Papers

Graph-based retrieval-augmented generation (RAG) can help answer questions that require information from many documents. However, building a graph often requires many language-model calls during ingestion. It is therefore important to ask whether its quality gains justify the additional cost. We present EffiRAG, a graph-based RAG system designed to reduce this cost. It uses the graph to locate relevant passages and generates answers from the original text. This design preserves source information while keeping graph construction and query processing lightweight. We evaluate EffiRAG on UltraDomain, which contains 120 open-ended questions from four domains. Compared with LightRAG-hybrid, EffiRAG produces the preferred answer on 93 questions. LightRAG is preferred on 7, and the remaining 20 are splits. EffiRAG also reduces total system cost by 57 percent, from USD 0.952 to USD 0.408. The cost includes language-model calls during ingestion and querying. The advantage remains as the corpus grows. At 10 and 20 documents per domain, EffiRAG uses a lightweight, non-LLM filter to skip low-salience chunks. It remains preferred over LightRAG-hybrid. It costs 4.2 times and 4.5 times less, respectively. The comparisons identify different quality-cost trade-offs. Graph-based RAG systems should therefore be evaluated by both answer quality and cost. The results favor graph structure that locates and preserves source evidence.

In this paper, we develop a systematic construction framework of hyper-derivative algebraic geometry codes via local expansions, extending hyper-derivative Reed-Solomon codes from the rational function field to general algebraic function fields. Using the residue theorem, we determine their Euclidean duals and illustrate that the duals naturally reverse. We further give criteria for reverse self orthogonality and reverse self duality in terms of two classes of bilinear forms. Finally, we provide an asymptotic bound on the rate and relative distance via function field towers.

Community-based fact-checking is promising in countering misinformation, yet its scalability is constrained by slow rating accumulation. To address this challenge, platforms such as X implement platform-directed rating mechanisms, specifically through “Needs Your Help” algorithmic prompts, to target unresolved notes. Using a dataset of over 220 million rating contributions – including 1.9 million platform-directed ratings – on X, we examine contributors' response to note prompts, notes' resolution, and raters' spillovers. We found (i) at note level, population-sampled ratings concentrate on recent notes with certain helpfulness and high disagreement. Once sampled, population-sampled rating was associated with faster and more transitions to resolved statuses. (ii) At rater level, following raters' first observed population-sampled rating, raters exhibit significant yet modest increases in daily ratings, rating pace and tag usage, while other behaviors show no change. These highlight the promise of algorithmic nudges to guide volunteer attention toward contested content, accelerating consensus while sustaining rater engagement.

Research agents working in separate sessions need to know what others have tried and which results they can build on. Agora stores their contributions as an append-only directed acyclic graph (DAG) in Git. Each commit records a result, insight, hypothesis, verification, or report and links it to prior work. Searchable views show leading results, neglected branches, and verification status; diversity-aware recommendations suggest experiments beyond the current leaders. We report a run of nearly 12 days in which 13 language-model workers, with no assigned tasks or central planner, used Agora to solve a weight-transfer problem. Given 141 pretrained donor models and a frozen 119.6M-parameter attention–SSM hybrid whose dimensions match no donor, the workers had to initialize the target without training data or gradient updates. They published 1,703 contributions and reduced the development evaluator score from 3.39 to 1.899 bits per byte, closing 62% of the gap to a trained GPT-2 124M. The best method compresses donor next-token statistics into the target's embedding and output head, then adds short-range context through sparse edits to attention, feed-forward, and state-space blocks. Its 145-commit ancestry spans 15 accounts. Participants also posted 165 verifications of 95 targets, each by an account other than the target's author, with no reported failures. The run documents how agents reused and verified shared work. Measuring the effect on discovery per unit of compute requires a matched comparison.

