Papers

Alignment-free RGB-T salient object detection (RGB-T SOD) aims to identify salient objects from unregistered RGB and thermal image pairs without costly pre-alignment. However, spatial misalignment breaks pixel-wise correspondence and causes feature contamination during cross-modal fusion. To address this issue, we propose S2A, a semantic-to-spatial alignment framework for alignment-free RGB-T SOD. Specifically, a global-guided hierarchical fusion module (GGHF) first exploits global semantic guidance to suppress background interference and refine hierarchical intra-modal features. Subsequently, the alignment-free cross-modal channel attention module (AFCA) globally exchanges complementary semantic information through channel-wise interaction, effectively overcoming the interference caused by local spatial misalignments. Finally, a spatial deformable cross-attention module (SDCA) predicts adaptive sampling offsets to recover local cross-modal spatial correspondence. Through this semantic-to-spatial paradigm, S2A first enables reliable cross-modal semantic interaction and subsequently performs local spatial calibration, effectively reducing misalignment-induced feature contamination. Without bells and whistles, S2A achieves highly competitive performance on multiple public alignment-free RGB-T benchmarks, demonstrating its effectiveness in alleviating misalignment-induced feature contamination.

Machine fault diagnosis from vibration requires learning from scarce labelled fault recordings while meeting the computational constraints of edge devices for local inference. We introduce DualRes, a compact oscillatory state-space model that combines two complementary spectral views of vibration, capturing rapid changes and fine frequency structure. Time-aligned views are processed by selective oscillatory memory, which learns how long to retain temporal patterns. The encoder contains 39,528 parameters. We evaluate supervised learning across six bearing datasets and a gearbox benchmark, with an additional gearbox pilot. Recording-level splits and explicit accounting of labelled duration distinguish data efficiency from repeated exposure to correlated samples. On the main gearbox benchmark, DualRes achieves state-of-the-art performance among the nine evaluated methods at six of seven label budgets. With about six labelled seconds per class, it improves macro-F1 by 16.1 percentage points over the next strongest comparator. On the same benchmark, DualRes achieves a 1.44-fold recording-level speedup and a 24.8-fold reduction in checkpoint storage relative to a selective state-space baseline under matched hardware and runtime conditions. Bearing results reveal task-dependent trade-offs. These findings support oscillatory memory as a compact approach to vibration diagnosis under limited labelled exposure.

Limited expert annotation capacity is a pervasive constraint in biodiversity monitoring. Passive acoustic recorders and camera traps generate data faster than experts can analyse them. Machine learning (ML) models can process these data at scale, but their reliability depends on the quality, quantity, and coverage of labelled samples, so expert time remains a constraint. Active learning (AL) eases this bottleneck by selecting, under a fixed annotation budget, the samples expected to improve a model most, and published evidence shows it can reduce the labels needed to reach a target performance. Monitoring programmes, however, face a broader question: how should a limited expert budget be divided so that model training, validation, and the ecological estimates built on model outputs all remain reliable? Because AL selects samples non-randomly, its labels are unsuitable for validation, calibration, or threshold selection, a tension rarely acknowledged. We synthesise AL research across acoustic and image modalities and identify gaps and opportunities. Most studies evaluate query strategies on pre-labelled benchmarks with simulated annotators; deployments in real monitoring workflows are rare and concentrate on birds and cetaceans. Bats, insects, amphibians, and fish are underrepresented, and multimodal applications remain largely unexplored. Evaluation centres on headline reductions in annotation effort, often without random-sampling baselines, per-class results, or calibration analysis, and rarely accounts for the labels required for validation. We provide a tutorial treatment of the AL loop that makes these budget decisions explicit, and a roadmap towards AL methods that support label-efficient training, validation, and trustworthy downstream ecological inference.

