Papers

A durable assumption holds that graph analytics requires a purpose-built graph engine, and that relational systems are ill-suited to connected data. We argue the opposite for the workloads enterprises actually run. A columnar relational engine fronted by a graph query language matches or exceeds native graph engines on analytical graph queries, and - decisively - scales past the point where in-memory graph engines fail. We further argue that the node/edge property graph is not a more faithful model of connected data but a re-encoding of relationships that already exist explicitly in relational tables; reconstructing them at query time is pure overhead. We present ClickGraph and its Databricks-dialect sibling DeltaGraph, systems that translate Cypher directly onto the native relational schema - the tables, columns, and foreign keys as they already exist - and execute in place on ClickHouse, Databricks, or in-process on lakehouse files, with no import and no separate cluster. Because the output is ordinary SQL, an underperforming query is an open optimization surface: it can be rewritten, and the engine itself extended. We support the argument with a peer system's own published benchmark, in which a columnar engine outruns Neo4j by two-to-four orders of magnitude, and with reproducible measurements across the LDBC Social Network Benchmark suite.

Interactive simulations increasingly evaluate policies in markets populated by language-model agents. Their outputs can look economic—prices, profits, consumer surplus, and welfare—without instantiating the behavior named in the claim. We audit this risk in a multi-turn buyer–seller testbed for configurable hotel transactions. An initial implementation reported welfare gains from two marketplace guardrails of +87.4, +35.0, and +28.8 across a Qwen2.5 1.5B–14B ladder. It also gave guarded and unguarded agents different offer schemas and choice procedures. Holding the schema and buyer chooser fixed changes the paired contrasts to +7.2, -13.9, and +23.8. The four largest 14B single-generation effects averaged +229; after three generations per profile-condition, they averaged +37.6 (95% bootstrap interval [-34.2, 109.3]), while generation residuals account for 49.9% of variation in this post-hoc probe. A seller-incentive check is non-monotone: increasing profit pressure produces less profit than the default seller prompt. Scripted positive controls show why this matters. A profit-maximizing seller already attains first-best welfare, so guardrails mostly redistribute and reduce welfare; they create welfare only when the seller is explicitly programmed to force inefficient bundles. We contribute a construct-validity contract separating incentive validity, protocol isolation, stochastic stability, and welfare accounting, and returning INVALID or INCONCLUSIVE before substantive policy claims. In our case, the original estimate is INVALID under protocol isolation, while the controlled study remains INCONCLUSIVE under incentive validity and stochastic stability. The case does not show that guardrails are ineffective; it shows their apparent value is unidentified until the simulated agents and protocol pass these checks.

There is tremendous value in humanoid robots taking on physically demanding, hazardous, and repetitive work in spaces built for humans. However, a useful robot for these spaces must coordinate locomotion, whole-body motion, perception, contact, and operator supervision. We present a robot-local, runtime-editable behavior authoring and runtime system that addresses these challenges. We argue that behavior architecture can be a primary enabler of capability, speed, and reliability, and that runtime editability enables fast behavior creation, adaptation, extension, and combination. Our behavior architecture combines object-centric Affordance Templates, a tree structure that provides organization and logic, and runtime-editable perception through a behavior scene and primitive scene actions. Our operator interface remains continuously synchronized to the robot for runtime authoring, monitoring, and repair. Action primitives execute through a whole-body controller that supports concurrent body motions and walking. Demonstrations of our system cover six task variants on Unitree H1-2 and Alex. We execute a push door traversal in 34 seconds and sort six balls by color in 45 seconds under human disturbance. Timed authoring sessions show scratch creation of new loco-manipulation behaviors and adaptation of existing ones in hours. Comparison against the literature finds our approach to be competitive with recent learned systems.

While 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction and novel-view synthesis, scenarios with limited input views often lead to poor reconstruction quality and artifacts in rendered novel views. Recent efforts attempt to utilize powerful diffusion priors, yet they typically process rendered and reference views concatenated along an additional dimension in a single network. These methods overlook an inherent nature that different views should maintain appearance similarity but differ in structure due to view shifts, leading to blur caused by conflicts between the two properties. In this paper, we propose DualDiff, a novel pipeline that leverages dual diffusion priors with a Structure-Appearance Attention (SAA) module to introduce reference guidance for refining low-quality novel views rendered from flawed 3D representations. Specifically, we retain one diffusion branch to focus on extracting structural information from the low-quality novel views, while introducing another branch to ensure appearance consistency with reference views. Furthermore, we present a 3D reconstruction framework named DualDiff3D, which integrates a reliability-enhanced Render-Refine-Optimize (RRO) loop to progressively and robustly incorporate the refined novel views, yielding more accurate 3DGS. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods even in the inference-only setting, with further performance gains achievable through training. Our code and pre-trained weights are available at https://github.com/Akaneqwq/DualDiff3D.

Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from option wording, answer correlations, or language priors. To reduce such shortcuts, we introduce TempCloze, a video cloze benchmark for evaluating visual temporal reasoning in Video-LLMs. Given the beginning and ending clips of a video, models must identify the true missing middle from four candidates. TempCloze contains 1,521 carefully filtered videos from seven sources, mainly long-take and egocentric videos. We construct same-source distractors along three dimensions: Semantic asks what event should happen, Alignment probes when it should occur, and Progression tests how it should unfold, while shared scenes and objects reduce appearance cues. Our evaluation of 10 proprietary and 21 open-source Video-LLMs reveals Alignment as the primary bottleneck: models often recognize plausible semantic content and local event progression but struggle with temporal alignment. We further conduct error pattern and behavioral sensitivity analyses on TempCloze-Mixed and TempCloze-Hard with four representative models to examine where errors arise and how candidate order, context direction, visible span, frame density, and test-time scaling influence model choices.

Historically, retrieving rainfall data from satellite imagery has been the domain of space agencies. However, in recent years, the development of cheaper, more compact satellites (SmallSats) capable of detecting rainfall proxies has led to a significant increase in private-sector initiatives for satellite launch and surface precipitation products. This rapid growth has yet to be matched by data validation efforts. Consequently, the need for a robust tool to detect anomalies in near-real-time data before it is disseminated to the public has become critical. In this paper, we present the development of an anomaly-detection system to identify artifacts in global satellite-based rainfall products. The developed framework leverages pre-trained computer vision models and incorporates scarce human-labeled data to detect specific anomalies. Our proposed anomaly detection strategy is tested on data from the Special Sensor Microwave Imager (SSMI) and the Special Sensor Microwave Imager/Sounder (SSMIS). Results demonstrate the efficacy of our approach at separating regular orbits from artifact-containing orbits for each satellite, with performance comparable to state-of-the-art in-place methods. Additionally, the framework offers explainability and the capacity for iterative refinement following false-positive or false-negative classifications.

Face forgery detectors often achieve strong results on controlled benchmarks, but their reliability under realistic image degradations remains limited. This paper presents a standardized benchmark for face forgery detection using the Multi-Dimensional Face Forgery Image (MFFI) dataset and evaluates performance on both clean and degraded test partitions. We compare six model families, including convolutional networks, transformer-based models, and a frozen self-supervised DINOv3 backbone, across spatial, spectral, and hybrid input representations. The results show that clean-set performance is not a reliable indicator of robustness under compression, resizing, and blurring. Xception with RGB obtains the best clean performance, reaching 0.884 mean ROC-AUC, but degrades substantially on the harder partition. In contrast, frozen DINOv3 achieves the strongest degraded-set result, with 0.726 mean ROC-AUC, while training only a linear classification head. The representation analysis indicates that Fourier-domain cues are most useful when combined with RGB information, whereas purely spectral inputs consistently underperform spatial representations. Qualitative attribution maps further suggest that convolutional detectors focus on localized artifacts, while DINOv3 relies on broader facial structure. These findings reinforce the need for degraded evaluation protocols and highlight self-supervised visual representations as a promising direction for robust face forgery detection. Our source code is publicly available at https://github.com/lucasdocunha/FaceForgery-Benchmark/.

Accurate radio planning is a fundamental requirement for the deployment of wireless networks in indoor environments, where signal propagation is strongly affected by walls, partitions, and other structural obstacles. Despite the availability of standardized propagation models, their ability to represent the characteristics of specific deployment scenarios is often limited, motivating the use of measurement-driven approaches. In this context, this paper presents a data-driven case study of next generation NodeB (gNB) placement optimization in an office using measurements collected from an experimental fifth generation (5G) testbed. A propagation model is trained from reference signal received power (RSRP) measurements using distance and wall count as input features and integrated with a combinatorial search framework. The proposed workflow is used to evaluate alternative deployment strategies under different optimization criteria. Results indicate that satisfactory indoor coverage and improved cell-edge conditions can be achieved with a small number of gNBs.