Global localization with scanning millimeter-wave radar remains challenging because place-recognition descriptors often discard spatial structure needed for accurate pose retrieval. We present ReRadar, a radar global localization pipeline that extracts rotation-equivariant intermediate features using steerable convolutional neural networks, forms rotation-invariant descriptors through group pooling and NetVLAD aggregation, and combines descriptor retrieval with landmark-based matching to estimate the robot's three-degree-of-freedom (3-DoF) pose. Across fixed database-query evaluations, ReRadar with target-dataset adaptation achieves 99.37% Recall@1 on OORD Bellmouth, 91.44% Recall@1 with 80.99% F1_max on Mulran DCC01, and 99.38% Recall@1 on falling-snow Boreas sequence. Without target-dataset data, the cross-dataset model reaches 98.07% Recall@1 on OORD, performing comparably to the evaluated state-of-the-art methods.

Vehicular federated learning (VFL) enables privacy-preserving collaborative model training for intelligent transportation systems, where communication resource allocation and gradient sparsification techniques have been explored to reduce communication overhead. However, vehicle mobility leads to rapidly varying channel conditions and transmission capacity, rendering predetermined resource allocation and sparsification decisions ineffective. In this paper, we propose FedPGT, a progressive gradient transmission scheme for VFL over time-varying channels, where vehicles progressively transmit high-magnitude gradient entries in response to instantaneous channel conditions. We establish a convergence bound that characterizes the impact of transmitted gradient entries and reveals diminishing-return behavior governed by a power-law decay. Motivated by this result, we formulate a stochastic optimization problem for online decision-making, where the main challenge lies in a cumulatively coupled, non-separable objective. To handle this challenge, we introduce per-slot surrogate transmission variables to decouple the long-term dependence across time slots and convert the original objective into an additive per-slot optimization problem, enabling a Lyapunov drift-plus-penalty approach for online scheduling. We further develop a low-complexity resource allocation algorithm for efficient online implementation. Experimental results demonstrate that the proposed scheme achieves a 3.65% accuracy improvement on the CIFAR-10 image classification task and a 12.66% reduction in average displacement error on the Argoverse trajectory prediction task compared with state-of-the-art baselines, demonstrating its applicability to diverse learning tasks under highly dynamic vehicular environments.

Detection-free methods for image-to-point cloud registration are prone to erroneous correspondences caused by domain and modality discrepancies, limited sensitivity of feature extractors, and the presence of non-overlapping regions. The Masked Autoencoder (MAE) has shown strong performance in visual representation for images and point clouds. It may be helpful to apply this approach to image-to-point cloud registration, a task that requires unified feature extraction and accurate cross-modal correspondences. Standard MAE's random masking may overlook key regions due to limited camera views, reducing registration effectiveness. To address this, we propose the Intermodal Dual-MAE Framework (ID-MAE) with a Similarity-based RL Masking Strategy (SRLM), which adaptively masks informative positions by leveraging cross-modal similarity and reinforcement learning, thus narrowing the modality gap. Our method enhances cross-modal representation learning by enforcing representation consistency during feature extraction, thereby enabling more reliable 2D-3D correspondence estimation. Experiments on RGB-D Scenes v2 and 7-Scenes benchmarks show that our method achieves state-of-the-art performance in image-to-point cloud registration.

Fine-tuning a Vision-Language-Action (VLA) model for a new deployment environment is expensive, yet most methods apply uniform-capacity adapters to every network region as if every region requires equal adjustment. This paper tests that assumption on five architecturally diverse VLAs (OpenVLA-OFT, $\pi_0$, SmolVLA, DTP, Octo; 93M-7B parameters). Measuring per-region adaptation cost as normalized parameter displacement under region-isolated fine-tuning reveals an adaptation spectrum in which appearance shifts concentrate cost in the vision encoder, instruction shifts in the language backbone, and novel-object shifts in the vision encoder together with the action head, across all five architectures. To exploit this structure, we introduce a pipeline that observes, diagnoses, allocates, and adapts. From ten unlabeled target observations and without fine-tuning, the diagnostic estimates per-region cost by combining reference-free gradient and Monte Carlo Dropout signals with a Centered Kernel Alignment score against a cached source reference; the allocator converts the estimates into variable-rank LoRA adapters under a parameter budget and freezes well-calibrated regions; and standard LoRA fine-tuning trains the resulting adapters. The diagnostic ranks regions within each deployment at a median Spearman of 0.91, and the allocation matches or exceeds uniform LoRA at every budget we tested on LIBERO and CALVIN. On a physical xArm-7, the pipeline matches full fine-tuning under an instruction-wording shift with 0.04% of its trainable parameters, and on five held-out scenes evaluated without retraining it leads every baseline, with 11-23 successes of 30 rollouts against 8-18 for the strongest parameter-efficient baseline at equal or larger budgets and 2-11 for full fine-tuning. These results suggest that adaptation cost in VLAs is structured enough to measure before fine-tuning begins.

