestures. We present viaCross, a pen-based technique in which crossing strokes define attribute constraints, paired with attribute widgets that visualize and allow subsequent edits to these constraints. A controlled study compared viaCross with traditional WIMP filter panels. Results show that viaCross was more efficient for complex object-level selections, requiring fewer strokes and maintaining efficiency as task difficulty increased. WIMP panels were faster and more intuitive for simple attribute-based selections, but participants encountered repeated deselections and occasional misclicks. viaCross matched panel performance for creating attribute selections but was slower during refinement, as widgets had to be recreated, indicating the need for persistent widgets or hybrid support with a WIMP-style interface. Overall, viaCross demonstrates that crossing-based gestures can provide an efficient and scalable approach to multi-object and attribute selection.

VeriContest is a benchmark of 1007 competitive-programming problems in Rust, each with a Verus specification, a judge-accepted solution, and a Verus proof. Its authors report that proof generation is the bottleneck for frontier models: given the specification and the code, the best model produces an accepted Verus proof for 13.95% of the problems on the first attempt. We report on solving the same proof-generation task with Rust-Prover, a verifier for Rust backed by Lean 4. The Verus specification and the Rust code are restated and translated into Lean, each specification becomes a theorem, and agents prove the theorems with Lean's kernel as the final check. All 1325 theorems of all 1007 problems were proved. 1259 of them were proved in one run of under 32 hours on Claude Opus 5.5, at a median of 3.2 minutes and $1.17 per proof, and 70% of them on the first iteration. The restated specifications were checked against the benchmark's test suites, and reviewed where no suite applies. None was wrong or weakened. The translated Lean programs were run on 21,413 of the benchmark's test cases and produced the same output as the Rust programs on every one. Across four Claude and four GPT models at five reasoning-effort settings, every current frontier model proves nearly all of a ten-theorem sample at every setting, and more effort raises the cost without raising the number of proofs. The cheapest Claude setting, Sonnet 5.5 at low effort, proves all of the 50 hardest theorems. We also rerun the benchmark's own Verus protocol with Claude Opus 5.5 on the 50 problems with the longest reference proofs. Opus 5.5 alone fails to prove one of them.

Multimodal skin lesion classification combines clinical images with patient metadata to improve diagnostic accuracy. However, complete metadata available during training may be only partially accessible at deployment, and resource-constrained settings additionally require computational efficiency. We address these challenges with a privileged-information distillation framework in which a multimodal teacher trained on complete metadata supervises a 9.2x smaller student trained with randomly masked clinical fields. Clinical fields are masked as whole groups at a per-sample rate drawn from U(0,1), so one training run covers the full metadata availability range. Fusion is residual, with metadata added as a gated correction to an unconditional image base. On the PAD-UFES-20 dataset, distillation under masked training improves balanced accuracy over cross-entropy training at every availability level, by an average of +4.7 points versus +1.8 points without masking. The masked student loses only 7.8 balanced-accuracy points as metadata decreases from complete to absent, compared with 36.6 points for the same student trained on complete metadata, highlighting the role of masked training in graceful degradation beyond distillation alone. Grad-CAM visualizations further show that the masked student's attention generally remains lesion-centered as metadata is withdrawn. The resulting compact model targets point-of-care settings, where clinical metadata is often incomplete.

In wireless sensor and mesh networks, modular robots, and shape-adaptive computers, computing modules attach, detach, or are replaced while the others keep running with their local state. A value computed under the old arrangement, such as a cached next hop, stays in memory but may no longer describe the current one, so a program can send to a neighbor that has left without any runtime errors. We present morph-aware computing, a programming model in which the application specifies a corrective update of such state, called a repair, and the compiler decides when it runs. In MorphLang, the repair is a Reconfigure branch next to the ordinary branches that handle sends, receives, and sensor samples. MorphC compiles MorphLang to bare-metal RISC-V and inserts a guard before every ordinary branch, so that each module repairs its state before any other branch sees a new topology. Relying on this order, MorphC also rejects sends whose target may be a literal or a value the repair does not always refresh. For a model of the code MorphC generates, we prove in Rocq that the repair precedes every later ordinary branch for any number of roles and topology changes. This shows that send-target checking is sound for a core language. On 19 MorphLang programs derived from seven network stacks, removing the repair worsens destination validity in ten of the 13 programs that declare one and never improves it. In a reduced reproduction of a released Contiki-NG defect, a callback-based version sends to a departed parent after 60 of 384 changes and the MorphLang version after none. The guards cost 12 cycles per loop in a microbenchmark, and on an FPGA the delay from each commit to the first send to the new neighbor matches RTL simulation.

