Papers

This paper develops a dynamic production-network model in which monetary non-neutrality emerges under fully flexible prices. Firms finance intermediate-input purchases from current nominal balances, and intermediate goods arrive with heterogeneous lead times across suppliers. A monetary shock then has two distinct effects. The first is miscoordination: because production uses dated input bundles assembled under past nominal conditions, the shock disturbs the composition of usable inputs (within and across firms) and thereby generates a deadweight loss. The second is reallocation: because the incidence of the shock is tilted toward smaller firms, which are disproportionately downstream, the shock redistributes resources along the supply chain. More specifically, positive shocks push resources downstream, negative shocks pull them upstream. This means that under a negative shock, both the miscoordination and the reallocation effect reduce downstream output and therefore GDP. Under a positive shock, reallocation raises GDP while miscoordination reduces it. The money-output relation is therefore sign-asymmetric: negative shocks generate sharp contractions, while positive shocks generate at most mild expansions, and sometimes none. Computational experiments on a reconstructed US production network generate output declines after a monetary contraction that are about three times as large as the increases after a monetary expansion.

Bandwidth extension, the task of reconstructing the high-frequency components of an audio signal from its low-passed counterpart, is a long-standing problem in audio processing. In this work, we extend recent advances in neural architectures by framing bandwidth extension as an audio token prediction problem. Specifically, we train a transformer-based language model on the discrete representations produced by a disentangled neural audio codec, where the disentanglement is guided by a Harmonic-Percussive decomposition of the input signals, highlighting spectral structures particularly relevant for bandwidth extension. Our approach introduces a novel codec design that explicitly accounts for the downstream token prediction task, enabling a more effective coupling between codec structure and transformer modeling. This joint design yields high-quality reconstructions of the original signal, as measured by both objective metrics and subjective evaluations. These results highlight the importance of aligning codec disentanglement and representation learning with the generative modeling stage, and demonstrate the potential of global, representation-aware design for advancing bandwidth extension.

Multi-user voice agents must track who said what across dialogue sessions. Text LLMs are attractive backbones for such agents, but transcripts alone do not expose acoustic speaker identity, leaving the model without a persistent reference for linking information to speakers across sessions. We address this gap by introducing Speaker Handles, soft-token representations that expose acoustic speaker identity to a frozen text LLM for cross-session speaker-dependent reasoning. A three-stage curriculum trains a lightweight projector, with fewer than 0.1% of the backbone's parameters, to map speaker embeddings into these handles. Establishing whether the resulting handles truly support cross-session speaker-dependent reasoning is challenging with existing benchmarks because textual cues can partially reveal fact ownership. We therefore present SpeakerBind, a controlled shared-agent benchmark in which overlapping facts across users require correct cross-session speaker attribution. Speaker Handles achieve 97.40-98.36% accuracy on VoxCeleb1 and 70.40% on SpeakerBind, close to the 71.88% topline. These results show that the proposed Speaker Handles provide an efficient way to integrate acoustic speaker identity into frozen text LLMs for speaker-content reasoning.

Memory-corruption errors remain a leading cause of high-impact vulnerabilities in C and C++ software. Deterministic detection, however, remains difficult to deploy: compiler-based sanitizers require source code and control of the build pipeline, hardware-assisted schemes depend on specific platforms, and dynamic binary translation can impose order-of-magnitude slowdowns. This paper presents MallocSan, a heap sanitizer for native, potentially closed-source x86-64 Linux applications that requires no source access, recompilation, or specialized hardware. MallocSan interposes on memory allocation through LD_PRELOAD and embeds an object identifier in the unused high bits of each protected pointer. Dereferencing the resulting noncanonical pointer faults at the offending instruction, which MallocSan decodes and patches at runtime so that subsequent executions perform per-object bounds checks entirely in userspace. Sites that cannot be patched fall back to in-handler emulation or single-stepping, while an optional profile-guided pass rewrites frequently executed residual sites offline. MallocSan also extends identity-based checking to vector gather/scatter instructions and supports policy-scoped coverage. Across seven SPEC CPU 2017 benchmarks, MallocSan outperforms Valgrind Memcheck on five, with a geometric-mean execution-time factor of 4.82x relative to native execution, compared with 18.55x for Memcheck, while preserving substantial parallel scaling on both evaluated multithreaded workloads: 644.nab_s and pigz. On the in-scope Juliet tests, MallocSan detects all seeded violations with no false reports on the good executions. It also detects heap-buffer errors in real-world applications, including a known one-byte overread in LibTIFF's tiffcrop utility.

