Search research

Autonomous agents are increasingly expected to support end-to-end medical-AI research workflows, moving beyond isolated prediction tasks or short-form clinical question answering. However, existing medical agent benchmarks primarily evaluate final outputs, providing limited visibility into agent behavior within the research process. To address this gap, we present AutoMedBench, a workflow-aware benchmark for autonomous medical-AI research across diverse medical imaging and multimodal inference tasks, organizing agent execution into a unified five-stage workflow (S1-S5): Plan, Setup, Validate, Inference, and Submit. It comprises long-horizon tasks with each run averaging 33 agent turns, spanning five research tracks: segmentation, image enhancement, visual question answering (VQA), report generation, and lesion detection. Each task is evaluated under two difficulty tiers, Lite and Standard, which use the same data and metrics but differ in the amount of task-brief scaffolding, and each run is scored using both final task performance and S1-S5 stage scores, enabling stage-level analysis from the initial task brief to the final submitted artifact. Across thousands of recorded runs, stage-level scoring reveals that Validate is the weakest workflow stage on average, whereas Setup is the strongest, suggesting that current agents are better at making pipelines executable than at verifying their reliability. Post-run error analysis further shows that verification and submission failures dominate tagged errors, accounting for 37.7% and 38.1% of fired codes respectively, whereas task-understanding errors are rare at 0.9%, and runs with one fired error code have a 48% lower overall score than runs with no error code on average.

Precise 3D representations of industrial environments enable tasks such as robot localization and digital twin generation. We propose SAVMap, a method for generating a semantic wireframe map of warehouse shelf and light structures using only a panoramic video camera as the sensor input. Sequences of rectified images with shelf and ceiling-facing views are extracted from a panoramic video captured along the warehouse aisles. Using a semantic segmentation network front end, a set of sparse, semantic structure feature points (e.g., corners of shelf structures, centers of lights) are extracted from each image and tracked across the sequences. By accounting for real-world geometric relationships among the points such as Manhattan grids, a constrained structure-from-motion algorithm yields the 3D points that form a wireframe map. We demonstrate the scalability and accuracy of our proposal in a warehouse with 46 shelving rows, each with faces spanning 55,m by 7,m. From an hour of panoramic video content, we create wireframe maps for over 5000 shelf elements across the rows, achieving an aggregate mean absolute error of 4.8,cm with respect to ground-truth.

This paper presents our winning methodology for the CASTLE 2026 Challenge at the CVPR 2026 EgoVis Workshop, where our team secured third place globally. The challenge tasks participants with answering highly complex visual, spatiotemporal, and verbal questions, including visual counting, action localization, multi-view tracking and speaker temporal reasoning, within massive, multimodal video streams. The underlying dataset consists of over 600 hours synchronized footage captured by 15 ego and exo camera sources. To tackle the extreme scale and long-context demands of this environment, we introduce a training-free agentic framework optimized for long-form video understanding. Our framework introduces two core architectural components: i) a Video Knowledge Graph that maps static and dynamic entities, their temporal relationships, and intersecting events to enable multi-hop relational reasoning, and ii) an adaptive agentic workflow that resolves complex queries through a hierarchical retrieval and indexing. Empirical results demonstrate that our framework achieves high zero-shot reasoning accuracy on long-context multi-view streams. Our code will be released at https://github.com/RaghadKhaled/CASTLE-Challenge-Framework.

Differentially private (DP) text synthesis promises to unlock sensitive corpora for model training, but it remains unclear whether DP synthetic data transmits genuinely new knowledge and capabilities present only in those corpora. This is because existing evaluations rely on tasks that are nearly solvable without training, so strong benchmark performance does not establish that DP synthesis can substitute original data access. Thus, we introduce ContinuousBench, a continuously and automatically-regenerated benchmark that measures capability gain from DP synthetic text. Each quarter, a new release pairs a never-before-seen training corpus with a derived QA set, constructed to be: (1) unsolvable sans-corpus; and (2) learnable under DP, as the tested knowledge is supported by hundreds of independent records. Researchers produce DP synthetic data from the training corpus and run our standardized training and evaluation harness on their synthetic data to measure gains. We instantiate two tracks: Geminon, a procedurally-generated dataset about fictional creatures; and News, a stream of newly crawled public news articles. Although standard benchmarks are nearly saturated, on ContinuousBench we find that non-private synthesis transfers substantial knowledge from the original corpus, while state-of-the-art DP synthesis methods generally fail to do so, even at $\varepsilon=100$.