Autonomous coding agents solve repository issues by reading code, running commands, editing files, and submitting patches. Extra inference-time compute yields gains only when it produces a useful repair and supplies reliable evidence for choosing one. Three behaviors decide both, and we argue they are teachable rather than byproducts of scale, so a policy can carry them instead of a scaffold. Location diversity remains narrow, since attempts return to the same site and extra samples add no coverage. Edit diversity is left unexploited, since methodologies that differ resolve complementary issues no single run reaches. Verification misleads, since a test the agent writes for its own patch accepts many incorrect ones. Directing search by execution feedback and scoring each patch against its own reverted tree resolves 52.8% of SWE-bench Verified using 48.1% of the agent-steps an eight-sample baseline spends. Training moves these behaviors into the policy. On the 270 issues held out from SFT and RL training, weighted supervised fine-tuning raises pass@1 from 31.9% to 35.2% and pass@8 from 46.7% to 51.1%. A reinforcement objective then trains the verifier against gold-labeled repairs and incorrect variants, crediting the assertions that detect them. It raises pass@1 to 43.0% and pass@8 to 60.7%, lifts verifier precision from 26.8% to 41.7%, and more than halves false acceptance. Resolution improves on two of three out-of-distribution suites and verifier precision on all three, and the gains hold at 7B, 14B, and 30B against published coder baselines.

We study constrained online convex optimization with adversarial convex costs and constraints ($\mathsf{COCO}$). At each round $t\in[T]$, a learner selects $x_t$ from a $d$-dimensional convex decision set $X$, after which an adaptive adversary reveals a convex cost function $f_t$ and constraint function $g_t$. Consequently, the learner incurs a cost of $f_t(x_t)$ and a constraint violation of $\max\{0,g_t(x_t)\}$, and aims to simultaneously minimize regret and cumulative constraint violation ($\mathsf{CCV}$) over the entire horizon. Existing algorithms achieve $O(\sqrt{T})$ regret and $\widetilde O(\sqrt{T})$ $\mathsf{CCV}$. We show that an online policy can achieve $O(\sqrt{T\log T})$ regret and $O(\log^2 T)$ $\mathsf{CCV}$, reducing the $\mathsf{CCV}$ from polynomial to polylogarithmic while retaining near-optimal regret. When all cost functions are either $\alpha$-exp-concave or $\beta$-strongly convex, the algorithm achieves $O(\log T)$ regret with the same $\mathsf{CCV}$ bound as above. Our approach combines continuous Hedge with elimination on shrinking feasible sets. The key observation is that whenever the mean of the Hedge distribution violates a constraint, Grünbaum's inequality guarantees that a constant fraction of the Hedge probability mass is eliminated. We use an adaptive learning-rate schedule and a potential function coupling the surviving volume with the learning rate to convert this probability-mass reduction into a bound of $O(\log^2 T)$ on the $\mathsf{CCV}$.

We study constant-delay enumeration for conjunctive queries with negation ($\texttt{CQ}^{\neg}$). It is known that $\textit{signed-acyclic}$ queries can be enumerated with constant delay after linear preprocessing time, using linked lists with skip links. We use a hypergraph width measure for $\texttt{CQ}^{\neg}$, the $\textit{fractional signed hyperorder width}$ ($\textsf{sfhow}$), which requires a single variable order to simultaneously handle every subset of the negative atoms, which Capelli et al. introduced to characterize the preprocessing time of direct access. $\textsf{sfhow}$ strictly generalizes signed-acyclicity (recovered when $\textsf{sfhow} = 1$) and fractional hypertree width (recovered on queries without negation). Our main algorithmic result is a variable-elimination algorithm that achieves constant-delay enumeration on input $I$ for any full $\texttt{CQ}^{\neg}$ query with preprocessing time $O(|I|^{\textsf{sfhow}})$. Furthermore, we show that using multiple variable orders can improve this bound, exhibiting an $O(|I|^{3/2})$ algorithm for $k$-cycle queries with at least one negative edge.