We present a novel algorithm for calculating the preimage of an affine space through a product ${J}={J}_{T-1}\cdots{J}_0$ of matrices ${J}_t$ of special form: finding the largest input space $\mathbf{X}$ such that $\mathbf{x}\in\mathbf{X}$ implies ${J}\mathbf{x}\in \mathbf{Y}$, where $\mathbf{Y}$ is a given output affine space. These special matrices arise in AD, where the Jacobians $J$ describing the linearized computation have precisely this structure: the product of a series of linearized primitive numeric operations. This allows us to use the new algorithm to formulate Null-A mode preimage AD, which finds the affine preimage through the Jacobian or Jacobian transpose of a numeric computation. This is a generalization of the inverse AD problem of solving ${J}\acute{\mathbf{x}}^{\ast}=\acute{\mathbf{y}}^{\ast}$ or ${{J}}^{T}\grave{\mathbf{y}}^{\ast}=\grave{\mathbf{x}}^{\ast}$. The key is to represent affine spaces in a fashion which lends itself to efficient preimage calculation, in a compositional and quasi-local fashion, through a succession of matrices ${J}_t$. Unlike previous methods, Null-A preimage mode AD allows the ${J}_t$ matrices to be non-square, corresponding to a computer program whose number of active variables swells and shrinks during the computation. When ${J}$ is square and the initial affine space is a single point, this finds the conventional inverse. But in the more general case, having the entire affine space provides freedom which can be leveraged in a problem-specific manner. We apply the method to small problems on-CPU where the $J_t$ are linearized scalar unary or binary numeric functions; and to larger problems on-GPU where the $J_t$ are linearized aggregate array operations like convolution and attention.

Robotic manipulation integrates vision, touch, and language, whose importance shifts across stages: vision guides reaching, while touch, through its evolution over time, decides grasping, alignment, and contact. Yet existing multi-modal manipulation policies typically use fixed temporal contexts and fusion strategies, despite shifts in what each modality contributes across different skills. We study how vision and touch should be combined at the level of primitive skills, asking what each skill needs from each sensor, and propose a skill-conditioned representation in which the queried skill conditions fusion over modality-specific short-term observation tokens while attending to a sparse event memory that retains terminal observations from the last $K$ executed skills. Evaluated by skill progress estimation on three contact-rich tasks, it reduces slip-detection delay by 87% against fine-tuned SOTA progress models, twist-completion delay by 67.5% against a vision-only ablation, and progress error on a blind search task by 92% through sparse event memory. Gains concentrate exactly where completion is defined by contact or task history. More broadly, our results suggest that observation formation not only policy architecture is a central challenge in multi-modal representation. Project Website: http://what-to-attend-what-to-keep.github.io/

We present gap-lean4-port (Release v0.2.0), a machine-checked formalization of foundational algorithms in computational discrete algebra and permutation group theory within the Lean 4 interactive theorem prover and Mathlib4. While modern proof assistants feature extensive abstract algebraic hierarchies, constructive and operational permutation group algorithms, such as Charles Sims' 1970 Schreier-Sims algorithm, transversal tree lookups, and backtrack ordered partition refinement, have remained largely unformalized in dependent type theory. Here, we formalize the operational algorithmic core of the Groups, Algorithms, Programming (GAP) system library across four foundational modules, proving 35 machine-checked theorems with zero unproven conjectures (sorry) and zero custom axioms under standard Lean 4 foundations (propext, Classical.choice, Quot.sound). We machine-check: (1) Schreier-Sims stabilizer chain hierarchies (StabLevel, StabChain) and the invariance of incremental transversal tree extensions (extendSchreierPoint_invariant); (2) single-level and multi-level Schreier sifting reductions (siftOneLevel, siftFull), proving that full sifting strictly fixes all base points (siftFull_fixes_all_basePoints); (3) constructive soundness and completeness of Base and Strong Generating Set (BSGS) membership testing (membershipTestKnownBase_iff_mem); (4) backtrack ordered partition cell refinement (splitCellByPred), proving mutual cell disjointness, union conservation, and exact cardinality preservation; (5) cyclotomic extension rings Z/nZ(eps_m) and machine-check GAP's exact size theorem |Z/nZ(eps_m)| = n^m; and (6) executable Bezout inverses via Extended Euclidean GCD (Nat.gcdA) over residue rings Z/nZ. The entire codebase compiles deterministically under 'lake build RequestProject' and is openly available at https://github.com/pCwOrM/gap-lean4-port.