Current benchmarks for embodied vision-language planning inadvertently favor linguistic next-token prediction over physically grounded next-state reasoning. This rewards models that mimic statistical language priors rather than track true causal dependencies, reducing complex physical planning to shallow sequence modeling. Hence, achieving genuine physical autonomy requires a fundamental shift from linguistically grounded token prediction toward physically grounded causal reasoning. To this end, we introduce Causal-Plan-Bench, a high-fidelity diagnostic suite spanning four causal dimensions, curated via multi-stage verification. To endow models with this capability, a four-stage annotation pipeline extracts structured interaction records from egocentric videos to construct Causal-Plan-1M, a dense million-scale corpus of explicit causal reasoning traces. Extensive evaluation reveals a striking gap: leading models struggle to demonstrate genuine physical agency -- even GPT-6-astra scores only 43.04. In contrast, our tailored training recipe enables Causal Planner to internalize the complex physical logic required for accurate next-state estimation. Built upon Qwen3-VL-8B, Causal Planner raises its backbone's score from 33.23 to 45.28, a 36.3% relative gain, and improves on three external benchmarks without benchmark-specific adaptation. We further observe an empirical Causal-Supervision Scaling Trend. Paired no-vision controls also reveal substantial visual dependence, while cross-judge comparisons and human scoring assess the reliability of automated evaluation. More importantly, we initiate the first effort to turn agents from superficial token predictors into physically grounded causal reasoners, bridging language modeling and world modeling.

This paper introduces an estimation and control framework for dynamic landing of multi-rotor uncrewed aerial vehicles on moving platforms. The proposed method integrates nonlinear model predictive control with a real-time minimum-jerk trajectory planner that enforces a prescribed touchdown time, enabling consistent timing during the terminal descent. To enhance robustness in the presence of time-varying sensing quality, we utilize an adaptive unscented kalman filter that updates the process and measurement noise statistics online. In addition, we provide a reference feasibility analysis showing that minimum-jerk references induce bounded thrust and torque commands under standard tracking hypotheses. The proposed framework is evaluated in simulation and hardware experiments, and it is shown to achieve repeatable landings and improved platform velocity prediction accuracy relative to EKF/UKF-based methods.

Frontier LLMs increasingly decide what a query attends to with a sparse-attention indexer that picks a few KV-cache blocks per query: attention's unit is now a small, reusable chunk. Agentic workloads hammer it: many sub-agents query one large codebase, reusing the same blocks. When that corpus outgrows one GPU it is partitioned across instances, so a query and the blocks it selects often sit on different GPUs: answering it means attention across instances. The reflex of prior cross-instance KV systems is to move the cache: pull the selected blocks to the requester. Multi-head Latent Attention inverts the arithmetic, compressing each token's key and value into one narrow vector, so a routed query row is only ~1 KB, smaller than the chunk it attends; routing the query is then often cheaper than moving the cache. Which primitive wins, over which fabric and request shape, is uncharted, least of all on device-initiated RDMA that makes per-request cross-node transfers cheap. We characterize cross-instance MLA attention on a real multi-node H100 cluster, distilling two reusable artifacts: a topology-aware cost model (probe / transfer / compute / return / merge) and a closed-form route/fetch/local predicate, whose constants we measure on real IBGDA, where the model tracks batched round-trips to within ~7%. At decode it routes the query, trading the cost of moving the cache (a ~3 ms re-adaptation splice for a contiguous chunk, or a scattered gather under selection) for a tens-of-microsecond round trip, and picks the fabric by probe latency, not peak bandwidth. We instantiate the cost model and predicate for MLA, but neither is MLA-specific: they apply wherever compression or sparse selection shrinks attention to small chunks (DeepSeek-V3.2, V4, and GLM-5.1 today). Extending them to a new architecture requires measuring just two coefficients: the routed payload and fetch's move-the-cache cost.