Text-to-video (T2V) diffusion models can reproduce copyrighted, violent, or explicit content, which motivates concept erasure: removing designated concepts from a pretrained model while preserving its behavior on everything else. Existing T2V erasure methods leave two problems open. Their frame-agnostic suppression can leave isolated frames in which an erased concept resurfaces, a frame-reactivation gap that clip-level averages obscure; and they are usually evaluated with one target concept or category at a time. We propose Frame-Aware Diffusion Erasure (FADE), a multi-concept video unlearning framework. FADE first applies a joint closed-form key/value edit that suppresses all target concepts, then trains per-concept frame-aware low-rank adapters whose strength is gated by the frame index and the denoising timestep to remove residual per-frame leakage. Each adapter is trained with the other targets' prompts as hard negatives, which keeps the concept-specific components of different adapters well separated, and a similarity-based soft router combines the adapters according to the prompt. With 16 concepts (objects, artistic styles, and nudity) erased from a single Wan2.1-T2V-1.3B backbone, FADE reduces the residual accuracy on the object benchmark to 4.9%, against 15.5% for the strongest of eight baselines, while keeping the VBench average within 0.9% of the unedited model. The ranking is unchanged under a VLM judge and a blinded human study, and the advantage over the strongest baseline carries over to prompts that combine several erased concepts, to 30 simultaneously erased celebrity identities, and to Wan2.1-T2V-14B, CogVideoX-2B, and HunyuanVideo-1.5.

Autoregressive transformers remain comparatively weak for protein sequence and structure generation. We study the role of target representation: amino acid tokens encode residue identities without explicit contextual semantics, while backbone coordinates require a discrete representation in our framework. We introduce two learned latent protein languages. Protein Latent Language (PLL) maps sequences to a 4,096-state contextual alphabet built on a frozen ESM-2 encoder, with one token per residue. Structure Latent Language (SLL) adapts GCP-VQVAE Lite with auxiliary sequence and confidence supervision while retaining decoding to backbone coordinates. We separately pretrain autoregressive transformer models on PLL and SLL tokens using next-token prediction, yielding PLLM and SLLM. Under matched downstream sequence training, PLLM has a fitted compute-scaling exponent of 0.038 versus 0.020 for the amino acid autoregressive model. In unconditional sequence generation, PLLM reduces the fraction of samples below a heuristic 1.5-bit residue-composition entropy threshold by 54% relative to the amino acid model across sampling temperatures. For sequence-to-structure prediction, replacing the original GCP-VQVAE Lite tokenizer with SLL reduces best validation perplexity by 34% under matched training. For long proteins, latent-token sampling is approximately 1,000 times faster than MSA-based AlphaFold2 in our measurements. In backbone generation, SLLM compares favorably with other generative models on diversity and novelty. We also observe early signs that using SLLM's internal token confidence for inference-time sampling can improve sequence-to-structure prediction quality beyond a single decoded sample. These results position learned latent protein languages as a promising substrate for autoregressive transformer scaling and inference-time sampling in protein generation.

Ising machines have emerged as promising hardware accelerators for intractable optimization and sampling problems, yet their practical impact increasingly hinges on the co-design of algorithms and hardware, where algorithmic demands shape new architectures and new hardware capabilities inspire entirely new algorithms. In this Review, we survey probabilistic algorithms designed for portability across diverse Ising platforms, advocating a top-down perspective that prioritizes principled methods with provable guarantees. We cover foundational methods such as simulated annealing and parallel tempering, including two-dimensional extensions that natively encode hard constraints, and examine approaches that expand the scale of solvable problems from cluster mean-field methods to variational samplers. We highlight the Probabilistic Approximate Optimization Algorithm (PAOA), a classical analog of QAOA that emerged directly from probabilistic hardware development, and explore how generative AI and Ising machines might reinforce each other: learned models propose global moves to accelerate optimization, while probabilistic techniques improve inference in large language models. Much as quantum computing has seen algorithms co-evolve with hardware, probabilistic and Ising computing stand at a similar inflection point. We outline a co-design framework for accelerating the capabilities and adoption of next-generation Ising machines.