Clinical research in psychiatry increasingly relies on large scale collection of spoken language data to identify acoustic and linguistic biomarkers. Yet evolving consent and protocol requirements can oblige investigators to remove a designated speaker from multi-speaker recordings and to verify said removal at a scale infeasible for manual review of entire corpora. We study this verification problem for role-driven dyadic clinical dialogue in psychiatry and investigate it with two parallel, symmetric pipelines: confirming that clinician speech has been removed from psychiatric interview recordings, and confirming that patient speech has been removed from the same recordings. Each pipeline redacts the raw audio for its target role and then scans the surviving output with audio-language and large-language models to identify missed deletions. We evaluate this approach on a corpus of 48 dyadic recordings drawn from psychiatry settings, testing four open-weight models in an inference-only setting: Gemma-4-12B, Gemma-4-31B, Nemotron-3-Nano, and Nemotron-3-Nano-Omni. A disjunctive OR ensemble over fourteen model-view configurations had a combined F1 of 0.478 (precision 0.330, recall 0.870), an improvement over individual model estimates driven by recall gains that point to substantial complementarity across models and context views.

Large language model (LLM) agents that reason over clinical records must track changes in a patient's state while preserving the history needed to understand them. Simply accumulating memories leaves it unclear which information still applies, whereas overwriting earlier memories can erase evidence needed to reconstruct treatment history and clinical trajectories. We introduce STAM, a state-transition-aware memory framework that records state changes as new clinical entries arrive. STAM combines semantic retrieval with typed clinical relations to identify affected memories, maintaining current information in Active and superseded or resolved information in History. At read time, a query-dependent gate selectively serves historical memory. Across four longitudinal clinical benchmarks, we evaluate STAM with downstream question answering, direct state-maintenance diagnostics, and comparisons at approximately matched context lengths.

Conventional 3D Gaussian Splatting (3DGS) requires depth sorting and ordered alpha blending to correctly render overlapping Gaussian primitives. Stochastic transparency enables sorting-free rendering by replacing fractional alpha contributions with discrete stochastic visibility samples, but produces substantial spatial and temporal noise at low sample counts. We refer to this conversion from continuous Gaussian splats to discrete visibility samples as Gaussian Stippling. Based on this, we present an efficient order-independent rendering and reconstruction framework that operates directly on unmodified 3DGS assets. Our method adaptively integrates primitive-based and fragment-based stippling, leveraging their complementary strengths across different rendering regimes to significantly improve rendering throughput. To recover high-quality images from sparse stochastic samples, we further introduce a lightweight Gaussian-aware spatiotemporal reconstruction network. By exploiting the Gaussian attributes retained by each stipple, the network aggregates structured stochastic clues across both space and time, effectively suppressing stippling noise. Experiments show that our hybrid Gaussian stippling method, coupled with a spatiotemporal reconstruction network trained on diverse scenes, generalizes to unseen scenes and enables interactive, temporally stable, and visually plausible rendering on mobile devices without retraining or preprocessing. With scene-specific training and appropriately scaled sampling and network capacity, our method further outperforms the baselines in visual quality, offering a high-fidelity configuration for quality-prioritized applications.

Judging image quality is not only ecologically relevant to everyday human tasks, but also underpins many machine vision tasks such as image generation. This paper proposes a framework to understand the inherent perceptual space underlying image quality judgment in humans. We propose a multi-dimensional observer model that represents images as distributions in a latent perceptual space and that models human judgment as comparing noisy samples. Being constrained by neural representations in the primate ventral stream and fit to large-scale behavioral data, the model enables analysis of perceptual structure while matching the predictive power of existing metrics. Using this model, we find that the perceptual spaces needed to account for image quality judgment in humans are extremely low-dimensional compared to the image space even when considering its sparsity. The exact structure of the space (e.g., dimensionalities, information encoded) varies between low-level and high-level quality judgments, suggesting that, despite a shared retinal encoding in the beginning, humans selectively construct task-dependent perceptual spaces in visual decision making.