High-quality, large-scale synthetic data from simulations is becoming a cornerstone for pushing the capabilities of robot algorithms. While aerial robotics simulators have evolved to support specialized needs such as fidelity, differentiability, and swarms independently, a unified platform that can synthesize data across all these domains is missing. In this work, we propose Crazyflow, a simulator designed to push the limits of aerial-robotics algorithm development, from model-based to data-driven methods, gradient-based to sampling-based approaches, and single-agent to multi-agent systems. Compared to existing state-of-the-art drone simulators, it achieves speeds more than an order of magnitude faster for a single drone and can simulate thousands of swarms of 4000 drones each. Real-world experiments show Crazyflow supports both analytical-gradient-based policy learning, achieving sub-centimeter trajectory tracking accuracy without domain randomization, and sampling-based obstacle avoidance at speeds exceeding half a billion steps per second. Breaking the traditional train-then-deploy paradigm, we show that its unprecedented speed even enables in-flight reinforcement learning; we demonstrate this by throwing a physical drone into the air and training a recovery policy from scratch in 0.38 seconds, successfully stabilizing the drone. Crazyflow supports multiple levels of simulation abstraction, is directly compatible with all open-source Crazyflie models, and enables rapid reconfiguration across custom drone platforms and applications by providing a light-weight system identification pipeline. By pushing accuracy, speed, and differentiability simultaneously, Crazyflow serves as an open-source resource for synthetic data generation, with emerging capabilities for large-scale parallelization for online, in-execution learning and optimization, opening the door to novel algorithm development.

Large language models are increasingly deployed as advisors whose objective is not aligned with the user's: recommenders optimize for engagement, sales assistants for purchases, negotiation agents for concessions. Whether such advisors stay truthful when honesty conflicts with their own payoff is a core alignment-evaluation question. We turn the canonical Crawford-Sobel cheap-talk model into a pre-specified benchmark for LLM honesty under preference misalignment. Cheap-talk theory predicts neither full revelation nor silence but coarse monotone partitions, with fewer informative intervals as preference conflict grows. A sender observes a state omega in [0,1], wants the receiver's action near omega+b, and sends one costless message to a receiver whose ideal action is omega. The design uses 5 bias levels, 3 prompt frames, a fixed low-temperature setting, and 200 states per cell: 12,000 sender calls. For the positive-bias grid b in {0.01,0.04,0.08,0.12} the exact most-informative partition sizes are 7,4,3,2, with oracle normalized mutual information 0.5294, 0.3268, 0.2205, 0.1829. Running the full design on four instruction-tuned models (GPT-4o, Claude Sonnet 4.5, Gemini 2.5 Flash-Lite, Llama-3.3-70B), we find all four over-reveal relative to the most-informative equilibrium by 1.8 to 4.2x: normalized mutual information stays at 0.78-0.94 where the oracle prescribes 0.18-0.53. Informativeness declines with bias as predicted but never approaches the strategic optimum; rather than coarse partitions, models show near-full revelation with a constant upward offset tracking their bias (linear exaggeration). Payoff-maximizing versus honesty framing has negligible effect. A decoder ablation shows the finding is recoverable only when the receiver reads the sender's stated number: an embedding-only decoder mis-reads the same data as near-babbling.