Automated repair of High-Level Synthesis (HLS) designs using large language models (LLMs) is an emerging but underexplored problem. While LLM-based repair shows strong results on register-transfer level (RTL) Verilog, the only prior systematic study of HLS logic repair reports just 10.5% correction accuracy for GPT-4, with no analysis of why repair fails or what drives difficulty. We present the first comprehensive evaluation of LLM-based HLS repair across four models (GPT-4o, GPT-4o-mini, GPT-5.4, and Claude Opus 4.6) on 125 benchmark instances spanning eight logic bug types across three open-source HLS suites (CHStone, MachSuite, Polybench). We construct the first executable APR-style HLS repair benchmark with suite-specific functional oracles, enabling pass@k evaluation rather than the string-match approximations used in prior work. Design context and scale, rather than bug type alone, dominate repair difficulty: repair rates range from 6-45% on complex cryptographic kernels (CHStone) to 81-93% on compact algorithmic kernels (MachSuite) despite identical bug type distributions. We introduce solution multiplicity, the fraction of distinct patches generated across repeated repair attempts, as an empirical measure of repair underconstraint, and show it strongly predicts repair failure across all four models (Spearman rho = -0.393, p = 6.61 x 10^-20). Frontier models reduce underconstrained instances from 41-46 (GPT-4o, GPT-4o-mini) to just 3 (Claude Opus 4.6), with pass@1 improving from 42-53% to 73-76%. SHFT bugs remain consistently hard across all models, and semantic bug classes such as buffer indexing become reliably repairable only at frontier scale. These findings show that future APR benchmarks must include complex, executable, and weakly identifiable designs that remain challenging after frontier LLM repair.

Space infrastructures play critical roles in modern society, including satellite communications (SATCOM). Like the Internet, space infrastructures are vulnerable to cyber attacks, or space cyber attacks, highlighting the importance of managing cyber risks to space infrastructures, or space cyber risks. However, adequately managing space cyber risks is an open problem. In this paper, we propose the first Space Cyber Risk Management (SCRM) framework to systematically analyze and mitigate space cyber risks. The framework models space infrastructures, space missions, and space cyber attacks, while offering algorithms for space mission risk analysis and hardening. We demonstrate its usefulness by conducting a case study on real-world space cyber attacks against the SATCOM infrastructure implemented in our testbed. Our results show, among other things, that: (i) dealing with space cyber attack cascading effects is essential to space cyber risk management; (ii) the framework can effectively harden space missions; (iii) National Institute of Standards and Technology (NIST) security controls can effectively mitigate space cyber risks.

Software performance optimization requires identifying bottlenecks and improvement opportunities, and empirically evaluating the effects and trade-offs across performance objectives. Autonomous AI coding agents submit performance-oriented pull requests (PRs) to open-source projects, yet it remains unclear whether these changes reflect established optimization practices and adequately substantiate their claimed value. Extending our MSR 2026 Mining Challenge pilot study of 407 performance PRs, we analyze a sample of 1,130 agentic and 1,130 human-authored performance PRs collected through June 2026. We compare adoption outcomes and patch characteristics between the two groups, and examine their optimization practices and validation behaviors. The results show that agentic PRs are merged less often than human-authored PRs (54.4% vs. 73.3%), but the two groups use similar optimization strategies and report validation at comparable rates. Agentic PRs rely more on static reasoning and less on benchmarks (46.1% vs. 57.2%), although benchmark use converges by the end of the study period. Agentic PRs also report validation for code-smell refactorings as often as for resource-targeting changes, whereas human-authored PRs do so less often. Across both groups, about half of validated PRs report no quantitative performance metric, and relevant trade-offs are rarely quantified. Agentic optimization practice has become increasingly similar to human practice, but the supporting evidence remains incomplete. Establishing whether agent-proposed optimizations are supported by rigorous, quantitative, and multidimensional evidence remains an important challenge. These findings motivate evaluation infrastructure and review criteria that measure intended effects and relevant costs rather than treating the presence of validation alone as sufficient.