Benchmarks for vision-language models offer their answer choices in some convention: a letter, a color name, a pixel coordinate. That convention is treated as neutral. We find it is not, and that the limits a benchmark reports can belong to the readout rather than to the model. On 200 COCO photographs, Qwen3-VL-4B picks the correct one of nine locations for a named object 68.5% of the time when the locations are given in English and 20.0% when the same locations are given as pixel coordinates. Chance is 11.1%. The cost arises when the answer options are coordinates; giving the model a coordinate in the question instead costs 3.5 points and is not significant. The gap holds on a 4x4 grid, under 8-bit rather than 4-bit quantization, and in every slice by object size, boundary distance and category. It also decides which model wins. Two models that tie under English names differ by 39 points in one coordinate system and by 54 in the other, in opposite directions. On the color task, three of the four open models capable of the task show the penalty; on photographs, two of three open models do, and so does Gemini, at 11.1 points on parseable answers (p = 1e-4). GPT-4o does not. To ask whether a model reads a coordinate at all, we attach the wrong name to each one and record which the model follows. Color options written as hue angles are followed below chance; a normalized pixel convention is followed at four times chance. This tells apart conventions a model can use from ones it cannot, though it did not predict accuracy on two untried conventions. Five models also name the same color wheel five different ways, so a fixed answer vocabulary is not neutral across models either. Five times during this work we measured a capable model as incapable because our scorer and the model disagreed about what an answer looks like. We report each case. They are the phenomenon in miniature.

Deploying large language models (LLMs) on sensitive data via Retrieval-Augmented Generation (RAG) introduces severe privacy risks. Recent studies apply Differential Privacy (DP) to LLMs with RAG for formal privacy guarantees. However, existing DP-RAG frameworks rapidly exhaust the privacy budget. Although recent efforts attempt to save the budget by narrowing the retrieval scope or sparsifying private generation, these methods themselves cumulatively consume the budget, whereas they could actually rely merely on public information or at a negligible one-time privacy cost. This mismatch fails to align budget expenditure with the model's actual reliance on private data, causing substantial waste on operations that require no private access. To address this, we propose SparsePay-RAG, adopting "only pay what you must spend" as its core principle. Using public information as a zero-privacy prior, it charges the privacy budget only for the private increment. Specifically, SparsePay-RAG narrows the retrieval scope via public topic-guided clustering, adaptively controls private access frequency without privacy cost through isotonic cross-layer trajectory fitting, and compresses per-access budget via DP contrastive decoding. Under strong privacy constraints, experiments show SparsePay-RAG achieves superior privacy-utility trade-offs over baselines.

The design of credible auctions—mechanisms where a revenue-maximizing auctioneer has no incentive to deviate from the protocol—faces a fundamental cryptographic barrier when the auctioneer controls shill bidders. While a natural approach is to use Secure Multi-Party Computation (MPC) to remove the trusted auctioneer, the impossibility of fair coin flipping of Cleve (1986) implies that monolithic MPC protocols grant the auctioneer a "free option": they can learn the auction's outcome and unilaterally abort if the revenue is unsatisfactory. Cryptographic commitments with ex-ante penalties mitigate this abort asymmetry, but no finite penalty suffices for heavy-tailed distributions. We circumvent this barrier by introducing the MPC Decomposition Principle. Rather than encrypting the entire mechanism, we use MPC strictly as an information-restriction tool. We isolate the winner determination problem into a minimal MPC gadget that computes and reveals the winner's identity but no payment information. This qualitative restriction mathematically bounds the information leaked upon an abort. By combining this gadget with sequential revelation and finite economic penalties, we design the Sequential Revelation Auction (SRA). We prove that bounding the information leakage strictly bounds the value of the free option, showing that a penalty of $k \geq \sum_{i=1}^n Rev(F_i)$ is sufficient for credibility, and tight: for equal-revenue distributions, every smaller penalty admits a profitable deviation. Using constant-round MPC, the SRA resolves an open question of Akbarpour and Li (2020) and Ferreira and Weinberg (2020) by providing a constant-round, incentive-compatible, revenue-optimal credible auction for all product distributions with vanishing revenue tails

Recent zero-shot text-to-speech (ZS-TTS) systems can reproduce a speaker's voice with high fidelity from only a few seconds of reference speech, raising concerns over unauthorized voice cloning and impersonation. Speaker identity unlearning has recently emerged as an approach to selectively suppress this capability for speakers who opt out while preserving synthesis capability for other speakers. Although existing approaches reduce speaker similarity, preventing re-identification often faces severe degradation of speech quality. Motivated by this observation, we propose GUARD, a lightweight speaker identity unlearning framework that combines a learned speaker gate with speaker-agnostic activation steering on a frozen TTS backbone. The steering vectors are optimized using group-relative reward optimization to shift outputs from forget speakers toward population-level impostor similarity while preserving intelligibility and speech naturalness. On CosyVoice2, GUARD reduces forget-speaker similarity from 0.541 to 0.103 and re-identification accuracy in a 150-speaker gallery from 73.5% to 0.5%, while preserving retain-speaker reproduction. The results demonstrate that similarity reduction alone may not fully characterize successful speaker identity unlearning and highlight re-identification as a complementary criterion for its evaluation.