Integrated sensing and communication (ISAC) is a cornerstone of sixth-generation (6G) networks, yet conventional fixed-antenna systems lack the spatial adaptability to cope with dynamic users and targets. The emerging pinching antenna (PA) offers a flexible, low-cost solution by dynamically reconfiguring radiation points along waveguides, introducing large-scale spatial degrees of freedom. This article develops a unified architectural perspective for PA-enabled ISAC. We first discuss the unique advantages of PAs over existing flexible solutions, and then propose a PA-enabled ISAC framework that accommodates both uplink and downlink communication while being compatible with passive and active sensing targets. Within this framework, we identify representative application scenarios, discuss major design challenges, and highlight critical enabling techniques. A numerical case study demonstrates how PA reconfigurability affects the communication-sensing rate trade-off. We also outline open issues to guide further PA-ISAC research for future 6G networks.

In this paper we tackle the problem of aligning LiDAR point clouds also known as the point cloud registration problem. We propose a new algorithm, PESTO, that exploits tetrahedra as "universal features" for LiDAR data, i.e., features that are agnostic to the environment where the LiDAR sensors are deployed. We show empirically that PESTO is competitive with existing solutions for aligning LiDAR point clouds, especially in environments with occlusions. Moreover, we establish PESTO's formal correctness by proving worst-case bounds on the alignment error.

Linear probes can decode safety-relevant concepts such as truthfulness from language-model activations, but probe accuracy may show only decodability, not that the features the probe weights causally drive model behavior. We demonstrate that this gap cannot be closed from the geometry of probe weights alone: the features geometrically aligned with probe direction need not be the ones the model uses, so causal relevance requires intervention. We introduce a feature-level diagnostic that decomposes a deployed True/False probe into sparse-autoencoder (SAE) features, ranks those features by both probe alignment and by gradient sensitivity of the model's behavior, and ablates the resulting shared, probe-only, and random feature sets under a coherence gate. On the truth probe of Buerger et al. (2024) (TTPD), applied in the instructed truth/deception setting of Long et al. (2025) for Gemma2-9B-Instruct, the two rankings overlap only weakly (about 12%, Spearman rho = 0.10), and ablation dissociates them sharply: features the probe shares with the model flip the output far more (up to 27%) than equally sized probe-only (6%) or random (1%) features at full coherence, while probe-only features instead perturb the probe's own readout. The dissociation holds across five seeds and a held-out split, and an activation-aware selection of features flips behavior nearly three times as often as the probe's geometric top features (17.6% vs. 6.1%). In this setting, therefore, the geometric projection of a probe's weight vector alone does not identify the features the model causally uses; however, combining probe information with feature activation statistics recovers substantially more behaviorally causal features, and coherence-gated SAE intervention is needed to separate them from probe readouts.