Large Language Models (LLMs) and more broadly Artificial Intelligence (AI) systems are often described and understood in human-like terms, a phenomenon known as anthropomorphism. This paper provides a synthesis of recent literature on anthropomorphism in AI, covering theoretical frameworks, the role of language in framing AI as human-like, the various risks of anthropomorphizing machines, and strategies to mitigate these issues. After examining why we tend to anthropomorphize AI systems and whether we are right to do so, we highlight the impact of linguistic framing on anthropomorphism. Then, we introduce a conceptual taxonomy of risks associated with AI anthropomorphism. This taxonomy groups twenty-one concerns within five analytical categories: epistemic, affective, human agency, normative, and societal and institutional risks. Finally, we relate these concerns to proposed interventions in design, communication, education, and governance. We argue that a better understanding of AI systems requires concepts and theories grounded in their organization and demonstrated capacities. The linguistic shaping of anthropomorphic perceptions should form part of this scientific effort, since our descriptions influence both how these systems are understood and the roles we allow them to occupy in society.

Unified multimodal models (UMMs) train image understanding and autoregressive image generation on shared parameters, and the two objectives are known to interfere. Existing diagnoses and remedies operate at the resolution of layers or experts, measuring conflict per layer and resolving it by separating parameters. We argue that this resolution hides an orthogonal axis. Generation in a UMM is next-token prediction over a raster sequence of visual tokens whose roles vary systematically with position, so how strongly a generation gradient interferes with understanding should depend on where in the sequence it originates. We introduce a position-resolved interference map that attributes understanding-generation gradient conflict to visual-token positions within every layer, computed from a single backward pass at $1.2\times$ the cost of a standard backward pass. On Show-o and Janus-Pro, position explains a large share of conflict variance after controlling for depth (partial $\eta^2=0.31$ vs. $0.35$ for layer on Show-o; $0.15$ vs. $0.30$ on Janus-Pro): the first quarter of the sequence has a mean gradient cosine of $-0.18$ against understanding, the last quarter $-0.02$. The dependence survives per-position gradient-norm normalization, retaining $80%$ of its effect size, and conflict strength tracks semantic content (Spearman $\rho=0.64$). Building on the map, we propose position-aware modulation (PAM), which removes the anti-aligned component of generation gradients only at high-conflict positions without changing the architecture. Under a matched trainable-parameter budget, PAM improves over layer-wise separation by $+21$ MME and $+2.4$ GenEval points on Show-o while matching it on POPE and overall FID; a random-position control recovers about $31%$ of the gain. Position-based and layer-based separation are complementary degrees of freedom and can be combined.

Retrosynthesis enables the discovery of viable synthetic routes to target molecules. It plays a central role in modern drug discovery and materials design. Retrosynthesis involves molecular graph transformations that can change both connectivity and graph size. These transformations may introduce reactant components absent from the target while revising the product-derived structure. To model these transformations, we propose RetroGEF, a flow-based generative model for single-step retrosynthesis. Starting from the target molecule, it constructs possible reactants by adding atoms and changing bonds in the molecular graph. RetroGEF models molecular transformations and changes in graph size within the same generative process, rather than relying on a fixed-size graph canvas. It learns this process directly from product–reactant pairs without requiring a prescribed edit order. Experiments on representative retrosynthesis benchmarks demonstrate that RetroGEF achieves state-of-the-art performance.

Indirect manipulation of deep-seated deformable anatomy inaccessible to the robot is challenging in robot-assisted minimally invasive surgery (RAMIS) because intervening tissues spatially filter deformation transmission. Passive observations can be ambiguous because the Decoupled and Blocked modes may produce similar motion responses. We propose CADeT, a causal-aware deformation transmission framework that integrates structural causal model (SCM) with active sensing to infer a latent transmission mode and estimate a state-dependent adhesion Jacobian online. During normal manipulation, control actions update the mode belief; when ambiguity persists, an additional probing action is selected to improve mode distinguishability. The mode belief and learned Jacobian are incorporated into a belief-aware model predictive controller for indirect target-shape control. Validation in simulation and on the da Vinci research kit (dVRK), using phantom and ex vivo porcine tissues, shows higher mode-identification accuracy and faster shape-error convergence than the evaluated model-free and model-based baselines. These results show that active sensing improves mode identification and indirect deformation control under the evaluated conditions.

Existing architectures for LLM-based multi-agent systems (MAS) cannot reliably and efficiently solve multi-step tasks at scale: they struggle to support large numbers of agents and concurrent tasks, tolerate failures, govern agent interactions, and accommodate the diverse planning and execution patterns different tasks require. We present PANDA, a decentralized architecture that connects a large collective of heterogeneous, independently administered agents, letting them discover each other's capabilities and self-organize into small specialized teams per task. PANDA scales by decoupling collective communication from team communication, allowing agents to participate in multiple teams simultaneously, load-balancing tasks across the collective, and scheduling concurrent work within each agent. PANDA further separates the underlying architecture from the orchestration strategy, supporting three planning and execution patterns (star, chain, and mesh) that can be selected according to the structure and requirements of each task. PANDA detects infrastructure and orchestration failures and recovers affected tasks by dynamically replanning around failed components. Finally, to provide governance without a centralized service that would limit scalability, PANDA uses a web-of-trust model to constrain agent interactions to established trust relationships. We evaluate PANDA on the HotPotQA benchmark, demonstrating that it scales to thousands of agents, assembles teams in milliseconds, matches state-of-the-art accuracy at up to 8x the efficiency, and sustains 100% task completion under faults where existing systems fail.