DSpark-style parallel drafters have made speculative decoding highly effective, yet their draft phase remains serialized on the critical path of every round. Parallel speculative decoding (PSD) overlaps drafting with verification, yet existing methods must guess the accepted prefix and bonus token in advance: a wrong guess reverts the whole batch to serial drafting. We present DPara, a PSD framework that reuses effective parallel drafters yet guarantees backbone–verification overlap in every round, thereby eliminating this probabilistic fallback altogether. While the target verifies, DPara's diffusion backbone precomputes draft representations for every acceptance boundary with the bonus left unspecified; a lightweight autoregressive head then combines the revealed verification outcome with the matching precomputed representation to emit the next round's draft tokens almost instantly—fully parallelizing the dominant backbone forward with verification and leaving only the negligible head cost serial. Experiments on Qwen3-8B and Qwen3-14B across seven math, coding, and chat benchmarks show that DPara achieves average speedups of $3.21\times$ and $3.52\times$ over autoregressive decoding, surpassing the strongest serial and parallel speculative decoding baselines alike.

Compact vision-language models (VLMs) now power a growing share of multimodal applications. The benchmarks used to compare them, however, inherit a frontier-centric design: each model is reduced to a single accuracy number, narrowing the inter-model gap on saturated suites and pressing models into low-score bands on harder ones. We introduce PRISM-VLM, a multi-axis discriminative benchmark that scores every item along seven axes covering the recurring failure modes (task quality, behavioral robustness, and capability bottlenecks) and combines them into a single PScore, with items recycled from fifteen public benchmarks. Across compact VLMs from the past two years, PScore separates model pairs more reliably than prior single-axis benchmarks under an item-level paired bootstrap, and surfaces behavioral differences these benchmarks average away. Even models with statistically indistinguishable PScores diverge sharply along the per-axis profile, particularly on sycophancy, which is nearly orthogonal to single-prompt accuracy. We will release the full pipeline, prompts, and per-item annotations.

Automotive spinning FMCW radar provides dense, $360^\circ$ sensing and remains reliable under poor illumination and adverse weather, making it well-suited to autonomous navigation. Place recognition uses these observations to identify previously visited locations for re-localization and long-term navigation. However, heading changes appear as circular shifts in the polar radar representation, and conventional global aggregation can lose relationships among radar responses that are important for distinguishing similar places. We propose SGCA-Net, a spinning radar place recognition framework that combines rotation-robust feature extraction with Spatially Gated Correlation Aggregation (SGCA). SGCA learns spatial weights to reduce the influence of unstable and ambiguous radar regions, while aggregating pairwise correlations among local responses to preserve informative feature relationships. Experiments on the MulRan dataset show that SGCA-Net consistently outperforms SOTA methods across urban, campus, and open-road environments, while remaining robust to substantial heading variation. Evaluation on the HeRCULES dataset further demonstrates that SGCA-Net generalizes to unseen environments and radar sensors without fine-tuning.

Rely/Guarantee is a well-known verification technique for reasoning about concurrent programs. However, for some algorithms, devising suitable rely and guarantee conditions is challenging, due to the strong interference exhibited in these algorithms. The Ben-Ari concurrent garbage collector is an algorithm where the complex interactions between the components prevent the construction of compositional rely and guarantee conditions. This paper investigates an approach for verifying the Ben-Ari algorithm, which enables reasoning to be performed in a more compositional manner in cases where compositional reasoning would not otherwise be possible. This is accomplished by reasoning that a given property holds for all instances of a particular variable and then instantiating the variable to the local variable required. As well as providing a reasoning approach which is more compositional, the result is the identification of the core property required of a component, thus enabling a deeper understanding about the reasons why the algorithm works correctly. This helps to reveal the reasons why the rely/guarantee approach does not work directly for some problems.