Warm-start transfer accelerates delayed generalization (grokking) on algorithmic tasks, yet how internal blocks, residual-stream depth, group non-commutativity, and continual optimization govern transferred circuits remains unclear. Across ten scale-matched batteries ($>1{,}800$ trajectories) on abelian $\mathbb{Z}_{113}$ ($L \in \{1,2,3\}$) and non-abelian $S_5$, transferring internal blocks alongside boundary carriers lifts early accuracy by $5.46$ percentage points and cuts validation confirmation latency by $616.7 \pm 129.0$ steps in 1-layer models ($p_{\rm Holm}=0.004$). In 2-layer models, full transfer compresses trigger onset $8.1\times$ ($+704.7 \pm 84.3$ integral units), whereas omitting donor embeddings incurs a $-4{,}475.6 \pm 76.8$-unit interface deficit. On ternary $S_5$ conjugation ($aba^{-1}$), two-token architectures stall in a unary conjugacy-class shortcut ($\mathrm{Cl}(aba^{-1})=\mathrm{Cl}(b)$, $34.48\% \pm 6.19\%$ peak accuracy). Combining three-token causal routing ($[a,b,a]$) with Peter–Weyl width ($d_{\rm model}=256 > \sum_\lambda d_\lambda^2 = 120$) reaches $97.97\% \pm 1.01\%$ ($80.08\% \pm 7.81\%$ at equal $427\text{k}$ parameters) with $3.2\times$ faster onset than scratch. Under continued AdamW optimization, unshielded circuits relapse by $11.85\%\text{--}80.58\%$ drawdown, and depth-$L$ stability follows a graded $(L-1)$-prefix pinning hierarchy ($75.99\% \to 31.26\% \to 0.32\% \to 0.04\%$ drawdown at $L=3$). Finally, Closed-Loop Curvature-Anchored Consolidation ($\eta_k = \eta_0(1 - A_{\rm val}(k))$ with monotonic AMSGrad second moments) holds saturated drawdown to $0.00\%\text{--}0.12\%$ and lifts pre-saturation terminal accuracy by $+1.67\text{--}5.37$ points over fixed-budget micro-stepping ($87.06\% \pm 0.94\%$ vs.\ $81.69\% \pm 0.90\%$ on $S_5$, $p_{\rm Holm}=0.002$).

Open-source video generative models ship almost exclusively as PyTorch/CUDA reference implementations. This leaves Cloud TPU pods without a production-ready inference path, despite offering large, cost-effective accelerator memory pools ideal for long-sequence spatiotemporal attention. We present vidax, an open-source JAX/Flax inference engine and zero-copy PyTorch-to-JAX weight translator for modern video generation architectures. vidax covers a diverse set of spatiotemporal models — including Diffusion Transformers, omnimodal Mixture-of-Transformers, 3D VAEs, text encoders, and native samplers — with zero PyTorch dependency in the execution path. The framework unifies 1D tensor parallelism with DeepSpeed-Ulysses sequence parallelism on a single JAX sharding mesh, integrates TPU flash-attention kernels, and implements per-layer weight offloading to support reference resolutions that exceed single-device memory. We benchmark compile times, latency, and peak memory utilization on TPU v4-8 hardware, and document real-world numerical bugs surfaced during checkpoint translation. vidax is released open-source as a baseline for JAX and TPU video generation research.

Conventional video metrics such as PSNR, SSIM, and VMAF measure visual distortion or perceptual quality, but they do not directly capture semantic preservation: whether compression retains a video's objects, actions, and temporal narrative. Existing Quality-of-Experience (QoE)-driven bitrate-selection and resource-allocation methods primarily aim to minimize rebuffering and bitrate switching while maximizing perceptual video quality, without explicitly considering semantic preservation. To address this gap, we introduce video semantic fidelity (SF), a metric that quantifies how well a compressed video preserves the semantic content of its source. An offline multimodal large language model (MLLM) generates structured descriptions of the reference and compressed versions of the video, and a separate text-only large language model (LLM) evaluates their semantic correspondence. The resulting content-dependent SF–bitrate profiles are cached and queried by the online bitrate selector without invoking MLLMs at runtime. Evaluations on three subjective QoE benchmarks show a consistent positive association between SF and mean opinion scores (MOS). A separate human semantic-rating study evaluates semantic preservation and shows that SF correlates more strongly with human judgments than conventional video metrics. We then embed these profiles into a 5G MEC-assisted video-on-demand (VoD) resource-allocation framework at the base station. When wireless resources cannot support high bitrate levels for all users, the framework uses the SF–bitrate profiles to select bitrate levels jointly across users and reduce the semantic loss caused by the required bitrate reductions. NS-3 simulations with the 5G NR module show that the proposed framework achieves higher average and worst-user SF than the evaluated baselines, with a widening advantage as the wireless resources available to each user decrease.