Compressed context is usually carried as human-readable text or as rendered images that must be decoded, even when its consumer is a language model. We introduce LatentPress, which writes conversational histories and long documents into a third representation: continuous memory tokens that a frozen decoder reads directly through its input-embedding interface, with no text reconstruction at inference. A small reader-matched writer compresses $4$-$16\times$ while training only an adapter (4.2M-26.2M parameters, $\sim\!0.1\%$ of the decoder). On LongMemEval, LatentPress reaches $0.504$ accuracy at $7.70\times$ compression versus $0.490$ for uncompressed evidence, outperforming text summaries (0.184) and OCR-based compression (0.426 to 0.312). On LongBench-QA, in-domain writers match or exceed raw-context reading at $4$-$8\times$ compression, while $16\times$ trails raw. Writing takes 43ms per conversation, roughly an order of magnitude faster than text summarization or OCR reconstruction, and reading is $5$-$9\times$ faster than raw context or cached OCR. We validate the interface under two transfer settings, zero-shot from UltraChat to LongMemEval memory QA and from LongMemEval-derived QA to unseen LongBench document domains, establishing direct soft tokens as a practical machine-facing context interface beyond text and vision. The implementation of the experiments could be found at: https://github.com/HJSang/LatentPress.

Learning- and LLM-based software vulnerability analysis is only as trustworthy as the data it is trained and evaluated on, yet that data is rarely examined as a first-class object. We investigate the data behind vulnerability analysis through a dataset-centric taxonomy that separates what an artifact is (code, metadata, patches, tests/PoCs, reasoning, traces), how good it is (realism, label evidence, scale, diversity, leakage, availability), and what it is used for. From a systematically assembled corpus of 1522 papers covering 2016-2026 plus foundational earlier work we deep-code a tiered set of 111 anchor papers, backing every affirmative rubric-graded value with a verbatim span, and we report, per attribute, both how much it has been studied and how well datasets achieve it. The results trace an evidence ladder: executable artifacts are the only major type where 15 of the 24 datasets are both graded real-world and carry labels that received an independent check, while code-sample datasets-the largest category in both the auto-tagged corpus and the anchor set-are the least realistic: 20 of the 41 draw their vulnerabilities from authentic projects or CVEs, but only 3 keep the sample at the unit the code is deployed in, and only 2 do both-though these are coarse component tests, and just one code-sample dataset meets the codebook's stricter full-context real-world grade. Among these, leakage goes unaddressed by 49 of the 90 datasets where it applies, more than a quarter say nothing about availability, reasoning data has arrived only recently and is mostly model-generated, and primary trace corpora remain limited to three datasets, the total after a corpus-wide screen and a full-text check of every candidate it surfaced, with further datasets releasing traces secondarily behind benchmarks and harnesses.

Ruby is a dynamically typed and object-oriented programming language. Its primary implementation, CRuby, contains a bytecode virtual machine and a mature lazy basic block versioning (LBBV) just-in-time (JIT) compiler called YJIT. In order to both implement more advanced optimizations than YJIT supports and also encourage more outside contributions, we present a new method-based JIT called ZJIT. Like YJIT, ZJIT compiles from bytecode to machine code. Unlike YJIT, ZJIT has multiple global and local optimization passes. ZJIT's high-level intermediate representation is in static single assignment (SSA) form. In order to optimize Ruby's local variables, ZJIT lifts local variables into SSA values. This is a departure from how other Ruby compilers handle locals: other JIT compilers either leave local variables as memory loads and stores or do advanced partial evaluation to recover SSA values from memory. While implementing locals, we (re-)discovered what features make local variables in Ruby especially challenging to compile correctly and efficiently. We demonstrate these features and illustrate how we solved these problems in ZJIT.

Security evaluations of decentralized federated learning (DFL) typically focus on how Byzantine participants behave, while largely overlooking which participants are compromised. Yet, because aggregation is distributed over a communication graph, the placement of Byzantine nodes determines how malicious influence propagates through the network. We therefore treat Byzantine placement as an explicit adversarial decision and formulate the attacker's objective as selecting, under a fixed compromise budget, the set of participants that maximizes its finite-time impact on honest nodes. To approximate this objective without executing the learning process for every candidate placement, we introduce Byzantine Placement Influence (BPI), a set-level measure derived from the actual gossip dynamics that quantifies the cumulative exposure of honest nodes to Byzantine sources over the training horizon. Unlike placement criteria based on node centrality heuristics, BPI directly accounts for weighted multi-hop propagation and interactions among compromised nodes. We develop efficient algorithms for optimizing BPI and evaluate them across six heterogeneous graph families, untargeted model poisoning, and backdoor attacks. BPI-guided placements consistently identify highly damaging configurations across different network structures and remain effective when the linear gossip assumption is relaxed through Byzantine-robust aggregation. Our results show that Byzantine placement is a critical but under-modeled dimension of DFL threat models and robustness evaluations.