Audio language models understand what is said far better than how it sounds. Closing this gap takes more than data. Detailed acoustic annotation is costly, labels from stronger models inherit their errors and limits, and fixed data cannot adapt as the learner improves. We therefore propose EvoAudio, a recursive self-improvement system for audio understanding. To our knowledge, it is the first to evolve the model, waveforms, questions, and difficulty in one closed loop. EvoAudio uses the current model's performance to set the focus and difficulty of the next training data. A library of audio tools then constructs questions whose answers follow from how the audio was made, providing verifiable supervision without new human annotation. Reinforcement learning updates the model, and validation decides whether it enters the next evolution round. Across 13 rounds, EvoAudio improves five models with different audio encoders and language backbones on MMSU, MMAU-Pro, and MMAR. It achieves the highest average for every backbone, raising overall performance by up to 6.3 points. The improvement unfolds over successive rounds, with each stronger model starting the next round.

AraGenre is a shared task on hierarchical, definition-guided Arabic genre classification, motivated by the limited availability of annotated data in Arabic and other low-resource languages. Systems assign each Arabic text segment both a broad communicative genre and a fine-grained specific genre. The released training and development sets contain limited, primarily synthetic and controlled examples, whereas the hidden final benchmark contains noisier naturally occurring text spanning Modern Standard Arabic, Classical Arabic, and multiple dialects. Participants received natural-language definitions for 74 previously unseen specific genres, creating a zero-shot label generalisation setting in which systems had to infer class semantics rather than memorise fixed label-feature associations. The task attracted 46 registrations and 373 submissions, with 17 teams completing the final evaluation. Thakaa ranked first with a Hierarchical Macro F1 of 0.7352, followed by HoangPhong (HP) with 0.7169 and NAMAA with 0.7013. The results show strong broad-genre recognition but a substantial gap in fine-grained classification under linguistic and domain variation.

Intent-based networking decouples desired outcomes from device-level configuration, but most systems still map intents to parameters of an algorithm selected in advance. Large language models (LLMs) create an opportunity to automate algorithm design, yet unrestricted generated code is unsuitable for transport-network control because feasibility, reproducibility, and robustness must be enforced independently of the model. We present VERA-TN, a verification-guided framework that compiles a network intent into a bounded algorithm-design specification. The target architecture uses an LLM as a semantic variation operator over typed request-ordering and path-ranking programs; generated logic remains separated from a trusted allocator that enforces path validity, latency, capacity, and single-path constraints. We prove feasibility preservation under explicit assumptions and establish a sufficient bound for the lexicographic latency tie-break in the exact reference model. The released proof-of-concept instantiates the same interface with a bounded ten-parameter numerical candidate and deterministic replay, rather than a completed live-LLM/AST study. Across 150 certified held-out cases on a 28-node TEFNET24-derived hierarchy, evolutionary search reaches a mean priority-utility ratio of 0.958, compared with 0.952 for equal-budget random search and 0.940 for priority-greedy routing. The gain over random search is small but statistically detectable (Holm- adjusted p = 0.0083). The candidate does not improve congestion relative to MILP-C, and the effect of failure-aware training is inconclusive at the 0.05 level (p = 0.051). Eight discovery runs on the official national topology and replay on 12 unseen metro-regional topologies show no stable intent-specific specialization. These results support the trust-boundary and numerical-evolution claims but do not establish a benefit from LLM generation.

Time-series foundation models (TSFMs) provide forecasts for operational decisions, but accuracy alone does not determine their value. Evaluating agents that use these models requires measuring decision quality and forecast cost. FWBench evaluates this capability on 1,251 electricity and cycle-hire cases using fixed forecast tools and simulated capacity contracts. Agents select models, histories and horizons, then submit capacities to minimize a stated loss-cost objective. We evaluated two hosted and eight local configurations, including small language models, and tested local models with and without TSFMs. GPT-6 Astra bought inexpensive short-horizon forecasts selectively, using 2.5% of the budget, and outperformed fixed policies when the saved decisions were scored with three loss-cost weightings. FWBench enables reproducible evaluation of how language models select and use time-series forecasts to make decisions under cost constraints.