This work studies how refraction-induced bias on acoustic ranging affects multi-agent collaborative localization in a range of oceanographic conditions and spatial scales. While multi-agent range-aided navigation, which uses range measurements to either fixed infrastructure or other agents, is a promising solution to the challenges of large-scale underwater localization, its accuracy depends strongly on the quality of range measurements. Sound speed variability induces refraction (bending) of acoustic rays, yet, for algorithmic tractability, standard sensor fusion pipelines assume straight-line propagation. This refraction systematically biases range measurements to be longer than the straight-line assumption predicts. However, the effects of this bias on multi-agent collaborative localization on kilometer scales remains unexplored. We present a series of simulated experiments with several agents operating over kilometer scales. The simulation uses HYCOM reanalysis data to recreate realistic oceanographic conditions, ray tracing to generate refraction-informed ranges, and a centralized multi-agent factor graph estimator to quantify the resulting measurement bias on estimated trajectories. Preliminary results indicate that refraction-induced bias can induce significant degradation of estimated trajectories, particularly in regions with sharp sound-speed gradients. We also share the simulation environment to support further studies https://github.com/UMich-RobotExploration/manta-ray.

K-12 robotics and AI education remains difficult to scale, especially in rural regions lacking sustained technical mentorship. Programs like FIRST provide competition pathways and instructional opportunities, but they do not eliminate the need for local programming and robotics expertise. We introduce AI, Robotics, & Community (ARC), a hubs-based framework where colleges train undergraduate mentors and host workshops for nearby K-12 teams. Mature school programs can become secondary hubs that support additional schools, creating a self-reinforcing education loop where mentorship reach propagates geographically and can even grow super-linearly. We first evaluate ARC through a trial deployment at one university. The trial created three rural robotics teams. On five-point Likert surveys, mean increases in K-12 programming knowledge, resource access, and practice opportunities were 2.00, 2.25, and 1.25 points. Likewise, undergraduate confidence teaching technical concepts, adapting explanations, managing groups, and finding mentoring enjoyable and meaningful increased by 1.29, 1.14, 1.00, and 1.14 points. Additionally, we create a spatial Markov model of ARC's growth and simulate it using the state of Indiana as a testbed. Under moderate conditions, we find that ARC reaches 74% of Indiana's 1,925 public K-12 schools and produces 992 robotics programs after 40 years, compared with 161 projected under natural growth alone. Together, these results show ARC can create and support rural robotics programs, train undergraduate AI and robotics mentors, and potentially scale mentorship across a region.

Vine robots navigate cluttered environments by extending from their tip. Although their ability to operate in such environments has been extensively demonstrated, little work has addressed growth planning, i.e., finding optimal growth paths. Moreover, existing planners do not account for the growth pressure necessary to follow a given path, which can cause the robot to burst when it is too high. In this paper, we address the problem of finding minimum-pressure paths for vine robots growing around polytopic obstacles. We propose an efficient algorithm that is guaranteed to find globally optimal solutions in 2D and approximate solutions in 3D, with an error that vanishes as a discretization parameter approaches zero. First, we derive a growth pressure equation for vine robots of arbitrary shape, which we use to show that there always exists a minimum-pressure path that is piecewise-linear and can bend only at specific points on the obstacles. We then leverage this observation to reduce the growth-planning problem to a shortest-path problem with time-dependent weights, which we efficiently solve using a modified Dijkstra's algorithm. We demonstrate the speed and scalability of our approach through numerical simulations. We also validate our algorithm with hardware experiments and provide an open-source and high-performance implementation in the Python package, VinePlanner: https://github.com/Ahsoka/VinePlanner.

Underwater semantic segmentation is essential for marine ecosystem monitoring, yet remains challenging due to severe visual degradation. Light absorption and scattering often lead to color shifts, low contrast, and blurred boundaries, making shallow detail features unreliable. Existing underwater segmentation methods improve RGB feature aggregation or boundary prediction, but still lack an explicit mechanism to distinguish structure-related details from degradation-induced responses. To address this limitation, we propose GeoCueFormer, a lightweight framework that combines geometry-constrained frequency enhancement with prediction-cued refinement. GeoCueFormer performs stage-specific wavelet enhancement on hierarchical encoder features to complement shallow boundary details while preserving deep structural semantics. A depth-derived spatial gate constrains shallow frequency enhancement toward geometry-consistent regions, and a prediction-cued dual-stage decoder further refines ambiguous high-resolution features. GeoCueFormer obtains 82.23% and 73.04% mIoU on SUIM and DUT, respectively. Under comparable model complexity and standard benchmark settings on SUIM and DUT, it achieves SOTA performance while maintaining a favorable accuracy-complexity trade-off. These results show that distinguishing structural details from degradation-induced interference is more effective for underwater segmentation.

