Papers

Understanding agent behavior requires methods that scale to thousands of trajectories and surface new patterns in long, often unfamiliar tasks where pre-built classifiers fall short. We propose to bring grounded theory into agent trajectory analysis: a six-decade-old qualitative method from the social sciences, with a principled saturation criterion and an auditable trail from data to theory. We propose AutoTraceGT (Automated Trace analysis through Grounded Theory), the first multi-agent pipeline that automates grounded theory on agent trajectories. It iteratively performs open, axial, and theoretical coding until saturation, producing a behavioral taxonomy tailored to each task. Across six trajectory corpora, AutoTraceGT produces codebooks that recover 73-91 percent of the failure modes in human-annotated taxonomies and surface additional patterns that those taxonomies miss. The emergent theoretical narrative aligns with prior expert accounts. Used as a deductive feature space, the codebook outperforms zero-shot and few-shot LLM baselines on downstream failure prediction. These results suggest Grounded Theory offers a scalable analytic tool for ML researchers and agent developers studying what agents actually do.

Accurate uncertainty estimation is essential for machine learning systems de- ployed in high-stakes domains such as medicine. Traditional approaches primarily rely on probability outputs from trained models (point predictions), which provide no formal guarantees on prediction coverage and often require additional calibra- tion techniques to improve reliability. In contrast, conformal prediction (region prediction) offers a principled alternative by generating prediction sets with finite- sample validity guarantees, ensuring that the ground truth is contained within the set at a specified confidence level. In this study, we explore the impact of pre-training approach, dataset scale and domain on both point and region-level uncertainty quantification, by studying domain-specific vision medical foundation models vs. general domain vision foundation models. We conduct a comprehensive evaluation across foundation models trained on retinal, histopathological, and Chest X-Rays data, applying various calibration techniques. Our results demonstrate that (1) pre-training on higher-quality domain-specific datasets along with self-supervised learning leads to better-calibrated point predictions than general domain pre-training, (2) stan- dard re-calibration methods alone cannot fully mitigate uncertainty discrepancies across models trained on different data sources, (3) domain-specific foundation model can lead to more efficient conformal prediction. These findings highlight the importance of careful model selection and the inte- gration of both point and region prediction to enhance the reliability and trust- worthiness of medical AI systems. Our work underscores the need for a holistic approach to uncertainty quantification in recent development of medical vision foundation model, ensuring robust and interpretable AI-driven decision-making.

Cross-view video representation learning aims to capture viewpoint-invariant action semantics despite substantial appearance changes across egocentric and exocentric videos. However, existing methods encode each video as a unified embedding, where view-invariant and view-variant semantics inevitably entangle under co-occurrences - a failure mode we show persists even in cross-view methods explicitly trained for view-invariance. Our key insight is that a view-invariant feature is truly disentangled when it can be sufficiently recomposed with an arbitrary view-variant feature while preserving their independent semantics. Building on this, we propose PRISM, that decomposes video into view-invariant and view-variant latents and recompose them under language supervision encouraging clean decomposition of the two streams. PRISM achieves state-of-the-art results on EgoExo4D, EgoExoLearn, AE2, even surpassing in-domain models under zero-shot setting. Code is available at https://github.com/litcoderr/prism.

Multi-agent applications delegate work across independently operated deployers. After an incident, a verifier must answer two questions: which deployer released the reported bytes, and whether each cross-deployer edge was authorized. Credentials establish who may act, but need not bind them to later output bytes or prove both deployers authorized a dynamically created edge. We present a two-layer attestation design for dynamic delegation without a shared authority, public log, or precommitted workflow. A trusted deployer runtime signs a hash of each released output; this records released bytes but does not prevent prompt injection. Ancestry evidence records edge authorization. Under a unified threat model, we compare a signed linked list, a Merkle-chain variant, and a co-signed DAG. The primitives are standard; the contribution is deployer-side binding and the evidence needed for the two questions. After child-key compromise, the single-signer designs permit an unauthorized parent binding, whereas the co-signed DAG rejects it because the parent must authorize the edge. Fixed adversary matrices and regression tests validate the composed verifier. On an Apple M1 Pro, ancestry-only checks take 24.3-499.2us per hop. In a live local multi-service workflow, a parent discovers the child's A2A Agent Card; the child calls an MCP tool and releases local-LLM output: all 30 signed-DAG tasks passed complete verification, while a controlled child-key-only claim was rejected; its mean end-to-end latency was 813.1ms versus 770.8ms without evidence. In a complementary three-availability-zone AWS deployment, all 1,000 valid co-signed-DAG paths verified; issuance averaged 3.651ms and complete verification 5.015ms. The cloud result excludes TLS/mTLS, KMS, and model-serving latency.