This work considers reconfigurable intelligent surface (RIS) aided multi-way communication systems employing QPSK. The objectives of such system is to allow multiple users to exchange information, exploiting the full-duplex capabilities of RIS. The system under consideration comprises $K$ user terminals and an RIS with $N$ reflective elements. Each user terminal is equipped with one transmit and $M$ receive antennas. To mitigate inter-user interference caused by the full-duplex operation of the RIS, three successive interference cancellation (SIC) techniques are considered. We investigate three SIC ordering methods: $1)$ descending channel variances, $2)$ increasing mean square error, $3)$ optimization approach which maximizes the combined channel gain within the system. The bit error rate (BER) performance of these three SIC methods are evaluated using extensive Monte-Carlo simulations for different numbers of RIS elements, ranging from 4 to 64, and a varying number of transmitting users, ranging from 1 to 5. Additionally, an RIS phase shift optimization method for RIS with reflection elements of varying amplitudes is considered. In this case the previous SIC optimization technique is adapted to address phase-dependent amplitudes in RIS reflection elements. Simulation results indicate that in both ideal and varying amplitude scenarios, when the number of RIS elements is small, SIC with ordering based on increasing mean square error achieves the best BER performance. However, as the number of RIS elements increases, SIC ordering based on the optimization method achieves the best BER performance.

Each run of an AI-driven research system (ADRS) is an expensive search over a vast solution space, and dependable evaluation requires many runs, making run data both costly to produce and valuable to retain for large-scale analysis. Yet this data remains fragmented: teams operate in isolation, ADRS frameworks emit results in different formats, and no shared infrastructure exists to aggregate or compare runs across problems and systems. We present ROAR, a solution for systematically unifying and analyzing heterogeneous ADRS outputs. ROAR addresses two challenges: reconciling heterogeneous ADRS outputs and enabling analytics across runs with different objectives and scoring functions. We achieve this through a relational schema and parsing layer that normalize heterogeneous ADRS outputs while preserving data lineage and temporal structure, and accommodating new systems without requiring schema modifications. From building a corpus of more than 900 runs from multiple ADRS, we show how pooled data can reveal properties of problem landscapes that are difficult to observe. Consistent with prior work, runs with identical configurations may converge to different scores. We find that many runs realize most gains early, and that the effectiveness of different strategies for incorporating prior solutions into the search process varies across problems. We further show that the pooled corpus is actionable and not merely analytical by using ROAR to configure ADRS runs. Together, these results illustrate how pooled ADRS data can expose problem-dependent structure in search behavior that is difficult to detect from any single system, team, or benchmark. Such cross-cutting insights are difficult to obtain while runs remain siloed; ROAR is the first infrastructure designed to unify them.

Hybrid radio frequency (RF) and visible light communication (VLC) networks have emerged as a promising solution for high-capacity indoor wireless connectivity in sixth-generation (6G) systems. However, the limited optical coverage and vulnerability of VLC links to line-of-sight (LoS) blockage under user mobility remain fundamental challenges. In this work, a mirror-based intelligent reflecting surface (IRS) is deployed to assist a dynamic indoor hybrid RF/VLC network, where each mobile user is exclusively assigned to either the IRS-enhanced VLC subnetwork or the RF subnetwork through a binary selection decision. A joint optimization problem is then formulated to maximize proportional fairness by jointly optimizing the RF/VLC technology selection, power allocation, and IRS mirror roll and yaw orientation angles. To enable real-time adaptability, the problem is reformulated as a Markov decision process (MDP) and solved using a cooperative multi-agent deep reinforcement learning (DRL) algorithm based on centralized training with decentralized execution. Simulation results demonstrate the superior performance of the optimized hybrid network compared with optimized standalone VLC and RF networks. The results further validate the practicality and effectiveness of the proposed DRL framework compared to widely adopted DRL algorithms as well as conventional model-based optimization approaches.