Large language models (LLMs) are increasingly deployed in high-stakes domains such as housing screening. While alignment techniques mitigate explicit racial bias in generated text, they often leave covert attitudinal associations in internal probability distributions untouched. Adapting the matched-guise sociolinguistic paradigm, we examine covert dialect bias in housing-related social judgments across four varieties: Standard American English (SAE), African American Vernacular English (AAVE), Nigerian Standard English (NSE), and Nigerian Pidgin (NP). AAVE reflects the racialized dialect studied in prior covert-bias evaluations, whereas NSE and NP represent Black African, postcolonial varieties absent from this literature. Using 260 meaning-matched sentence quadruples and log-probability scoring over housing-relevant adjectives, we probe ten open-weight LLMs across three contexts varying in social proximity: tenant screening, neighbor acceptance, and roommate selection. Across all ten models, AAVE and NP are consistently associated with more negative adjectives than SAE, with NP penalized most severely. Crucially, each dialect is penalized via distinct stereotype clusters rather than a generic non-standard category. NSE, which carries institutional prestige, displays a context-dependent shift: favored over SAE in formal tenant screening but increasingly penalized as social proximity grows. Our findings reveal that LLMs inherit covert dialect bias along both racial identity and prestige dimensions, echoing documented human housing discrimination and demonstrating its reach across postcolonial English varieties.

Private large language model (LLM) fine-tuning is increasingly important for organizations that need to adapt models using sensitive data, but it often exceeds the memory capacity of commodity datacenter accelerators. Apple Silicon offers a different design point through large unified memory and lower complete-system cost, while recent Apple software support enables distributed execution over RDMA-over-Thunderbolt (TB). This paper studies whether Apple Silicon can serve as a practical platform for private LLM fine-tuning. We characterize RDMA-over-TB communication on Mac Studio nodes, showing that the measured bandwidth is far below nominal TB specifications. Next, we extend Apple's implementation with multi-trunk communication, persistent worker threads, and CPU-side gradient overlap to better exploit multiple direct TB links for LLM fine-tuning workloads. Finally, on a four-node Mac Studio cluster that fine-tunes a Qwen3-9B, our optimizations improve weak-scaling throughput by up to 1.6X over the single-trunk, non-overlapped baseline and reach 936 tokens/s for sequence length 17408. We further compare Apple Silicon with an NVIDIA H100 platform to quantify the trade-off between memory capacity, throughput, and acquisition cost, showing that Apple Silicon can provide a cost-effective solution for private LLM fine-tuning.

Interactive visual interfaces have become an important means of controlling generative image models, enabling users to manipulate generation through prompts, direct manipulation, and a range of interactions. However, existing techniques are typically presented as independent systems, making it difficult to understand how they relate, compare their interaction mechanisms, or identify opportunities for new interface designs. We introduce a design space for interactive visual interfaces for generative image models derived from 51 research systems and practitioner tools. The framework decomposes each system into three complementary components: the user interface (U), the controllable model objects (Z), and the mapping function ($\phi$) that translates user interaction into model operations. This decomposition provides a common representation for analyzing heterogeneous interaction techniques across model families, revealing recurring design patterns and underexplored regions of the design space. We further present an interactive corpus explorer that support comparative analysis, and discuss usage scenarios for both educational settings and HCI/AI practitioners identifying research and design opportunities.