Hybrid linear-attention architectures have recently scaled to large open-weight models, offering quality competitive with full attention while substantially reducing key/value (KV) cache growth. However, their in-place recurrent-state updates complicate cache management: prefix reuse requires state checkpoints alongside full-attention KV, while storing state checkpoints in full increases memory pressure, leading to more evictions and repeated prefill. By analyzing the decay structure of Gated DeltaNet (GDN) and Kimi Delta Attention (KDA), we find that different heads and channels retain prefix information over markedly different timescales, which we term retention horizons. This variation suggests substantial compression potential in persistent state checkpoints. Building on this observation, we introduce Decay-Aware State Compression (DASC), which derives retention horizons from model weights, selects long-horizon state units, and packs them into a ragged state checkpoint layout. To integrate efficiently with tensor-parallel inference engines, DASC furtherly balances compressed state checkpoints across TP ranks. On reuse, DASC either zero-fills omitted units or refreshes them from a bounded suffix with additional compute cost. Across retrieval and end-to-end reasoning benchmarks on Kimi-Linear, conservative DASC configurations remain close to full caching while compressing KDA recurrent state checkpoints by $2.63\times$. Under fixed state checkpoint memory budgets, the resulting capacity gains reduce mean Time to First Token (TTFT) by 42.6% and improve input throughput by 68.4%. At larger compression ratio, suffix refresh recovers much of the accuracy lost to more aggressive omission, at the cost of additional replay computation. Qwen with GDN exhibits a similar quality–efficiency trend, showing that DASC extends from channel-wise KDA to head-wise GDN.

Database Management Systems (DBMSs) support multiple SQL mechanisms for representing intermediate query results, including VIEWs, Common Table Expressions (CTEs), and Temporary Tables (TEMPTs). When these mechanisms are used to represent the same intermediate query result, the corresponding queries are expected to produce consistent results. However, we observe that such queries can return inconsistent results, indicating potential DBMS logic bugs. Existing approaches for detecting DBMS logic bugs have never explored result consistency across such equivalent representations. In this paper, we propose ERIQ, a novel testing approach for detecting DBMS logic bugs from the perspective of checking result consistency across Equivalent Representations of Intermediate Query Results. ERIQ constructs SQL variants using a VIEW, a CTE, or a TEMPT to represent the same intermediate query result, executes these variants, and compares their returned results. We evaluated ERIQ on four widely used open-source DBMSs: MySQL, MariaDB, Percona, and OceanBase. In total, ERIQ detected 64 bugs, 63 of which were confirmed by developers, and two have been fixed. Among the confirmed bugs, 54 were unique and previously unknown logic bugs, and one was a documentation issue.

By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1–4 bits per dimension, we reduce memory cost and memory bandwidth of a typical large-scale Approximate Nearest Neighbor (ANN) search system, while reducing its complexity and keeping or improving recall across multiple benchmark datasets. State-of-the-art systems filter candidates using coarse partitions, approximately score them to narrow the set, and then rescore the best with higher precision representations (often >=8 bits per dimension). Our relativized codecs can bring this down to 2–4 bits per dimension. We use the properties of the ANN system to encode residual vectors instead of full vectors, both for the approximate scoring phase and the rescoring phase. Since Maximum Inner Product Search (MIPS) is very sensitive to vector norms, we correct the $L_2$ norms of quantized vectors. Our major innovation is that we correct the $L_2$ norm of the final reconstructed vector rather than just the residual. Our rescaling replaces more complicated schemes, such as Anisotropic loss. The residualization scheme gives us a more favorable quality vs size trade-off than generic quantization methods. Our high-performance implementation leverages a block-wise cascaded Fast Walsh-Hadamard Transform (FWHT) with linear-like complexity, AVX SIMD-optimized codebooks, and a steganographic encoding of scaling factors for perfect cache-line alignment.