Most clinical benchmarks evaluate language models (LMs) on diagnosis using complete case descriptions. In clinical practice, however, patients present information in different ways, and clinicians must obtain relevant history and determine which examinations are needed before reaching a diagnosis. Diagnostic accuracy alone therefore cannot establish whether an agent gathered essential information or conducted an appropriate clinical assessment. Furthermore, existing benchmarks lack professional clinicians' verification. To address this gap, we introduce KlinikeBench, a benchmark of 333 clinician-authored tasks, each providing an isolated sandbox environment with a virtual patient, clinical tools, and task-specific success criteria. More than 35 clinicians contributed to case authoring and benchmark evaluation. In an empirical study, clinicians gave simulated dialogues higher mean quality ratings than reference conversations, which is adapted from real conversation. In each task, an LM has a fixed budget of turns to communicate with the patient, ask about relevant history, request examinations, follow action constraints, and record a final diagnosis. We score these steps separately as well as together. Across 31 models and seven model families, the best-performing models (e.g., GPT-6-astra and Claude Opus 5) succeed on less than 30% of tasks, even though their diagnosis accuracy reaches 90.7%. Some models benefit from talking with the patient; others diagnose well from a complete chart but perform much worse in conversation. Overall, KlinikeBench provides a testbed for evaluating the full clinical encounter and reveals a substantial gap between diagnostic accuracy and performance in interactive clinical assessment. All the code and data is available on https://zehui127.github.io/klinikebench/

This paper presents an explainable approach to pedestrian routing, in which perceived safety is estimated from street-level imagery through an explicit natural-language intermediate representation. A vision–language model caption is generated and stored before any scoring is undertaken, and the perceived-risk class is derived entirely from structured features of that stored text, so that every segment score remains inspectable by the user. Nine captioning conditions across five model families are benchmarked against a direct Contrastive Language–Image Pre-training (CLIP) image-embedding baseline under an identical downstream pipeline, and the caption-mediated representation is found to reach parity with the image embedding rather than to trail it. The approach was deployed over 654,115 images covering 36 electoral wards in two locations in Northern England (Manchester and Huddersfield). Independent field validation against 3,669 locally collected ratings of 494 images across 70 participant sessions established agreement that is statistically significant but modest, at $r=0.262$, against a measured noise ceiling of 0.737 imposed by disagreement between raters. A single-use confirmatory test then found that a pipeline 44% stronger on the supervised benchmark did not produce measurable improvement in the field ($r=0.250$, $p=0.84$), so the benchmark gains did not predict the deployment gains in this case. Routing behaviour varies systematically with journey length. There is negligible change below 1\,km, reaching a median increase of 12.78% in low-risk route length for a median detour of 2.73% on journeys of 3 to 6 km.

Large language models (LLMs) incur substantial storage, memory-bandwidth and energy costs, motivating compact weight representations. Existing seed-based compression methods reconstruct weights from compact pseudo-random representations but do not explicitly account for the non-uniform sensitivity of model weights. We introduce Seed-Q, a security-enhanced sensitivity-aware seed-based weight compression framework that uses lightweight Linear Feedback Shift Register (LFSR)-based weight generation with non-uniform bit allocation. Our approach assigns larger representation budgets to sensitive weights while aggressively compressing less sensitive regions. Importantly, this non-uniform allocation requires no side-information: the decoder deterministically reconstructs the bit-allocation schedule, with no rung depending on the decoded weights, eliminating the need to store per-block metadata or use calibration data while preserving the baseline coding rate. Experiments across diverse LLMs show that Seed-Q matches 4-bit perplexity of SeedLM with fewer bits, while at the same 4 bits/weight it reduces both perplexity degradation and zero-shot accuracy loss relative to SeedLM. We also show that Seed-Q simultaneously achieves high security against bit-flip attacks on model parameters, as bit corruption affects multiple reconstructed weights, greatly amplifying its impact and making it easier to detect. We further implement Seed-Q in an ASIC-based accelerator and demonstrate modest hardware overhead compared to prior seed-based approaches.