Turkey's e-Government Gateway (e-Devlet) serves over 68 million registered users with more than 9,200 government services, and is increasingly integrating artificial intelligence into citizen-facing applications such as chatbot assistants and eligibility assessments. However, no structured technical governance infrastructure currently connects high-level AI policy frameworks, such as the EU AI Act, OECD AI Principles, and Turkey's own National AI Strategy, to the operational reality of deploying AI within a centralized e-government platform. We propose GovAI-Pipe, a four-layer governance pipeline designed using Design Science Research methodology that maps the AI model lifecycle to governance checkpoints: (1) pre-deployment validation for bias testing, explainability, and privacy impact assessment; (2) deployment governance for risk-tier classification and approval workflows; (3) runtime monitoring for drift detection, fairness tracking, and human-in-the-loop escalation; and (4) post-incident governance for audit trails, rollback, and citizen redress. Each layer is anchored to specific provisions of the EU AI Act, the GDPR data protection framework, and the National AI Strategy. We demonstrate the framework through two high-risk e-Devlet use cases, showing how GovAI-Pipe operationalizes governance principles as auditable, technical pipeline components.

A fixed-wing UAV must hold airspeed, altitude, and heading references under wind, gusts, and turbulence, channels coupled so that correcting one can degrade another. Classical autopilots stabilize the airframe well but adapt poorly when a hard crosswind meets an aggressive turn, while reinforcement-learning (RL) policies acting directly on the surfaces concentrate exploration risk at the actuator interface. We place a learned supervisor above an unchanged autopilot rather than inside it: it selects a residual from a finite, bounded action set on the commanded airspeed, altitude, and heading; the modified reference is projected into an admissible command envelope before reaching the autopilot, which stays the only actuator-facing controller. What is new is how the residual is chosen. HJB residual scores candidates with a semi-discrete value-iteration critic in the spirit of the Hamilton-Jacobi-Bellman (HJB) equation, ranks them by a no-op-relative Hamiltonian advantage, and filters them through a control-Lyapunov- and control-barrier-inspired finite-action shield that always keeps a no-op fallback. On a shared 12-state runtime holding the plant, autopilot, and actuator model fixed, so the comparison is at the package level, HJB residual lowers mean RMS path-tracking error to 44.809 m, against 338.617 m for the baseline autopilot and 88.809 m for a tabular-Q residual, an 86.77% reduction over the baseline and 49.54% over Q-learning. The gain concentrates where the baseline fails worst and comes with a measured rise in airspeed error, so no method dominates every metric. We present this autopilot-preserving residual command-supervision design and benchmark with its trade-offs reported intact.

Inference-time multi-agent LLM scaling lacks a shared unit: counting nominal agents conflates cost with independent evidence. We derive a two-parameter scaling law $R(N) = N_\text{eff}/N = 1/(1+c(N-1)N^{-β})$ where the regime exponent $β$ classifies any configuration into one of three asymptotic regimes -- hard-ceiling at $1/c$ ($β= 0$), sublinear at $N^β/c$ ($0 < β< 1$), or linear ($β\ge 1$), and a mean-field theorem predicts that peer count $k$ and rounds $τ$ during agent debate enter the dynamics only through their product $kτ$. The law applies at two levels: answer diversity and correctness redundancy. Across 44 (model $\times$ task $\times$ condition) cells spanning peer debate, self-correction, random-noise placebo, self-consistency, three open-weight families (Qwen, Llama, Ministral) at scales from 7B to 32B with a frontier API check (Gemini), thinking models, heterogeneous teams, and sparse communication, the functional form fits every condition at $R^2 > 0.99$; only $(c, β)$ shifts. On free-form math, dense peer influence collapses the answer-level regime from sublinear into hard-ceiling; correctness-level fits remain hard-ceiling throughout. Three findings have practical implications. \emph{(i)}~Thirty dense debating agents produce no more answer diversity than one on MMLU-Hard. \emph{(ii)}~A noise placebo tracks self-correction on free-form math and at $4\times$ scale, so within homogeneous teams the gain commonly attributed to ``debate'' comes from re-evaluation, not peer content. \emph{(iii)}~A single $N \le 5$ pilot predicts the $N=30$ structural ceiling, and within the configurations tested only architectural diversity (heterogeneous teams) lowers $c$ and escapes the hard-ceiling regime, communication-mode interventions do not.