We present how Hyper-V sockets can be used as a real-time communication channel for a malware analysis sandbox. We show that, compared to WinSock TCP sockets, Hyper-V sockets are not subject to TCP/IP-layer blocking and are not enumerated by common TCP connection listing tools. We compare the throughput of the two communication channels as a function of buffer size.

Popular adaptive stochastic gradient descent (SGD) methods to train artificial intelligence (AI) systems include the RMSprop, the Adam, and the AdamW optimizers, where the adaptivity parts in Adam and AdamW basically just coincide with RMSprop. Such adaptive methods involve several hyperparameters including the regularization parameter $\epsilon$ (which ensures that one does not divide by 0 and is often chosen to be very close to zero such as $10^{-8}$ in PyTorch by default) and the second moment decay parameter $\beta$ (which is often chosen to be very close to $1$ such as 0.99 (RMSprop) and 0.999 (Adam and AdamW) in PyTorch by default). Despite the high relevance of such methods, it remains an open research problem to provide error estimates for such methods with the error constants being not exploding but uniformly bounded with the respect to the hyperparameters, even in the situation of convex stochastic optimization problems. It is the key contribution of this work to essentially solve this problem for RMSprop. Specifically, we bound the expectation of the stopped evaluation of the objective function at the RMSprop process from above by the sum of an initialization term that decays exponentially in the training time, a stochastic approximation remainder of order $\gamma_n$, and a memory error of order $( 1 - \beta)^2$ with the error constants being uniformly controlled over all admissible choices of the step sizes, the second moment decay parameter $\beta$ and the regularization parameter $\epsilon\in[0,1]$ (also covering $\epsilon=0$). Our non-asymptotic error estimates hold not just for all sufficiently large n but hold for every gradient step $n=1,2,3,...$ with all error constants being explicitly specified. The key innovative new feature in the proof of our analysis are suitable inverse moment bounds for the second moment process in RMSprop.

Function secret sharing (FSS) has become a core primitive in privacy-preserving computation. However, each FSS invocation requires a fresh pair of function keys generated by a trusted dealer , expands the system's trust boundary and hinders practical deployment. Existing dealerless protocols eliminate this dependency, but incur substantial communication and a number of interaction rounds that grows linearly with the input bit-width, making key generation a major bottleneck. This paper present KORD, a protocol–hardware co-design that dramatically reduces the cost of dealerless FSS key generation. At its core is a pair of special-purpose chips that establish a common root of trust through mutual attestation and, within it, reconstruct FSS keys—eliminating the need for a dealer. This root of trust further forms a security boundary within which KORD restructures the generation protocol, collapsing the interaction of prior dealerless protocols into a single round, independent of GGM depth. A cross-key scheduling scheme then interleaves independent GGM-tree traversals, sustaining high computational throughput. KORD reduces per-key-generation communication by 7,633–70,274$\times$ over the state-of-the-art distributed FSS protocol across a comprehensive suite of FSS building blocks. Post-route analysis projects 12.75 million 32-bit DPF keys per second at 204 MHz using 21.5K LUTs, with 99.8% AES lane utilization. On private ResNet-18 inference, KORD cuts the share of end-to-end time spent on key generation from over 96% to 11.9%.

Direct vision-language-action policies generate continuous robot actions efficiently, but standard behavior cloning leaves two complementary gaps: their representations are not explicitly required to describe how the scene evolves over multiple time scales, and deployment trajectories of unequal quality are often reused without separating useful dynamics from undesirable behavior. We introduce \method, a direct world-action policy that combines outcome-agnostic predictive learning with outcome-aware policy improvement. \method first retains a local fixed-offset JEPA objective and adds trajectory-relative multi-horizon transition alignment at 25%, 50%, 75%, and 100% of the remaining episode. These training-only targets require the current policy representation to preserve both local physical changes and longer-range task progress, without supplying explicit future tokens to the action head. \method then trains an independent distributional value critic on cumulative deployment trajectories, computes action-chunk-aligned $N$-step advantages, and converts them into positive, negative, or null text conditions for a flow-matching actor. Thus, every valid trajectory can teach what physically happened, while the actor is deployed only under the condition associated with relatively better actions. The multi-horizon predictor and critic are removed from online execution, preserving direct action generation from the current observation, language instruction, and proprioception. \redclaim{Across the three simulation benchmarks, \method achieves the strongest overall performance while preserving the direct actor's online execution path.}