Black-Box Optimization (BBO) has broad applications, while traditional algorithms such as evolutionary algorithms and Bayesian optimization face efficiency challenges as real-world BBO problems grow increasingly complex. Data-driven optimization has been the most popular paradigm to improve the efficiency of BBO, by learning from data. Offline data-driven optimization seeks high-quality solutions using only a fixed set of previous evaluations, attracting substantial attention because it requires no additional online evaluations. Many offline optimization methods have been proposed, but a fundamental question remains unanswered: what learnability is sufficient for offline optimization? Prior theoretical studies show that Probably Approximately Correct (PAC) learnability is insufficient, as the optimal region may remain poorly learned even when most regions are well learned. In this paper, we propose algorithm-dependent learnability, which requires accuracy only on the optimizer's trajectory. We prove that its value-query form is sufficient for representative discrete settings, including greedy and local search for submodular maximization, while its first-order analogue is sufficient for projected gradient descent on convex minimization. Motivated by this notion, we formalize a trajectory-learning framework comprising trajectory construction, trajectory modeling, and candidate generation, and analyze existing trajectory-based methods under it. We further propose Uncertainty-aware Gradient-guided Trajectory Learning (UGTL), which constructs locally coherent improvement trajectories reflecting plausible search paths, models them with conditional diffusion, and selects a diverse candidate set. Our experiments show that UGTL achieves the best average rank, 3.1/25, among 25 methods on Design-Bench tasks, and confirm that our trajectory construction plays a significant role in the improvement.

The growing rate at which LLM agents interact with one another raises key questions about language evolution in multi-LLM-agent settings, with implications for safety and monitorability as well as for linguistic accounts of LLMs. To address these questions, we introduce GlossoGen, a novel platform for studying multi-agent language evolution in complex scenarios. Within GlossoGen, we build the SaveVeyru scenario, which requires agents with partial information to communicate under pressure. We find that language evolution does occur between LLM agents, that the resulting languages are compositional and morphologically productive, and that they deviate from the LLMs' English prior in ways that render them incomprehensible to humans. Moreover, we identify several qualities essential to this evolution: pressure towards efficiency; the strength of the models backing the agents; and access to a "postmortem" stage in which agents can agree on linguistic conventions. Importantly, we observe that different conditions govern the transmission of language to new agents. Specifically, we find that agents learn new languages from usage alone, take an active role in this learning, and that while stronger models are required for novel language emergence, weaker models can learn an existing language once it has emerged. Taken together, our results indicate that current LLMs have the potential for cumulative cultural evolution – previously attested only in humans – with mixed populations of agents developing capacities that go beyond their lowest common denominator.

This work considers the multidimensional approximate agreement problem. In this problem, $n$ parties in a distributed system, up to $t$ of which may be corrupted by a Byzantine adversary, need to output vectors that are close to each other and that lie inside the convex hull of all non-corrupted input vectors. We assume that nodes communicate in a fully-connected authenticated network and analyze synchronous and asynchronous communication models. The focus of this work is on the contraction factor of approximate agreement protocols. The first multidimensional approximate agreement protocols had a contraction rate of $1-1/n$(VG, PODC'13) and $\sqrt[d]{1/2}$(MH, STOC'13). While a rate below $1$ is sufficient for convergence, it is not sufficient for practical applications. To date, the best known convergence rate of approximate agreement algorithms is $\sqrt{7/8}\approx0.935$ (FN, DISC'18), which is achieved through the MidExtremes protocol. This stands in contrast to the lower bound on the convergence rate in the $1$-dimensional setting, which is $1/2$. In this work, we propose BallMidpoint - a novel approximate agreement protocol with a contraction rate of $1/\sqrt{2}\approx 0.707$ in the synchronous and the asynchronous communication models. This algorithm satisfies the optimal resilience under convex validity. The presented contraction rate is achieved by choosing the midpoint of the smallest enclosing ball of the so-called local safe areas, and it is tight for the presented algorithms. Similar to (FN, DISC'18), our algorithm is coordinate-free, and the point inside the safe area can be computed efficiently. This work presents the first multidimensional approximate agreement protocol where the convergence rate is closer to the best known lower bound rather than the upper bound of $1$.

Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steering future actions. Such skills may leak secrets, corrupt code, bypass approvals, or stage data for exfiltration only after a concrete user task and workspace state make the unsafe action appear useful. This makes pre-install vetting insufficient and calls for runtime, task-conditioned protection. We propose Defense-as-Skill, a defense paradigm that implements the runtime guard itself as an installable, inspectable, and editable skill. Our guard, SkillSonar, runs alongside untrusted task skills and checks sensitive actions against the user's task boundary, routing each action to an allow, replan, or confirmation decision without modifying the underlying agent runtime. To study this setting, we construct SCOPE-R, a task-conditioned dataset covering 6 risk families and 21 sub-categories, with 206 attack-confirmed malicious instances and 43 benign tasks. We then improve SkillSonar on the SCOPE-R training subset using runtime guard-skill evolution, a Monte-Carlo Tree Search procedure that evolves the on-disk guard skill from feedback on the rollouts. Across Claude Code and OpenClaw, the evolved guard substantially reduces attack success while maintaining a favorable safety-utility trade-off; on repeated GLM-5 runs, ID ASR drops from 0.482 to 0.104 and OOD ASR from 0.606 to 0.115, with gains transferring across victim models, held-out risk families, and external benchmarks. These results show that runtime guards can be skill-native, transparent, and evolvable policy artifacts for skill-augmented agents.

We construct additive rank-metric and sum-rank-metric codes from Drinfeld modules by restricting bounded-degree morphisms to prime-to-characteristic torsion. For supersingular Drinfeld modules of rank $r$ in characteristic $\mathfrak{p}$ of degree $d$, the stabilization formula for morphism spaces yields rank-metric codes of $\mathbb{F}_q$-dimension $mrt-c$ and minimum distance $r-t+1$, where $c=r(r-1)(d-1)/2$. Simultaneous restriction to $\ell$ distinct degree-$m$ torsion modules gives additive sum-rank codes of the same dimension and minimum distance at least $\ell r-t+1$. Their normalized Singleton defects tend to zero, while in characteristic $(T)$ the module $\phi_T=\tau^r$ makes the defect vanish and produces an explicit MSRD family. We identify this family with a skew Chinese remainder theorem code supported on central skew polynomials and prove that its poly-skew weight is exactly $m$ times its sum-rank weight. This gives a specialized Singleton-type bound and a polynomial-time unique decoder up to the full sum-rank unique-decoding radius. We also derive a Welch-Berlekamp-type filter equation for the general supersingular sum-rank construction; it becomes an effective decoder whenever bases of the relevant morphism spaces and the restriction maps are computable.

A pair $(\mathcal{A}, \mathcal{B})$ of families of subsets of $[n]$ is cancellative if whenever $A, A' \in \mathcal{A}, B \in \mathcal{B}$ satisfy $A \cup B=A' \cup B$, then $A=A'$, and whenever $A \in \mathcal{A}, B, B' \in \mathcal{B}$ satisfy $A \cup B=A \cup B'$, then $B=B'$. We show that for every cancellative pair $(\mathcal{A}, \mathcal{B})$, the inequality $|\mathcal{A}||\mathcal{B}| \le 2.25^n$ holds, matching Tolhuizen's $(2.25-o(1))^n$ lower bound construction.

This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems without human intervention. We introduce Harness-of-Harness (HoH), a framework that enables coding agents to continually improve software during autonomous development. HoH operates on existing coding-agent harnesses, and organizes their executions into iterative planning-coding-testing loops. To sustain improvement across loops, HoH balances repair with capability growth, scopes development into small and verifiable increments, separates implementation-time testing from independent evaluation, and constrains verifiable outputs rather than prescribing agent workflows. It progressively exposes deliverables, role-specific tools, and skills, encourages reuse rather than recreation, and maintains versioned project histories. On GameCraft-Bench, FrontierSWE, and ProgramBench, three harness-model pairs (Codex with GPT-5.5, OpenCode with DeepSeek-V4-Pro, and Pi with MiniMax-M3), HoH consistently outperforms the corresponding standalone harnesses, achieving an average relative gain of 52.25 percent and a maximum gain of 82.86 percent after three iterations. In a multi-day deployment with more than 70 iterations, HoH autonomously develops a first-person-shooter game, featuring a coherent storyline, fully implemented core mechanics, human-playable experience, polished visuals and integrated audio. Github: https://github.com/Flesymeb/HarnessOfHarness Project Page: https://flesymeb.github.io/HarnessOfHarness/