Speech technology penalizes some voices: recognition errs nearly twice as often for Black speakers, and accuracy declines for second-language accents and older speakers. We introduce TRIAD, an audit grid crossing 120 texts, 24 rendered demographic voice profiles (gender, age band, accent), and ten expressive styles via controllable text-to-speech, isolating perceived demographic attributes from content and affect. For ten open-weights encoders we define axis-fidelity functionals, principal-angle leakage between axis subspaces, and group-conditional gaps; a proposition proves that average probe disparity grows with the same aggregate voice-semantic leakage $\Lambda$ we measure, and a corollary shows that peak leakage forces worst-case disparity inside an active region. The measured mean-square probe disparity tracks $\Lambda$ (Pearson r = 0.93), and a black-box protocol exposes the same signature in two closed-source models. ORCA, an adapter combining axis-specific contrastive heads, an orthogonality penalty, and group-balanced sampling, cuts leakage 72% and roughly halves the gaps.

Contact detection during robotic manipulation allows robots to recognize unexpected contact and adapt their motion accordingly. However, in low-cost robot arms without dedicated force or tactile sensors, detecting weak contacts from proprioception is challenging because the resulting changes in joint-level proprioceptive signals can be small compared to normal variation and noise caused by robot motion itself. We introduce Contact-free Proprioceptive Response Estimation (CoPRE), improving proprioceptive contact detection sensitivity using only contact-free motion, without additional force sensors, contact labels, or analytical dynamics models. CoPRE estimate the expected joint torques under contact-free motion from proprioceptive state history and commanded motion, while removing recent observations that may already reflect contact. It then computes the residual between the expected and observed joint torque estimates, and maps this residual to a contact score using a noise-weighted Jacobian. Real-robot experiments on ARX Arm and Unitree G1 show that CoPRE achieves 74.1% and 82.2% recall on the tested contact trials, compared with 0%/0% on ARX and 16.3%/42.2% on G1 for the learned torque-prediction and inverse-dynamics baselines. CoPRE also reaches 90% detection rate for pushing force at 3.5 N on ARX and 5.5 N on G1. To demonstrate the downstream utility of our method, we implement belief-space manipulation planning for obstacle-aware object placement and book insertion where detected contacts update the spatial belief and enable the robot to retreat from blocked motions, adjust its pose, and retry. Project website at https://copre-arm.github.io

Retrieval-augmented generation often relies on multiple retrieved contexts that contain substantial redundancy, motivating context compression to preserve useful information under limited input budgets. Likelihood-based compressors can account for cross-context redundancy through sequential scoring, but this makes evidence scores dependent on context order. We show that permuting the same contexts under an unchanged compressor can substantially change which supporting evidence survives compression. We attribute this sensitivity to information preemption: earlier, partially relevant contexts can absorb credit for shared information, reducing the incremental scores of later, stronger evidence and increasing its risk of removal. Controlled pair-swap interventions provide direct empirical support for this mechanism by showing that placing stronger evidence before overlapping, partially relevant contexts can improve its survival. Based on this insight, we introduce MORSE, a compression-aware method for evidence-preserving context ordering. MORSE uses reverse query likelihood to construct an evidence-first anchor and to evaluate compressed candidate outputs, enabling compression-aware selection among alternative permutations. Across multi-hop Question Answering (QA) benchmarks, compression procedures, budgets, and scoring models, MORSE improves evidence retention over reverse ordering and generally outperforms matched random search, with downstream QA gains. Our code is available at https://github.com/tbn5pj/MORSE_code

End-to-end speech-to-speech dialogue models listen and speak simultaneously, so a continuously open acoustic channel is exposed to adversarial manipulation. We formalize imperceptible attacks on full-duplex agents as optimization over additive perturbations confined beneath the psychoacoustic masking threshold of the carrier speech, under three goals: targeted semantic hijacking, response suppression, and policy jailbreaking. Against an undefended Moshi-style agent, white-box attacks succeed in up to 91.7% of trials. We then introduce psychoacoustically aligned latent smoothing (PALS), which injects anisotropic Gaussian noise shaped by local codebook covariance at the residual-vector-quantized latent interface, with input noise shaped by the masking threshold constraining the attacker and trained by a Kullback–Leibler consistency objective. Deployed with no inference-time cost, PALS reduces hijack to 8.3%, mute to 11.2%, and jailbreak to 9.1% at clean quality within 2.3%. A Monte Carlo-smoothed variant certifies an ellipsoidal latent radius up to 0.616, a guaranteed floor that the empirical robustness far exceeds.