Recurrent, attention-free sequence models share a structural weakness: a fading state cannot perform exact recall of something seen once, far in the past. We add to the Kathleen trunk a second memory layer – a "notebook": a fixed-key holographic (HRR) associative store with a learned local write gate, a self-gating raw read, and write-triggered forgetting – 25K parameters that attach to the logits of any trunk. (1) Mechanism: on a controlled needle-in-haystack task the notebook reaches 80-82% one-shot recall at 4x the training length, where the bare trunk scores ~4% and a parameter-matched attention head scores 100% inside its training length and 0% beyond it. Addressing is length-invariant by construction; the untrained memory alone recalls at 90% accuracy identically at 512, 2048 and 4096 bytes. Because the store is a linear superposition, two capabilities follow from arithmetic alone: selective unlearning (one subtraction erases one fact to chance, retained facts unharmed) and per-token attribution (counterfactual erasure names the source fact of every correct byte, 100% provenance). (2) Real text: on WikiText-2 bytes the notebook improves prediction of repeated rare words by +0.15-0.27 bits/byte, the gain growing with the distance between mentions and holding zero-shot at 4x training length; write-triggered forgetting eliminates memory pollution at 8x length (first-mention cost +0.33 -> -0.004). (3) Scope and scale: a parameter-matched attention head does generalize on natural-text repetition, so the notebook's claim is exact recall at O(L); on a WikiText-103 ladder (8 to 512 MB) the zero-shot repeat gain rises monotonically. All experiments are pre-registered, seeds reported, and reproducible on a single free-tier GPU.

We study null-space estimation from a noisy matrix. For a simple left null space, we first derive an exact compact expression for the error of the smallest left singular vector. We then give an all-order series for the SVD vector and projector, followed by compact and consistently truncated series forms for the fixed-realization empirical risk and conditional population generalization risk. The recursion extends to a multiple-dimensional null space by following the complete invariant subspace. The convergence radius is not inferred from an error plot: it is computed independently from the nearest complex exceptional point that joins a retained eigenvalue branch to its complement. A reduced-nullity experiment shows that moving this spectral boundary can increase the radius, although the improvement is not monotone in the retained nullity. For individually ordered null directions under Gaussian training with \(\tau\geq m\), we prove that the Wishart splitting matrix \(W\) gives a strict second-order empirical ranking. Gaussian averaging equalizes the leading generalization risks at both small and very large noise, while a column-swap theorem proves strict expected generalization ranking for an isotropic signal subspace. For unequal spikes, an exact population-overlap criterion and a simultaneous \(99\%\) Monte Carlo confidence certificate explain the observed intermediate ranking. A sixth-order risk correction improves the lower-crossover estimate in the reported experiment. This equal–ranked–equal phenomenon is a finite-sample diagnostic related to spectral mixing, but its tolerance crossings, the exceptional-point radius, and the asymptotic BBP threshold are three distinct quantities.

Multi-Agent Debate (MAD) has been widely adopted to improve LLM-based evaluation by prompting multiple agents to negotiate and reach a consensus. However, for subjective rubric-based scoring, inter-agent agreement does not guarantee alignment with human judgments. In this paper, we compare a single-judge baseline against a consensus-based MAD protocol on subjective evaluation tasks and design three ablations to isolate the impact of role prompting, multi-round interaction, and explicit score sharing. Evaluations across six LLMs show that the single-judge baseline achieves the strongest human alignment on average across six judge models, whereas MAD shows degradation in human alignment on both tasks. Our ablations demonstrate that this performance drop stems primarily from asymmetric role prompting rather than the interaction itself. Specifically, assigning a strict judge role introduces a systematic downward bias that the consensus process fails to correct. The central finding is that this bias reflects strict-stance dominance beyond averaging: the consensus score falls well beyond the arithmetic midpoint of the standalone strict and lenient conditions, rather than averaging them out. Removing role asymmetry (Symmetric MAD) largely recovers baseline performance, while masking peer scores widens inter-agent disagreement on average and worsens average human alignment. These findings demonstrate that multi-agent consensus can enforce artificial agreement at the expense of true human alignment, revealing a structural limitation in consensus-style, role-specialized MAD protocols for subjective scoring.