Beyond semantic content, camera parameters play a pivotal role in dictating the geometric perspective and appearance of any given image. While recent image editing models excel at semantic and stylistic manipulation, they struggle with explicit camera parameter control. When handling large perspective shifts, instruction-driven models face a dilemma: they either suffer from structural tearing or generate conservative outputs that ignore geometric instructions. To address this, we introduce CameraEditor, a framework that reformulates camera-controlled editing from a spatial problem into a temporal sequence prediction task. By leveraging the temporal coherence of video diffusion models, our approach integrates an explicit geometric perception module with a dynamic reference routing mechanism. This allows us to construct geometrically rigorous visual reference pairs via dynamic panorama cropping, overcoming the ambiguity of text-based instructions. Furthermore, CameraEditor strategically inserts intermediate transition frames to decompose large perspective shifts, providing a robust temporal buffer that preserves content identity and spatial coherence. We construct a training dataset of 5,760 instances. As an independent contribution, we introduce CamEditor-Bench, a model-agnostic evaluation suite of 462 test cases. Extensive experiments demonstrate that CameraEditor achieves state-of-the-art camera control precision and source identity preservation, outperforming existing methods.

Vehicles and roadside infrastructure are increasingly equipped with sensors capable of perceiving their surroundings. Sharing this information through vehicle-to-everything (V2X) communications is a key enabler of Day-2 applications and is supported by the ETSI collective perception service (CPS). While CPS is expected to play a fundamental role in future intelligent transportation systems, its operation may significantly increase channel load, posing challenges in terms of radio resource utilization, communication reliability, and information management. This paper reviews the current status of CPS standardization and investigates its impact in dense deployment scenarios where connected vehicles communicate through fifth-generation (5G) New Radio-V2X (NR-V2X) sidelink (SL) communications. The main contribution is a realistic evaluation of communication reliability, latency, channel occupancy, and information usefulness under different object-selection strategies for collective perception messages. The analysis is conducted through a network-level simulation framework integrating empirical object traces derived from real-world datasets, thereby avoiding the limitations of synthetic traffic models. Results show that perception message generation and radio access mechanisms are tightly coupled and should be jointly designed to maximize the benefits of collective perception services.

Codes over graphs store symbols on edges of a complete undirected graph on $n$ vertices with a self-loop at each vertex; erasing a node removes all its incident edges. Extending Yohananov, Efron, and Yaakobi's construction, we obtain binary codes correcting any three node erasures at infinitely many prime lengths $n$, unconditionally, with redundancy $3n-2$, one bit above the graph Singleton bound. The earlier construction has the same redundancy but requires $2$ to be primitive modulo $n$, which is not known for infinitely many primes. We give a deterministic decoder for these triple-node codes using $O(n^2)$ binary operations and construct Singleton-optimal binary triple-node codes at $n=6,8,10,12$. When $2$ is primitive modulo an odd prime $n$, we extend their double- and triple-node codes to binary codes correcting $\rho$ node erasures with redundancy $\rho n-(\rho-1)$ for $2\leq\rho\leq(n+1)/2$, saving $\rho-1$ bits over the binary symmetric rank-metric construction when $\rho<(n+1)/2$. Over every finite field of size $q$, the node weight of a word is the least number of vertices whose erasure removes its support. We give exact formulas for ball volumes in this node metric and prove that, for fixed $q,t$, the radius-$t$ volume is asymptotic to $\binom nt q^{tn-\binom t2}$ as $n\to\infty$. We obtain existence and covering bounds; for fixed $q,\rho$, we show that linear $\rho$-node-erasure-correcting codes exist with redundancy at most $\rho\log_q n+O_{q,\rho}(1)$ above the graph Singleton bound. Finally, reformulating Yohananov and Yaakobi's criterion, we show that a linear code over any finite field is Singleton-optimal for $\rho$ node erasures if and only if its dual is Singleton-optimal for erasures of the coordinates inside any $n-\rho$ vertices.