Cross-lingual legal question answering must retrieve statutes across languages while preventing unsupported legal claims. We introduce a bilingual evaluation suite of 231 Vietnamese–English question–answer pairs from Vietnamese labour law. Of these, 75 are additionally annotated for five challenging legal reasoning phenomena. We evaluate a verifier-guided pipeline that decomposes answers into claims, checks citation reachability and entailment, and corrects citation failures and contradictions. We also introduce six automatic diagnostics for faithfulness to retrieved evidence, covering citations, modality, exceptions, procedures, conclusions, and evidential support. Experiments show that learned-sparse retrieval performs poorly for English-to-Vietnamese retrieval (R@5~=~0.032), whereas dense retrieval reaches 0.358 and slightly outperforms hybrid retrieval. Translation placement has no statistically detectable effect on these automatic diagnostics in our controlled comparison and supporting sensitivity analyses. Verifier-guided correction improves citation preservation by $0.022$–$0.034$ at the system level but produces no reliable gains in the remaining dimensions. Human evaluation further shows that the automatic diagnostics do not fully align with human judgements of answer quality.

Test-time scaling with parallel branches is widely adopted to improve performance on challenging reasoning tasks. The predominant approach, repeated sampling, draws branches independently from a single policy, which can produce redundant attempts and thereby limit the gains from additional inference compute. To address this limitation, we propose Planned Test-Time Scaling (PTTS), which replaces independent sampling with a coordinated joint policy: a planner generates a solution outline for each branch, steering the branches toward distinct reasoning paths, and an executor produces a full solution conditioned on each outline. Formally, we show that PTTS strictly generalizes repeated sampling and, in a stylized setting, provably promotes coverage of complementary reasoning modes and yields better pass@k scaling. We instantiate PTTS on top of strong reasoning models, keeping them fixed as executors while replacing repeated sampling with PTTS inference to further enhance test-time scaling. Concretely, we develop two variants: PTTS-ZS prompts a model to jointly generate outlines for all branches in a single autoregressive pass, while PTTS-RL directly optimizes the planner against the pass@k reward using truncated execution rollouts for efficient training and a sharper reward signal. Across five mathematical reasoning benchmarks with Qwen3-1.7B and 4B, PTTS-ZS improves pass@64 over repeated sampling by up to 6.7 points, while PTTS-RL further increases the gain to up to 13.4 points. Further analysis indicates that broader coverage of distinct reasoning paths contributes to these gains. Overall, PTTS provides a general framework for improving test-time scaling by coordinating reasoning branches, with zero-shot and trainable instantiations that yield substantial performance gains.

Recurrent-depth language models, such as looped Transformers, repeatedly apply shared network blocks to refine latent representations without generating explicit intermediate reasoning tokens. However, each step recomputes full attention over the entire context, repeating costly global routing. We study how attention routing evolves across recurrent depth and find a consistent separation in convergence timescales: attention support and distributions stabilize substantially earlier than hidden states and attention outputs. This suggests two stages of recurrent inference: early discovery of a sparse working set, followed by representation refinement over largely stable routing support. Motivated by this finding, we introduce WISE (Working-set Inference with Support Exploitation), a training-free method that uses unrestricted attention during early recurrent steps to discover a block-structured working set, then reuses its support in later steps while keeping attention weights and recurrent refinement dynamic. Controlled interventions show that multi-step discovery yields more effective working sets than first-step selection, and that support reuse better preserves model behavior than more restrictive forms of attention reuse. Across multi-hop QA benchmarks, WISE largely preserves full-attention performance. Matched context-scaling experiments reveal an increasingly favorable quality-efficiency tradeoff as routing support becomes sparser with longer contexts. A sparse-attention implementation achieves up to a 1.76x late-step attention speedup over native FlashAttention at 4K context. Code: https://github.com/tbn5pj/WISE_code.

Benchmarks for full-duplex spoken dialogue models score turn-taking with binary fixed-window rules that reward immediate response or silence by completeness of the prior turn. We argue that the appropriateness of a response offset, whether delayed silence or anticipatory overlap, is conditional on the speaker's latent intent, identifiable only from that speaker's behavior. We introduce TACT, a benchmark of 9,728 episodes and 73.2 hours from five dyadic corpora; each episode carries dialogue history, a per-speaker memory profile, and an annotator-derived posterior over six intent classes. Scoring replaces binary windows with a strictly proper threshold-weighted continuous ranked probability score whose weights are intent-conditioned timing kernels fitted to human floor-transfer-offset distributions, proving boundedness, consistency, and binary reduction. Across eleven systems the best model reaches 0.47 against a human topline of 0.86, is nearly invariant to speaker profiles, and TACT agrees with human judgments at Spearman 0.81 versus 0.46 for binary metrics.