As Large Language Models rapidly advance, performance on standard multiple-choice question answering (MCQA) benchmarks is reaching saturation. While the community has responded by developing increasingly difficult datasets, validating question quality and filtering flawed items remains a labor-intensive process. To provide a scalable diagnostic approach, we propose a two-component probabilistic framework for auditing MCQA benchmarks using model output distributions. First, for benchmark-level analysis, we characterize the probability landscape using the top prediction probability ($P_{top1}$) and normalized residual entropy ($H_{norm}$), summarized globally by Mean Pairwise Distance (MPD). Second, for item-level diagnostics, we introduce noise injection to reduce meaningful distractor competition, enabling us to flag candidate items for targeted human review and categorize residual failure patterns. Across four MCQA benchmarks, our landscape analysis reveals benchmark-level differences in model confidence and residual option competition. Concurrently, our noise-injection method flags potentially actionable item-level issues, showing alignment with expert error annotations from MMLU-Redux. These results suggest that our probability-based framework provides a lightweight audit lens for comparing macro-level benchmark structure and prioritizing individual items for targeted human review.

Automatic cardiac image segmentation is pivotal for diagnosing and treating cardiac diseases. In this work, we introduce MCSeg, a volumetric transformer-based network tailored for multi-modal cardiac segmentation. To overcome the architectural mismatch inherent in existing hybrid networks, we propose a novel Scaling Feature Pyramid (SFP). Unlike conventional skip connections, the SFP effectively bridges the single-scale 3D Vision Transformer (ViT) encoder and the multi-scale CNN decoder by transforming the ViT's output into a hierarchical feature pyramid, ensuring that global contextual information is effectively leveraged. For the training paradigm, the ViT encoder first undergoes self-supervised pre-training via masked image modeling. Subsequently, the network is fine-tuned on downstream tasks, during which a regional mutual information (RMI) loss is integrated to improve boundary segmentation accuracy. In experiments, MCSeg consistently outperforms eleven SOTA methods on CT dataset ImageCHD, multi-modal dataset MM-WHS, MRI dataset HVSMR-2.0 and MSD Heart, highlighting the effectiveness of our MCSeg for multi-modal cardiac segmentation tasks. Furthermore, MCSeg's superior performance in few-shot experiment showcases its significant potential in adapting to limited data scenarios. Codes and pre-trained ViT-B weights are open-sourced at https://openi.pcl.ac.cn/OpenMedIA/MCSeg

We present OLIVE, a framework for adapting a foundation model to provide real-time assistance in temporally demanding, high-stakes, and dynamic tasks. We show that passive EEG, fused online with behavioral evidence, can meaningfully extend the number of targets users detect and engage beyond their unaided action bandwidth. OLIVE learns from both explicit behavioral signals (the targets the user shoots down in an XR first-person shooter game) and implicit physiological signals (fixation-locked EEG) to provide timely guidance, continuously adapting a frozen vision-language model's inference on which items are task-relevant by jointly estimating per-source reliability without manual labels or offline training. Through three user studies, including two live deployments of an assistive agent driven by OLIVE in XR, we show that OLIVE Pareto-dominates prior test-time adaptation frameworks, achieving the highest convergence rate at comparable convergence speed. Combining implicit physiological and explicit behavioral signals, the OLIVE agent produces the largest and most reliable within-session improvement to a user's ability to detect and engage targets, largely independent of the individual's skill. When the target switches silently, the agent that uses both behavioral and physiological signals reconverges significantly faster than the behavior-only agent (1.27 times faster on average, p = .008), restoring trustworthy guidance at the moment the task changes, precisely when reliable assistance matters most.