This paper investigates $k$-visibility, where a line of sight can penetrate up to $k$ obstacles. While computing the $k$-visibility polygon from a single query point is well-studied, existing spatial preprocessing approaches rely on full $O(n^2)$ line arrangements through all vertex pairs without characterizing the minimal set of topological boundaries. We present a refined cell decomposition framework that isolates the exact geometric events governing $k$-visibility: primary vertex horizon lines and secondary mutually critical hinge lines. We prove that this minimal set of partition lines yields a spatial decomposition of $\Theta(n^4)$ cells within which the combinatorial structure of the $k$-visibility polygon remains strictly invariant. By leveraging a combinatorial $\delta$-compression scheme across cell boundaries, we achieve an overall storage complexity of $\mathcal{O}(n^4)$ while supporting optimal $\mathcal{O}(\log n + m)$ query time to reconstruct explicit $k$-visibility polygons of size $m$. Our framework naturally extends to polygons containing holes.

As AI systems are increasingly used to draft radiology reports, reliably evaluating their clinical quality remains a critical challenge. Large language model (LLM)-based metrics are now the best-correlated with radiologist judgment, yet they output a single opaque score that neither a clinician nor a model builder can easily interpret or audit. We introduce RadMatch, a multi-stage, LLM-based metric that decomposes report comparison into a structured finding-level matching with significance-aware scoring and error characterization across seven clinical attribute dimensions (status, location, severity, morphology, certainty, longitudinal comparison, and measurement). The main score is the actionable-error count, both interpretable and auditable. Candidate findings are graded correct, partial, or incorrect, and unmatched findings are counted as missed or hallucinated. Triage and actionable safety recall/precision and per-subset views add complementary, deployment-oriented lenses. Across two expert benchmarks, RadMatch is the most clinically aligned metric, matching inter-radiologist agreement on ReXVal and more than doubling the best prior metric on the harder RadEvalExpert. Relying only on few-shot prompting, it is designed to extend to other modalities and anatomies. We will release RadMatch as open-source code with an interactive dashboard for inspecting results.

Let $q$ be an odd prime. Let $\zeta_q$ be a primitive $q$th root of unity, and put $K=\mathbb{Q}(\zeta_q)$, with ring of integers $\mathcal{O}_K=\mathbb{Z}[\zeta_q]$. As $q$ ranges over odd primes, we prove that the decision version of the Shortest Vector Problem ($\mathsf{SVP}$) in the canonical $\ell_2$-norm is $\mathsf{NP}$-complete on full-rank free submodules of $\mathcal{O}_K^2$ by giving a deterministic polynomial-time many-one reduction from Exact Cover by 3-Sets (X3C). The module rank is fixed at two. The main obstacle is closure under the action of $\mathcal{O}_K$. A module containing a nonzero vector also contains every scalar multiple of that vector by a nonzero element of $\mathcal{O}_K$, and some of these multiples may be shorter. Three ideas overcome this obstacle. First, we map the Bennett–Peikert Reed–Solomon lattice to a principal cyclotomic ideal and use Wan's point-count estimates to prove that a coset of this ideal contains many binary coefficient representatives. Second, we construct a checker whose canonical squared norm encodes the X3C equations, with a controlled nonnegative error term. Third, the checker and a second module coordinate combine with a separation bound for ideal cosets to rule out short vectors in NO instances. Each constructed instance consists of an odd prime $q$, two integral generators whose $2\times2$ generator matrix has nonzero determinant, and an integer squared threshold. The construction also gives $\mathsf{NP}$-hardness of search-$\mathsf{SVP}$ under deterministic polynomial-time Turing reductions with at most one oracle call.

A long-horizon agent's trace outgrows both of its consumers: the human observer monitoring the run, and the agent itself, whose bounded context the trace must be folded back into. We present a live trace model, an append-only event ledger folded incrementally into typed run state and compiled into per-consumer views, and evaluate it for both consumers against deterministic ground truth. For the observer side, evaluated with an LLM reader as proxy, the compiled view answers monitoring questions using approximately 14x and 15x fewer input tokens (by reader) and at 5-7x lower cost than a budget-capped single-call reading of the raw trace, with higher accuracy (0.85-0.87 versus 0.48). Because the questions were co-designed with the view schema, we treat the token and cost reduction, conditional on schema coverage, as the transferable result. For the agent, on 120-link sequential-dependency tasks, mechanisms that maintain the task's running statistic in per-step state succeed where full-context prompting fails (30/30 versus 8/30 under a clean protocol, n=30, labeled descriptive owing to benchmark-system co-development); a prompt-level scratchpad matches the fold's accuracy at lower cost, and a two-arm decomposition attributes the fold's accuracy to its deterministic aggregate and its cost advantage to its compactness. The fold's remaining value over cheaper alternatives is deterministic auditability and serving the observer from the same state. We derive eleven candidate requirements for trace folding from observed failures and delimit them with an order-sensitive task family on which the fold ceases to help. Code, benchmarks, a regenerable synthetic corpus, and all workbench traces are released.