Mixture-of-experts (MoE) inference on consumer hardware is bounded by weight memory: a 35B-class model is 19.5GB at 4-bit, and sparsity shrinks the compute per token, not the bytes that must be held. Naive offloading to SSD does not help on its own, because layer N+1's experts must be chosen before layer N's output exists, so the reads cannot start early enough to hide behind compute. We present Edge0, a streaming MoE inference engine that closes the gap with a prerouter: a per-layer head predicts the next layer's routing one token ahead, and the prediction is consumed as the routing itself, so the staged expert set equals the routed set and nothing is dropped. An unmerged recovery LoRA, trained on the student path, pays back the quality lost to int4 quantization and routing replacement. On a single 24GB machine, Edge0 serves a 35B MoE at 20tok/s inside 3GiB of peak active memory, within a few points of its fp16 teacher on average across five public benchmarks. An 8B tier runs on the same framework, and the framework, checkpoints, and adapters are open source.

Music and dance are social practices of expression and connection, yet most HCI work in human-AI co-creation centers the solo performer. As generative music matures, we ask not only what AI can compose but what social encounters it can organize around sound. We present Encypher, a collaborative generative music system that translates collective movement qualities into text prompts conditioning real-time music generation for dance cyphers. Through five weeks of co-design with local dancers, a user study with unacquainted participants, a public museum event, and a live performance, we found that users developed shared agency, perceiving the music as a response to the room's energy. While newcomers felt uncertain, the system fostered social presence by prompting them to look to each other for cues. By treating sociality as a design concern rather than a downstream effect, we offer a framework and design implications for AI systems for collaborative, embodied expression.

Human dishonesty in group settings is highly susceptible to peer influence, particularly when incentivized. Although artificial intelligence (AI) evolves from passive tools into active collaborators, its impact on human moral behavior within groups remains underexplored. We addressed this gap through a two-phase randomized behavioral study (N=280 and N=360). We found AI agents exert substantial social influence comparable in magnitude to that of human peers. Specifically, participants reported more dishonestly when exposed to dishonest rather than honest normative cues. This effect is evident across injunctive, subjective, and descriptive social norms. Interestingly, the only significant adjacent behavioral change occurred when dishonest peer behavior first appeared, whereas further increases from one to four dishonest peers produced weaker and non-monotonic changes. Furthermore, participants rapidly converge on decision-making, showing modest increases in dishonest reporting through repeated exposure. These findings highlight the importance of managing the behaviors and normative signals communicated by AI group members.

Finding the object referred to by language in a partially observed 3D scene is a core capability for embodied agents. Existing approaches either couple object search with online exploration, which can be costly when relevant observations have already been captured, or query pre-built open-vocabulary maps and scene graphs in a static, one-shot fashion. We present Finder, an agentic closed-loop object-finding primitive for embodied grounding. Instead of treating grounding as passive retrieval from a fixed scene representation, Finder maintains a typed loop state that links query-conditioned planning, scoped evidence gathering, candidate verification, and accept/continue/abort control. When evidence is incomplete or ambiguous, the loop can redirect subsequent perception and comparison rather than simply returning the top retrieved object. On open-vocabulary embodied Object Retrieval in Habitat/HM3D and real-world RGB-D scenes, Finder improves the averaged 1m success rate by 15.75 points over strong baselines. The same primitive also transfers to sequential object grounding and embodied object-centric question answering, improving spatial and temporal localization without changing the inner grounding protocol. Project page: https://finder-vln.github.io.

Reinforcement learning with verifiable rewards (RLVR) has significantly improved the reasoning capabilities of large vision-language models (LVLMs). However, standard on-policy RLVR algorithms face a critical optimization bottleneck in preserving and reinforcing visually grounded reasoning behaviors: valuable visually-grounded reasoning trajectories are discarded after a single update, while uniform token advantage allocation prevents the model from reinforcing critical perception or reasoning steps. To bridge this gap, we propose PIVOT, a dual-level learning framework that anchors policy optimization around informative visual reasoning signals. Specifically, PIVOT introduces a self-calibrated experience replay mechanism, which selectively collects and replays visually-grounded historical experiences as stable reference anchors for policy optimization. Building upon this, we further design a vision-guided advantage allocation mechanism to allocate additional vision-aware advantages to tokens based on their local visual support and impact on downstream reasoning. Extensive experiments across diverse benchmarks demonstrate that PIVOT achieves highly competitive performance in enhancing the multimodal reasoning capabilities of LVLMs.