Generative image models can produce highly realistic images, raising concerns about potential misuse in creating deceptive content. Current deepfake approaches face several challenges, including limited generalizability, lack of interpretability, and poor actionability. To help address these, we present ASAP, an interactive visualization system designed to empower users in the analysis and summarization of deceptive patterns in AI-generated images. ASAP introduces a novel CLIP-adapted image encoder that generates interpretable representations, enabling the extraction of influential pixel regions via calculated masks. This approach facilitates the identification of key deceptive features through influence measurement techniques. These backend techniques are integrated into a visual analytics dashboard that allows users to quantify and analyze authenticity-indicative patterns in image collections containing both authentic and AI-generated images. This approach also supports the comparative analysis of various generative models, including GANs and diffusion models. We demonstrate ASAP's efficacy through a user study and two application scenarios using established fake image detection benchmarks, showcasing its ability to effectively extract and quantify deceptive patterns.

Visual Place Recognition (VPR) in natural environments remains challenging due to repetitive vegetation, sparse distinctive landmarks, and substantial appearance and viewpoint variation across traversals. While visual observations of the same place can change considerably, their underlying spatial structure is often more persistent. We exploit this complementary geometric consistency through Depth-Aware Distillation (DAD), which conditions the token representations of a pretrained Vision Foundation Model (VFM) on geometry inferred by a Geometric Foundation Model (GFM), without any depth sensor. Rather than treating geometry as an additional input modality, DAD projects image-aligned depth into the VFM token space and selectively modulates visual representations through channel-wise geometric conditioning. A two-stage teacher-guided learning strategy first anchors the geometry-conditioned representation to the pretrained appearance space, before refining it for place discrimination. Evaluated on the WildCross benchmark, DAD improves average inter-sequence Recall@1 from 61.41% to 66.37% and Recall@5 from 65.86% to 72.49% over a matched appearance-only baseline, with the largest gains under reverse traversal and long-term appearance variation. These results show that GFM-derived geometry can provide a persistent structural prior for VPR when visual appearance becomes unreliable.

Weighted sum-rate maximization in multicell multiple-input multiple-output (MIMO) networks is commonly addressed by the weighted minimum mean-square error (WMMSE) algorithm or fractional programming (FP), both of which, after fixing their auxiliary variables, solve a power-constrained quadratic transmit problem that requires costly dense operations for large arrays. Replacing the underlying curvature matrix with a scaled identity can avoid the matrix inverse operation and thereby reduce complexity, but it discards the curvature eigenvalue structure and yields a loose lower bound. We propose Spectral-NFP, which retains selected dominant curvature eigenpairs and uses a scaled identity matrix to bound the curvature on the remaining subspace from above. The retained rank thus traces a continuous path from NFP to the exact WMMSE transmit update. With the surrogate curvature fixed, Spectral-NFP can be interpreted as Euclidean projected-gradient ascent after a linear coordinate transformation, admitting Nesterov-type acceleration. We derive a lower bound on the one-step transmit-objective gain of Spectral-NFP relative to WMMSE, expressed in terms of the curvature eigenvalues. Under an idealized Wishart model, we analyze this bound in both finite dimensions and the large-system limit, obtaining an asymptotic rank-selection rule. Experimental results show that retaining at most 20% of the transmit dimension, and often less than 10%, achieves more than 99% of the WMMSE WSR. In large-array settings, the measured update time is below 20% of that required by WMMSE.

Citizens' assemblies are deliberative bodies intended to form a microcosm of the population. Organizers rely on quota-based stratification and must decide which attributes define resemblance to the public. Yet meeting every quota can still leave a dimension citizens value unrepresented. We study this attribute-selection problem in general-purpose and climate-focused assemblies through randomized conjoint experiments. We find that demographic attributes matter for perceived representation, but political alignment and context-specific attributes such as climate concern exert a stronger influence. When both are shown in a climate-focused setting, each remains influential, with political alignment having the larger estimated marginal effect. We also examine the omission of a relevant stratification attribute. Panels stratified on demographics, even with political alignment included, match the observed pool's climate-concern distribution no better than uniform random samples. These results suggest that representation on a relevant topic-specific attribute cannot always be recovered through correlated demographic or political quotas, and may therefore require explicit stratification. Finally, we ask whether representation preferences can be learned from the observed profiles. We compare predictive models, from simple, interpretable matching rules to a learned metric and a respondent-conditioned utility model. Both learned models predict choices for respondents excluded from training with substantial accuracy, revealing generalizable structure without fully capturing these judgments. Together, these findings guide attribute selection in citizens' assemblies: designers should consider political and topic-specific dimensions alongside demographics, avoid assuming correlated proxies protect omitted dimensions, and use predictive models to diagnose how profiles shape representation choices.