Synthetic data are most valuable where general-purpose datasets cannot provide the domain-specific priors a task requires, and where manual annotation is expensive, imprecise, or infeasible. In this article we argue that the central question for specialized vision systems is not how to generate more data, but which data to generate. We therefore discuss curated synthetic data, whose scene content, appearance variations, sensing characteristics, and annotations are deliberately designed around a given task. We examine three complementary curation paradigms. Procedural rendering offers explicit control over scene parameters and the annotations follow by construction. Physically-based simulation encodes the mechanism behind an observed effect and yields exactly aligned supervision pairs. Generative AI learns sensor-specific appearance from small real seed sets and attains plausible realism, though it remains prone to hallucination and to inaccurate annotation. These paradigms are illustrated with examples from industrial surface defect detection, restoration of degraded digitized autochrome plates, and 6DoF pose estimation from RGB and event data. Using these examples, we analyze different data regimes and training strategies that combine synthetic and real data across these paradigms. We conclude that curated synthetic data are best understood as a complement to real observations, and that hybrid pipelines combining controllable supervision with learned appearance are the most promising direction for reliable sim-to-real transfer.

Many maintenance models implicitly assume that maintenance can be performed whenever intervention is warranted. In practice, however, environmental uncertainty, such as weather and sea conditions, can make maintenance opportunities intermittent and dynamically evolving. We consider a degrading asset for which preventive maintenance may be performed before failure, but intervention is possible only when the asset is accessible. Accessibility evolves stochastically over time and therefore affects not only whether maintenance can be performed now, but also the value of waiting for future opportunities. We formulate this setting as a finite-state Markov decision process under a long-run average cost criterion and investigate the structure of the optimal maintenance policy. Under monotone degradation and cost conditions, we show that an optimal policy retains a threshold form in asset condition, but unlike a single threshold, the optimal threshold varies with the accessibility state. Thus, intervention depends jointly on the asset condition and the expected evolution of future maintenance opportunities. Through a numerical study motivated by offshore wind turbine maintenance, we examine how accessibility dynamics, degradation characteristics, and economic parameters shape the optimal thresholds and compare the optimal policy with constant-threshold and age-based maintenance policies. In a representative setting, adapting the condition threshold to accessibility reduces long-run average cost by 4.31% relative to an optimized condition-based maintenance policy. Relative to an optimized age-based policy, the optimal policy reduces long-run average cost by 33.95%. The results show that maintenance thresholds are not universal: they should adapt to the degradation and accessibility characteristics of the system, and failing to account for these conditions can lead to substantial cost increases.

Retrieval-Augmented Generation (RAG) is now the standard way to ground Large Language Models (LLMs) in external knowledge, yet the design space of retrieval pipelines is large and the trade-offs between variants are not well understood, especially on domain-specific corpora at realistic scale. In this work, we present a controlled comparison of six retrieval strategies for scientific question answering: (i) classic top-k dense retrieval, (ii) LLM-based query rephrasing, (iii) query rephrasing followed by LLM-based reranking, (iv) multi-query fusion via Reciprocal Rank Fusion (RRF), (v) an agentic tool-call pipeline in which the generator decides for itself whether to retrieve, and (vi) late-interaction retrieval with ColBERTv2. All six pipelines share the same generator (Meta-Llama/Llama-3.1-8B-Instruct), prompt, and evaluation protocol; the five single-vector pipelines additionally share SPECTER2 embeddings and a Chroma vector store; and all six retrieve from the full corpus of 463,971 arXiv papers dated 2024-2025. To support reproducible, large-scale evaluation, we also release a synthetic question dataset of 19,484 problem-statement and methodology questions generated by Llama-3.1-8B-Instruct from a random sample of 10,000 papers across academic domains (query generation succeeded for 9,742 of them), and every strategy is evaluated on this same query set. We describe the architecture and implementation of each pipeline, release the code and the synthetic question dataset, and evaluate each strategy with an LLM-as-a-judge protocol along multiple quality dimensions, together with direct gold-paper retrieval metrics. The result is an open testbed for studying the cost and quality trade-offs of RAG design choices on a research-literature corpus, and a basis for future work on faithfulness, retrieval robustness, and agentic retrieval.