Parameter-efficient fine-tuning (PEFT) has recently emerged as a pivotal research direction for adapting pre-trained point cloud transformers to diverse downstream tasks. Although existing methods achieve excellent fine-tuning performance with high parameter efficiency, they ignore inference efficiency. To tackle this problem, a novel PEFT method termed position anchor tuning (PAT) is proposed in this paper. As multi-head attention (MHA) and feed-forward network (FFN) are computation-heavy blocks in pre-trained transformers, PAT decreases their computational cost through token aggregation-expansion pairs. Each pair comprises a token aggregation module (TAM) and a token expansion module (TEM). For MHA and FFN blocks, TAMs extract representative tokens from their input tokens based on position anchors in 3D space. These extracted tokens, rather than the original input tokens, are processed by the blocks, thereby reducing the number of tokens involved in computation. Then, TEMs propagate the learned representations back to the original input tokens. Since TAMs are solely responsible for capturing task-specific representations, base-sharing low-rank adaptation (BSLoRA) is further introduced to enable them to learn such representations effectively with only a small number of trainable parameters. Extensive experiments on widely used benchmarks demonstrate that PAT performs comparably to state-of-the-art methods while incurring significantly lower computational overhead and fewer trainable parameters.

This study empirically evaluates whether cost-efficient Large Language Models (LLMs) can be trusted to generate enterprise code to a written specification. Three models (Gemini Flash 3, GPT-5.4 mini and Claude Haiku 4.5) were asked to solve 992 algorithmic problems as Java Spring Boot service methods conforming to a mandated signature and data-transfer-object specification, crossing four model and agentic coding tool combinations with two prompt variants to yield eight configurations, with iteration forbidden and hardcoded answers explicitly prohibited. Eight problem statements were withheld to probe how models respond to missing input. The 7,593 resulting methods were classified by an eight-class outcome taxonomy describing what each does about producing an answer, then deployed and executed, giving 7,936 measured requests joined to that classification. Structural conformance approached ceiling, yet 38.4% of methods do not compute the value they returned and only 12.9% of returned answers were correct. Conditioning on outcome class shows that response reliability and correctness are inversely related, whereas genuinely computing methods answered least often and were correct 19.3%. Limitations include single generation runs per configuration, partial harness coverage, single-pass timing, syntactic classification, and probable corpus contamination.

Fresh-market blueberries require selective, gentle picking, which is labor-intensive and expensive. Over-the-row machine harvesters are fast but non-selective, bruising mixed-ripeness fruit and limiting yield to the processing market. Selective robotic harvesters typically target individual fruits rather than fruit clusters, which limits harvesting efficiency for small, densely clustered blueberries. This paper presents CLASP, a Cluster-Level Autonomous Selective Picking robot with a Soft Active Rolling-Band Gripper (SARB-Gripper). Two compliant bands envelop the cluster and roll against the fruit, drawing mature berries off in sequence, while closed-loop regulation of the pulling force keeps the applied load below the immature detachment threshold. A global-to-local perception pipeline pairs an eye-to-hand camera for global cluster detection and target selection with an eye-in-hand camera for local localization and cluster orientation estimation. Field measurements confirm a clear detachment-force separation between mature and immature fruit, and the SARB-Gripper reproduces a commanded pulling force to within \SI{3.7}{\percent}, enabling selective harvesting at the cluster level. In end-to-end field trials, CLASP autonomously grasped 23 of 25 presented clusters (\SI{92}{\percent}). With the component cost of approximately \$3326 per unit, CLASP offers a scalable approach to selective cluster-level harvesting for fresh-market blueberries.

How do elephant trunks generate complex postures without relying solely on fine segmental activation? We propose that part of this complexity arises from a low-dimensional geometric shortcut: dual-helicity coupling between opposite-handed oblique muscles. In a simplified soft-robotic prototype, varying only two geometric parameters generates a broad library of elephant-like postures, suggesting a dual-layer control architecture with implications for continuum robot design and biological hypotheses.