Verifying outsourced language-model inference requires a precisely identified computation and an audit whose cost a service can afford. We present Sampled Layerwise Proofs (SLP), a protocol and prototype that commits the boundary activations of every chunk of an inference trace, absorbs all commitments before any challenge is drawn, and then proves a verifier-selected subset of chunks together with the chunks that bind the prompt and the answer. Audit coverage becomes a runtime parameter over one set of commitments: on a TinyLlama-1.1B trace, proving seven of 47 chunks takes 22.0% of the time and 6.8% of the proof size of proving all 47. Because proof cost is dominated by weights rather than tokens, SLP packs concurrent requests into one trace under a block-diagonal causal mask and binds the prompt and answer of each request to its slot. Twelve packed requests are proved in 181.9 s, 6.5 times less than twelve separate proofs at the measured single-proof cost, and a simulated service proves twelve requests at 30.6 s per request with 0.6 s of verification each, rejecting a tampered answer. Disk-backed integer weights and streamed polynomial commitments let a single Llama-2-70B run complete on a 2 TB CPU host: 163 chunks sealed, five proved, a 4.34 MiB proof in 1,259 s, verified in 46.3 s without the weights. The proven object is a fixed-point canonical model; we trace a severe fidelity loss to the residual-stream bit width, repair it with an LLM-aware observer, and measure 84.8-84.9% argmax agreement with the floating-point reference over 334,705 WikiText-2 test positions. The limits are stated as precisely: guarantees cover proven chunks only, a fixed invalid chunk in the 70B setting is covered with probability 3/161, a manifest-only Fiat-Shamir schedule can be ground at 12.5 ms per attempt and needs an externally ordered challenge, and all measurements use a test reference string.

Anchor and Perturb (AnP) is a lightweight framework that resolves multi-agent coordination failures by decoupling exploratory variance injection from recurrent manifold stability. Existing remediation strategies predominantly alter mixing network architectures or enforce simultaneous exploration across the collective, which inevitably precipitates severe temporal-difference penalties in non-monotonic reward spaces. Specifically, AnP isolates underperforming lazy agents and injects an asymmetric exploratory pulse into targeted coordinates whilst anchoring converged teammates to nominal greedy exploitation. Empirical telemetry benchmarks demonstrate that AnP successfully rescues collapsed joint policies (recovering from a 5% evaluation win rate nadir back to 85%) and facilitates escape from suboptimal coordination plateaus, sustaining peak win rates of 90% without requiring structural network modifications.

Camera localization in a prior LiDAR map provides a persistent geometric reference for long-term robotic navigation, yet remains challenging because of the substantial modality gap between camera images and point-cloud maps. We present a unified localization framework that makes the LiDAR map visually addressable rather than relying on a dedicated image-LiDAR correspondence model. Map geometry and reflectivity are rendered into LiDAR-derived quasi-images with explicit 2D-3D provenance, enabling camera observations and rendered map views to share mature visual features and matchers for both global localization and continuous pose tracking. Point and line correspondences are established through this common visual interface, while the retained provenance recovers metric LiDAR geometry and line-supported planar constraints for pose estimation. To improve robustness under ambiguous associations and weak geometry, we further introduce a distribution-aware, observability-complementary optimization strategy. Instead of reducing matching ambiguity to a scalar confidence, candidate association distributions are propagated into directional pose-information uncertainty, and reliable structural factors are selectively reinforced according to their ability to complement the currently weak pose directions. Experiments on the EuRoC MAV benchmark and self-collected real-world sequences demonstrate accurate global localization and robust continuous 6-DoF tracking using only a pre-built LiDAR map as the persistent prior, including under severe illumination variations and dynamic occlusions.