Behavior cloning provides an offline route to autonomous-driving policy learning, but mean-squared-error regression is poorly matched to demonstrations in which one observation admits several valid actions. Diffusion policies can represent conditional multimodal action distributions, yet their closed-loop performance may be unstable when visual features and control are learned from limited data. This paper presents Diffusion-2BC, which combines a diffusion denoising objective with an auxiliary deterministic behavior-cloning loss over a shared visual encoder. The auxiliary branch is used only during training; inference remains diffusion-based. The proposed method is evaluated in the controlled Claw environment and in bird's-eye-view CARLA navigation, including route-conditioned driving, route-free navigation through multiple intersections, and cross-map evaluation from Town01 to Town02. In the Claw task, Diffusion-2BC reduced the mean mask-distance error by approximately 10% relative to a diffusion-based behavior-cloning baseline and by 85% relative to standard deterministic behavior cloning. In route-free CARLA, Diffusion-2BC traveled substantially farther before termination under the evaluation protocol than both baselines in Town01 and Town02. Additional qualitative rollouts revealed distinct route choices, showing the multimodal behavior of the proposed diffusion-based agent. The results indicate that an auxiliary regression signal can improve the closed-loop reliability of diffusion behavior cloning while preserving multimodal prediction in the controlled benchmark.

Hyperdimensional computing and vector symbolic architectures often represent quantized scalar levels by dense binary codebooks whose level-to-level similarity is intended to follow a prescribed function of scalar separation. At finite dimensionality, randomized scalar codebook constructions deviate from this target because of sampling noise, random-start imbalance, update-count fluctuations, component dependence, and finite-capacity effects. We develop a transition-based derandomization framework for dense binary scalar codebooks across two target-similarity families, with similarity decaying exponentially or linearly with level separation. The framework separates the target similarity law, the derandomization variant, and the concrete generator construction, making explicit how initialization, selection, update, and capacity-handling mechanisms shape the induced similarity profile. We formalize derandomization variants that separately constrain initial Hamming weight, update-count variability, and update balance, thereby controlling distinct sources of finite-dimensional error. For each family and variant, we derive the induced mean similarity, identify realization-wise and mean target-matching regimes, and derive exact finite-dimensional expressions for bias, variance, and root-mean-square error. Simulations across dimensions, quantization ranges, reference scalar levels, and generator constructions validate the theory and show how each constraint removes or reduces a specific source of similarity mismatch. The results provide practical guidance for choosing scalar codebook generators that more closely match a desired similarity law under finite-dimensional and hardware-relevant constraints.

Agent benchmarks test agents in worlds that stay still. Deployed agents work in worlds that other people also change. Someone texts the agent to send the money elsewhere or an order confirmation asks it to reply with a door code. We present BACKDROP, which asks how much of an agent's capability in a clean world survives in such a world. BACKDROP takes a task along with the agents execution environment, and plants four everyday hazards in its world, one at a time and all together. The instruction and the correct end state stay the same. Each hazard asks one question. Authority: does a message from another person override the user? Injection: does text planted in a record redirect the agent? Boundary: does a request pull it into an app it was not given? Fault: after a write fails without saying whether it landed, does the agent check before it retries? Across 3,678 variants and 16 models, , the average pass rate falls from 69.5% to 31.3% once all four hazards are present; the strongest models fall furthest (Claude Fable 5.1 from 96.6% to 56.0%). Agents have learned to resist injected text but often follow other unauthorized requests of other people. With all four hazards present, and counting only runs where the planted text reached the agent, agents followed another person's message in 46.4% of runs and injected text in 20.3%. The gap is consistent throughout all 16 models. BACKDROP formalizes these gaps and shows how an agent's score in a task's world is a ceiling on real-world performance.

This work proposes the L1 Adaptive Model Predictive Path Integral (L1-MPPI). It cascades L1 adaptive control with the Model Predictive Path Integral (MPPI) to improve tracking of high-speed UAV trajectories. Thanks to the L1augmentation, the tracking remains accurate even under model uncertainties and external disturbances, such as an additional payload or a mismatch in the modeled aerodynamic drag. In contrast to existing MPPI approaches for UAV control that do not explicitly model aerodynamic effects, varying payloads, and typically neglect the dynamics of low-level motor controllers, our L1-MPPI approach enhances the dynamic model used in the MPPI by incorporating the low-level flight controller and motor dynamics, as well as an iterative mixing scheme that reflects the approach of the low-level controller. The proposed method demonstrates improved tracking performance in both simulation and the real world, even when the UAV is subjected to an unknown payload. In flight with 35% mass increase, our approach lowers the RMSE by 58.61% with respect to plain MPPI. Compared to the same MPPI using an online mass estimator in place of the L1 augmentation, the RMSE is lower by 38.59%. During the real-world experiments the UAV reaches speeds up to 13.50 m/s and accelerations up to 2.5 g.