The BAIBAICHUCHU team participated in the Social Media Subtask of NTCIR-19 FinArg-3, ranking Chinese investor posts by Maximum Possible Profit (MPP). A three-track ensemble of lexical features, a FinArg-2-pre-finetuned MacBERT ranker, and an LLM judge reaches 0.734 in post-grouped development evaluation, but our best official run scores 0.517. All twelve submitted runs lie between 0.4598 and 0.5402, and our 26 unanimous three-track pairs score 0.500. A post-hoc audit finds that the submitted judge applied a long-only rule to bearish posts although MPP is stance-aware. Correcting it changes 28 of 87 official predictions without changing accuracy, yet lowers development accuracy from 0.680 to 0.622: a regime-specific semantic shortcut improved validation fit. We decompose ranking into directional text, volatility and horizon, and pairwise margin. A running-extremum model predicts $\sigma\sqrt{T}$ scaling, observed ex post in 502 price-aligned posts from a separate July 2026 collection. Pre-posting volatility scaled by the post-specific observation horizon, $\sigma_{\mathrm{pre},20}\sqrt{N_i}$, is associated with a later truncated-horizon MPP proxy (Spearman $\rho=0.320$; ticker-cluster 95% CI [0.133,0.466]) and correctly orders 61.4% of unequal-outcome pairs. Transferred text is nearly uncorrelated with the July outcome ($\rho=0.055$) and adds little conditional on this score and stance. Development reliability rises from about 0.60 to 0.93 as the labeled MPP gap widens. An earlier ERAI result of 0.6207 rules out universal unpredictability as a simple explanation. Evaluation should jointly consider text, market regime, historical volatility, horizon, and pair composition.

Instruction fine-tuning adapts a pretrained language model to follow instructions by training it on instruction–response pairs from a collection of tasks, such as summarization and question answering. Task-level poisoning exploits this task structure to manipulate the fine-tuned model into producing attacker-specified biased content on a particular target task, without requiring an explicit input trigger. Detecting such attacks is challenging because there is no explicit trigger to identify, the target task and biased content are unknown, and benign fine-tuning itself changes model behavior. We introduce Localize-and-Detect, a two-stage black-box auditing method for task-level poisoning that requires only outputs from both the base and fine-tuned models. In the first stage, we localize the target task by identifying candidate tasks on which the fine-tuned and base models have the largest differences in their next-token distributions. In the second stage, we search the shortlisted tasks for biased content that repeatedly appears in the fine-tuned model's responses but not in those of the base model. We evaluate Localize-and-Detect on 216 poisoned models across two model families, varying the target task, poisoning mode, poison budget, and type of biased content. Our evaluation demonstrates that Localize-and-Detect can effectively localize target tasks and detect biased content across a range of poisoning settings and models, with detection that tracks attack success and few false positives on clean models.

Recent world action models (WAMs) reuse pretrained video VAEs whose encoder latents directly condition downstream action policies. Quantization must therefore preserve not only reconstruction fidelity but also the policy-facing latent contract expected by the frozen policy. Direct NVFP4 leaves W4A4 quantization error uncompensated, whereas joint quantization-aware training (QAT) can recover reconstruction by moving this representation. On Wan2.1, joint QAT nearly matches FP32 VBench-7 (0.7403 versus 0.7409), yet LIBERO success collapses from 95.5% to 10.5%. Controlled decoder-only experiments show that activation quantize-dequantize operations alter the reconstruction signal and decoder Jacobian, redirecting the gradient returned to the encoder and inducing persistent latent drift. Based on this mechanism, we introduce LatentQuant, a two-stage NVFP4 QAT framework that first aligns the quantized encoder with its high-precision counterpart, then freezes it while adapting the decoder. Across Wan2.1 and Wan2.2, LatentQuant preserves near-baseline control and high reconstruction quality, achieving 95.75% success on LIBERO and 68.8% on RoboTwin. On NVIDIA B300 GPUs, NVFP4 execution achieves 1.17x-1.26x end-to-end VAE speedups over BF16 cuDNN.

Question answering over spreadsheet collections requires finding the correct workbook and computing over complete tables. We introduce Find-then-Compute (FiCo), which retrieves document summaries, disambiguates similar workbooks, and executes constrained Structured Query Language (SQL) over the selected full table. On DataBench (80 datasets, 1,810 questions), FiCo reaches 76.2% accuracy: 9.9 points above a strong TableRAG-style baseline on the same frozen workbook choices (66.3%) under the tracks' prespecified evaluators, and 63.4 points above prefix RAG (12.8%). On 508 MiMoTable questions, FiCo reaches 79.7%, versus 22.2% for prefix RAG. Giving the strong baseline the gold workbook raises it from 66.3% to 76.3%, exposing a 10.0-point source-selection cost under fixed compute. Despite 95.1% document recall and 98.5% executable SQL, only 81.3% of questions execute on the gold workbook. FiCo's advantage comes from integrating semantic source selection with exact, schema-grounded computation.