Tactile sensing is essential for physical interaction in robotics and human–machine systems. However, combining rich tactile information with compact hardware, low cost, and low computational overhead remains challenging. This work presents SpectraTac, a compact, camera-free optical tactile sensor that combines active red–green–blue (RGB) illumination with spatially distributed color sensing. Contact deforms a compliant transparent elastomer and modulates its internal light field, producing spatially differentiated changes in color and intensity. Three distributed color sensors capture these responses as low-dimensional spatio-spectral features, avoiding cameras, imaging optics, and high-dimensional image processing. The device measures 19.2 mm in diameter and 4 mm in height, with a material cost below USD~5. A data-driven decoding framework simultaneously estimates three-dimensional (3D) force and the contact region from the optical measurements. For 3D force prediction, the sensor achieved mean absolute errors (MAEs) of 0.161, 0.164, and 0.429 N along the x-, y-, and z-axes, respectively. The nine-region contact-classification accuracy was 99.9%. We further evaluated real-time 3D force tracking and contact-region-based human–machine interaction through an interactive control task. These results indicate that distributed color-resolved optical sensing offers a compact, low-cost alternative to camera-based tactile sensing for robotics, wearable sensing, and interactive systems.

Transformer-based electrocardiogram (ECG) models commonly tokenize waveforms into fixed temporal patches. Though convenient, fixed patching can split heartbeat structures across token boundaries. We study beat-synchronous tokenization as a physiologically grounded alternative, comparing fixed patches with three beat-aligned strategies: resampled beats, adaptive pooled beats, and resampled beats augmented with R–R interval information. Experiments span two settings: 10-second 12-lead diagnostic classification on PTB-XL after MIMIC-IV-ECG masked pretraining, and 60-second single-lead rhythm classification on Icentia11k after patient-level contrastive pretraining. On PTB-XL, resampled beat tokens achieve the highest mean macro Area Under the ROC Curve (AUROC; 0.8945) and nearly match the best fixed-patch macro Area Under the Precision-Recall Curve (AUPRC; 0.7414), reducing average sequence length from 100 to 11.2 tokens. On Icentia11k, beat-synchronous tokenizers obtain comparable AUPRC to fixed patching with better stability across runs. These results suggest morphology-preserving beat tokenization is a compact, competitive alternative to fixed temporal patching.

The loss landscape of Deep Neural Networks (DNNs) exhibits highly complex and non-convex properties. Recent studies have revealed the phenomenon of mode connectivity, demonstrating that independently trained network modes can be connected via a continuous low-loss path. However, existing mode connectivity research is predominantly confined to classifier-based models, leaving it an open question whether similar geometric properties exist in modern complex models. In this paper, we extend the boundaries of mode connectivity to generative and contrastive domains (specifically DDPM and NanoCLIP). Addressing the unique architecture of DDPM and CLIP, we propose an architecture-aware connection building algorithm. Extensive empirical results demonstrate for the first time that we successfully discover mode connectivity between independently trained DDPM and NanoCLIP modes. Our work provides a novel perspective for understanding the geometric properties of the loss landscapes in modern generative and contrastive models.

Retail banking attrition is usually represented as a terminal binary event, even though client relationships often weaken earlier through partial movements of deposits, investments, and recurring activity to external financial institutions. This paper defines that preceding state as financial fragmentation and presents an end-to-end temporal machine-learning system for predicting it before complete disengagement. Using anonymized multi-source data from a large retail bank, the framework predicts whether a valid external transfer or investment event will occur within 90 days. The study uses 595,220 client-month observations, with 346 engineered features combining monthly client profiles, balances, product relationships, prior flow-of-funds behavior, macroeconomic conditions, and competitor activity. A four-stage XGBoost cascade estimates (1) whether an external outflow will occur within 90 days, (2) the expected amount, (3) the originating product, and (4) the destination financial institution. The primary classifier achieved a test precision-recall area under the curve of 0.823. At the validation-selected threshold, it produced 86.4% precision, 75.1% recall, and an F1 score of 0.803. Ranking test observations in descending Stage 1 fragmentation score, the top 1% of clients yielded 95.3% precision, while the top 5% captured 78.7% of observed outflow cases. The amount model placed 94.9% of predictions within an adjacent amount bucket. Destination prediction reached a macro-F1 of 0.81 across 27 classes; source-product prediction achieved a weighted F1 of 0.92. By moving the analytical focus from terminal churn to earlier fund migration, the proposed approach provides a practical foundation for proactive, explainable, and economically informed client-retention decision support.