Text-conditioned full-body human-object interaction (HOI) generation requires synthesizing human motion and object trajectories that match the input text while remaining precisely coordinated over time. Most methods represent the human and object as separate trajectories and predict the global human-object couplings. Learning this complex, dynamically changing relationship implicitly, however, often yields object drift, missed contact, and penetration. We introduce PAMI, a Part-Anchored Motion framework for Interaction generation. Inspired by the classic Hough Transform, our key idea is to localize object motion by letting body-part anchors vote for it: we express object motion relative to multiple body-part anchors and use PamiVAE to learn an interaction latent space, decoding frame-wise weights that aggregate these part-specific votes. Building on this representation, PAMI generates interactions in a coarse-to-fine hierarchy. PamiGen first generates a coarse human-object interaction from text in this structured latent space, and PamiRefiner then recursively resolves fine-grained contact geometry using a hybrid surface-sensing representation, combining long-range probes that capture overall body-part influence with short-range sensors that resolve detailed contacts near the object surface. Experiments on InterAct show that PAMI generates more faithful interactions and more accurate human-relative object motion than previous methods, achieving 14.5% higher contact recall than the previous state of the art. Extensive ablations validate the contributions of both the part-anchored voting representation and hybrid surface-sensing refinement.

Unified multimodal models (UMMs) are increasingly designed around gradient conflict between understanding and generation objectives. The premise that reducing these metrics improves the downstream understanding-generation trade-off has never been tested directly. We audit it in a controlled testbed, GRIDUMM, which mirrors key structural ingredients of UMM training while making the ground-truth trade-off exactly computable. Across 63 configurations and 372 measured checkpoints, no directional conflict metric reaches an absolute Spearman correlation of 0.3 with a confidence interval excluding zero for conflict measured during training against the eventual trade-off. A dose-response intervention that monotonically suppresses conflict leaves the trade-off flat, separating correlation from causation. The norm ratio is a generation-failure detector and becomes null among configurations that master generation. Functional interference measures outperform directional conflict metrics, while training loss tracks the trade-off strongly. Our results do not show that conflict is useless; they show that its validity as a diagnostic target must be established, not assumed, and we release the audit protocol as a reusable standard.

Autonomous driving planners are typically evaluated using aggregate metrics such as driving score, destination rate, and collision rate, which do not explicitly measure compliance with traffic rules. As a result, planners can achieve high benchmark scores while still exhibiting unsafe or illegal behaviors, limiting their applicability to real-world deployment. To address this gap, we introduce TrafficSignBench, a large-scale, traffic sign-centric benchmark for systematic and interpretable evaluation of traffic-rule compliance in autonomous driving. Our framework combines real-map-based simulation for realistic road layouts with rule-targeted procedural scenario generation for scalable and balanced coverage of underrepresented rules. We implement traffic rules corresponding to 34 traffic signs, each equipped with an automatic rule checker for detecting violations during closed-loop execution. This design yields 29,000 diverse road scenes and 29 distinct testing scenario types, enabling controlled evaluation of rule-specific planner behavior. We construct 5,800 testing scenes and demonstrate that current autonomous driving planners can exhibit poor traffic-rule compliance despite strong performance on standard evaluation metrics. To address this limitation, we transform existing planners into rule-compliant trajectory experts via explicit traffic-sign constraints, enabling scalable generation of high-quality oracle trajectories for fine-tuning.

In this paper, we present a visual-inertial-wheel odometry (VIWO) framework with online calibration for four-wheel independently steered and driven (4WIS4WID) mobile robots. We derive a 2D odometry model directly from the four driving velocities and steering angles, using both the longitudinal rolling constraints and the lateral no-slip constraints of all wheels. A preintegration model and analytical Jacobians are developed for efficient filtering and calibration. An observability analysis of the linearized VIWO system shows that a drive-only model makes all steering offsets unobservable, whereas the proposed redundant model restores their observability. The analysis also identifies four standard VINS unobservable directions and three additional directions associated with the arbitrary placement of the odometry reference frame. Furthermore, we characterize several degenerate motions, including zero yaw rate, constant steering, and a non-rolling wheel, and derive the corresponding excitation conditions for the thirteen wheel intrinsics that remain after fixing the odometry frame reference. The performance of the proposed system has been demonstrated in both simulation and real-world experiments on a 4WIS4WID mobile robot.