We enable backscatter communication in the battery-less mobile Internet of Things (IoT). Backscatter communication is extensively studied in static settings. Existing designs are, however, fundamentally mismatched with mobility and time-varying energy patterns. Channel conditions rapidly fluctuate, impacting the achievable data rates and thus transmission costs. Energy availability varies unpredictably, possibly forcing devices to remain quiescent to recharge energy buffers. The two issues compound each other: while recharging, a battery-less mobile IoT device may miss more favorable channel conditions. We design a lightweight decision system that dynamically determines when to transmit by checking short-term trends in signal strength, while using Non-volatile Memory (NVM) to retain packets in unfavorable channel conditions and across energy failures. Using a prototype we built and real-world mobility and power traces, we compare our design against a rate-adaptive baseline that only considers the instantaneous channel conditions. Experimental results show that our system improves throughput by up to 5.16x while reducing transmission energy consumption by up to 47.3%, with only 0.23% - 7.3% additional energy overhead.

Augmented reality (AR) facilitates human-robot collaboration (HRC) by enabling in-situ spatial visualizations of the robot and the joint task. However, in safety-critical HRC scenarios such as search-and-rescue, spatial visualizations may also reshape visual attention in ways that create competing situational awareness (SA) demands, potentially introducing new safety concerns. While prior AR-HRC work suggests potential benefits for SA, rigorous evaluations that jointly consider robot and environmental awareness across multiple levels of SA remain limited. We address this through a between-subjects study with 30 participants comparing custom AR and mobile interfaces presenting equivalent information, measuring robot and environmental SA with the Situation Awareness Global Assessment Technique (SAGAT) across all three levels, with concurrent eye tracking to identify the attentional mechanisms underlying any SA differences. Both interfaces achieved high usability; relative to the mobile baseline, AR improved perception-level awareness of the robot but yielded no gains in higher-level robot awareness or in environmental awareness at any level. Gaze analysis explained this: AR freed attention from the map, but that attention was re-invested in the conformal visuals rather than the physical environment. Freeing the eyes from a screen is not the same as directing them to the world, a distinction AR interfaces for safety-critical HRC must design around.

Large language model (LLM) fine-tuning is increasingly shifting toward data generated on edge devices, where memory, computation, bandwidth, and connectivity constraints make conventional federated learning difficult to sustain. Split federated fine-tuning (SFT) improves client-side efficiency by offloading most model parameters and computation to the server but requires step-by-step bidirectional communication loop across the split interface and forces continuous client involvement throughout training. In this paper, we present L-shaped SFT, a split fine-tuning framework that removes this bidirectional bottleneck. Our key insight is that weight tying in modern LLMs enables server-side hidden activations to be directly supervised using target embeddings, allowing the training loss to be computed on the server without returning server outputs to the client. To further eliminate the need for continuous client participation, based on L-shaped SFT, we introduce one-shot SFT, in which clients upload activations once and then go offline while the server continues optimization over cached representations. We implement our design in a real system testbed with heterogeneous edge clients, including commercial smartphones and NVIDIA developer boards. Experiments demonstrate that our schemes significantly reduce communication costs and client online time compared with existing SFT baselines.

Composed image retrieval (CIR) retrieves a target image from a reference image and a text modification. This paper studies metadata-available CIR reranking, where a fixed CIR model first returns a candidate pool and gallery metadata is then used for second-stage concept-guided scoring. We introduce AutoConcept, a training-free reranker that converts concept evidence into an interpretable memory. AutoConcept filters noisy concepts, activates query-relevant positive constraints with an auxiliary negative penalty, and combines base retrieval scores with metadata-based concept-candidate alignment through inference-time calibration. On FashionIQ, AutoConcept yields significant early-rank improvements over WeiMoCIR and consistent plug-in gains on LinCIR candidate pools. Metadata-aware controls show that structured concept memory adds signal beyond direct query-text and extracted-attribute matching, while a query-only variant further supports the effectiveness of concept-level reranking. A supplementary real-human concept-label study indicates that the same memory interface can consume participant-provided evidence. These results position AutoConcept as an interpretable concept-memory reranker for product-style CIR galleries with available metadata.