As LLM agents take real-world actions through tools, indirect prompt injection (IPI) has emerged as a serious threat. The standard metric, Attack Success Rate (ASR), counts whether an injection succeeds but ignores what the user notices in the agent's final response. Looking at successful injection traces, we find two distinct outcomes: the agent executes the injection while returning an otherwise normal response, or reports the injected action in its final response, giving the user a chance to notice. We call these covert and overt successes. From the user's perspective, we decompose ASR into the Covert Success Rate (CSR), counting successes leaving no trace in the final response, and the Overt Success Rate (OSR), counting successes the user can detect. To understand what drives the gap, we analyze successful trajectories and find that the agent's behavior after the injection separates covert from overt: covert traces hand control back to the user task before ending, while overt traces end at the attack itself. This split follows from the ReAct format, where the final response summarizes the most recent action. Building on this observation, we propose ICoA (Induced Covert Attack), an IPI attack designed to induce covert outcomes by steering the agent back to the user task after executing the injection. Across four target models on AgentDojo, ICoA achieves the highest CSR, with gains of 3.79-12.01 percentage points over the strongest baseline.

The sound speed profile in the deep Arctic Ocean causes the surface layer to form a normal mode waveguide. When the depth of the sound source or receiver is near a node of the eigenfunction, the source cannot excite the mode, or the receiver cannot detect it, resulting in the modal amplitude at the receiver being approximately zero. This manifests as a dispersion interruption in the dispersion structure, which can be observed through time-frequency analysis of the received acoustic signal. Based on the interruption frequency identified from the received signal, combined with the relationship between node depth and modal frequency calculated from the ocean sound speed profile, the source depth can be estimated if the receiver depth is known. The phenomenon of dispersion interruption and the method of estimating source depth have been validated through simulations and experiments.

Recent advances in camouflaged object detection (COD) have led to substantial progress in challenging low-visibility scenarios, with pioneering studies demonstrating notable success in localizing objects in camouflaged scenes. Despite these achievements, existing approaches predominantly rely on conventional three-channel RGB imagery, thereby constraining the available visual information to a limited spectral range. Multispectral images offer a wide range of information about a scene by capturing fine-grained spectral signatures. Hence, by leveraging multispectral images for COD, we introduce a novel approach to detect camouflaged objects from the corresponding multispectral inputs. In particular, we propose an end-to-end framework, \textbf{MSFormer}, that takes a multispectral camouflaged image as input and predicts a binary mask for it. Additionally, we also provide empirical justification for integrating multispectral bands for this complex low-vision task. Our extensive experiments demonstrate the effectiveness of our method, which outperforms existing methods.

Smith's conjecture asserts that in every $k$-connected graph with $k\geq 2$, any two longest cycles intersect in at least $k$ vertices. In this work, we establish an $\Omega(k^{8/11})$ bound for this conjecture, improving upon the $\Omega(k^{2/3})$ bound of Ma and Zhao. Our proof combines a Ramsey theoretic refinement of the traditional Turán-type approach with computer search.

Clinical AI often optimizes predictive performance without engaging how clinicians decide where to look and what to write. We present Co-Annotator, which distills expert gaze and dictation into two guidance components: a gaze-aligned Vision Transformer producing fixation-aligned areas of interest (AOIs), and an ontology-bounded vision-language model (VLM) that pre-fills editable biomarker summaries for retinal optical coherence tomography (OCT). We first collect expert gaze and dictations (US1) to train the models, significantly improving diagnostic accuracy and biomarker generation. We then deploy the system with ophthalmology residents: a controlled resident study (US2) confirmed each modality is safe and independently beneficial, with AOI guidance producing lasting perceptual efficiency gains through post-guidance carryover and VLM guidance more than doubling biomarker documentation breadth. In a combined deployment across two academic institutions (US3), providing both modalities simultaneously produced efficiency gains that substantially exceeded either modality alone: correct diagnoses per minute increased by 40% and comment editing time fell by 67%, without compromising diagnostic accuracy. Notably, neither modality improved efficiency during guidance in US2, which makes the in-guidance efficiency gain under combined guidance in US3 the more striking result. Expert-distilled multimodal guidance can remove two distinct clinical workflow bottlenecks at once (visual search overhead and documentation burden) without compromising the diagnostic accuracy clinicians already achieve.

We prove that certificate complexity can be quartically larger than approximate degree. More precisely, we construct a family of total Boolean functions $G$ with $$ C(G) = \tilde{\Omega}(\tilde{deg}(G)^4), $$ where $C$ denotes certificate complexity and $\tilde{deg}$ denotes $1/3$-approximate degree. This is optimal up to polylogarithmic factors, since every total Boolean function $f$ satisfies $C(f)\le O(\tilde{deg}(f)^4)$ by the classical block-sensitivity bounds of Nisan and Nisan–Szegedy. Thus the result closes the gap between these two measures and improves the previously best known separation $C(f)=\tilde{\Omega}(\tilde{deg}(f)^3)$ by Balodis, Ben-David, Göös, Jain, and Kothari. The construction starts from the partial function they used to quadratically separate $0$-certificate complexity from unambiguous $1$-certificate complexity. It already has the required certificate hardness, but its $0$-certificates are unstructured, which blocks the derivation of a low-degree verifier. We keep its $1$-condition and restrict the $0$-inputs to those certified by a structured family whose validity admits a low-degree approximant, while preserving the quadratic hardness. The partial function with its low-degree verifier is then fed through the cheat-sheet framework to yield the total function $G$ with the claimed separation. The main technical ingredient is an approximate polynomial that verifies the certificate in degree $\tilde{O}(\sqrt n)$. The verifier forms a low-degree count $W$ of the candidate $1$-certificates that remain compatible with the asserted $0$-certificate, and tests whether this count is zero. Crucially, the construction ensures that $W$ never exceeds $\tilde{O}(n)$, instead of the $\Theta(n^2)$ candidate pairs it counts bringing the verification down to degree $\tilde{O}(\sqrt n)$.

Speech enhancement (SE) is commonly applied as a preprocessing step in spoken AI pipelines under the assumption that better audio quality improves downstream task performance. Whether SE-induced distortions propagate to downstream LLM task performance remains an open question. We introduce Output Divergence Rate (ODR), which measures how often SE changes an LLM's intent classification relative to clean speech, and benchmark five conditions on 2,974 SLURP clips using Whisper large-v3 and wav2vec2-large cascades. Every condition produces ODR significantly above zero ($p < 0.001$, binomial test). MetricGAN{+} more than doubles ODR versus unenhanced noisy speech (0.318 vs. 0.135) despite improving PESQ, and unmitigated echo reaches an ODR of 0.836 through speaker substitution, a failure WER cannot capture. Audio quality metrics range from near-zero to moderate correlation with ODR (SQUIM-MOS $\rho=-0.068$, PESQ $\rho=-0.467$). The MetricGAN{+} and echo results replicate across ASR architectures, indicating that standard audio quality metrics are insufficient for LLM pipeline quality.

Generating multiple diverse and high-quality solutions is valuable for many applications, such as code-test generation and drug discovery. However, Large Language Models (LLMs) tend to converge on a single high-confidence solution during inference, limiting exploration of alternative valid solution paths. Existing test-time methods promote diversity through tree-like search and prune semantically similar branches using response-level semantic embeddings. However, we find that such embeddings are easily confounded by linguistic and stylistic similarities, making it difficult to distinguish genuinely distinct solution paths. To address this, we introduce Answer Probing, which probes the potential answer an LLM would reach from an intermediate reasoning path. We demonstrate that the hidden states of probed answers more effectively differentiate distinct solution paths than semantic embeddings, and the perplexity of probed answers serves as a practical proxy for reasoning correctness. Based on these findings, we propose Answer Probing-Guided Tree Search (APTS), which guides the tree search by the probed answers' hidden state similarity and perplexity. Experiments on three reasoning tasks across two LLMs show that APTS consistently enhances solution diversity, demonstrating its effectiveness and robustness.

Most shape reconstruction methods assume measurements defined over planar sensing domains, such as RGB images or depth maps. In this paper, we use a curved capacitive textile as a shape sensor, treating its surface as a non-planar sensing manifold. Each scan is represented as a capacitive proximity field on this manifold, induced by the interaction between the curved electrode layout and nearby object geometry. We introduce a multi-view feedforward reconstruction model that aggregates these fields across known sensor views and recovers the observed object shape. Simulated and physical experiments demonstrate robust reconstruction from capacitive proximity signals acquired on curved sensing surfaces, pointing toward a new route to robotic near-field geometric awareness via embodied sensing.