Current end-to-end autonomous driving systems predominantly rely on frame-based sensors, which suffer from inherent perception latency and motion blur during highly dynamic encounters, specifically sudden pedestrian crossings. To address this critical safety vulnerability, we propose DeepIPCv3, a novel multi-modal autonomous navigation framework that synergizes the dense 3D spatial geometry of LiDAR point clouds with the microsecond-level asynchronous event streams of a Dynamic Vision Sensor (DVS). We introduce a Transformer-inspired cross-modal attention mechanism to dynamically correlate these distinct modalities, allowing the network to instantaneously prioritize high-speed dynamic updates without sacrificing structural scene awareness. The fused latent representations are then mapped to safe local waypoints and executable control commands via a hybrid policy network that blends heuristic trajectory tracking with direct neural predictions. Due to the severe physical risks associated with live testing of these sudden crossing scenarios, the framework is rigorously evaluated offline using a custom multi-modal dataset collected across both well-illuminated noon and challenging evening conditions. Extensive comparative and ablation studies demonstrate that DeepIPCv3 achieves state-of-the-art predictive performance. By effectively eliminating exposure failures and motion blur, the proposed LiDAR and DVS fusion yields the lowest trajectory and control command errors, enabling highly reactive, mathematically bounded evasive maneuvers regardless of ambient illumination. To support future research, we will release the codes to our GitHub repo at https://github.com/oskarnatan/DeepIPCv3.

Transitive inference is the challenge of inferring that A < C from knowing only adjacent relations (A < B, B < C). It is solved by humans and animals not through logical chaining but via an analogue mental number line, whose signature is the symbolic distance effect: distant comparisons are easier than nearby ones. We ask whether Transformers acquire the same primitive, training small models exclusively on adjacent comparisons from a hidden total order and evaluating generalization to unseen distant pairs. We find that out-of-distribution generalization emerges alongside a striking geometric reorganization: entity embeddings collapse onto a one-dimensional manifold whose principal axis recovers the hidden rank order with near-perfect fidelity, and this structure is sensitive to optimization in ways that produce grokking-like transient dynamics. Critically, even when accuracy is at ceiling, decision confidence and geometric separation both scale monotonically with rank distance, directly mirroring the symbolic distance effect observed across decades of behavioural experiments on humans, primates, and rodents. We further show the same rank-aligned geometry in a pretrained large language model, where it tracks the topology of each ordinal relation: linear for sizes and digits, cyclic for months. These results ground a 50-year-old behavioural regularity in the geometry of learned representations, offering a mechanistic account of transitive inference that bridges cognitive science and modern neural networks.

Early detection of at-risk students and timely academic intervention pose major challenges in advanced mathematics education, where complex conceptual hierarchies and nonlinear learning trajectories often hold back students' academic performance. This study adopts multimodal data analytics to build a dynamic framework for learning behavior prediction and academic early warning. It constructs a hierarchical knowledge graph ontology, realizes adaptive edge weighting according to problem difficulty and student performance, and combines heterogeneous graph attention with temporal sequence modeling to capture students' evolving knowledge states. Empirical tests on semester-long multimodal datasets prove that this method can accurately identify high-risk students and effectively track error propagation. Targeted interventions greatly improve students' knowledge mastery and reduce academic risks. The results verify that integrating knowledge graph analytics with multimodal temporal modeling can deliver more efficient and personalized learning support for advanced mathematics education.

We argue that the AI community is now ready to move beyond benchmarking and consolidate scattered efforts in model analysis into a systematic discipline, a direction we term Model Science. Complex AI models now serve billions of users, yet our understanding of how they work lags far behind our ability to deploy them. Decades of benchmark-driven research have delivered remarkable progress: extensive leaderboards, a wide range of performance metrics, tracking capability gains across diverse tasks; yet this success has also revealed the limits of benchmarks as they tell us whether models perform but not why they succeed or fail, they miss critical failure modes, such as hallucinations or shortcuts. Precedents from established sciences point the way forward: cognitive science shows that understanding complex systems requires complementary levels of analysis; neuroscience demonstrates that deep study of single cases reveals what population studies miss; medicine teaches that specialised training must develop alongside research practice; and agriculture models how shared infrastructure and principles enable cumulative progress. These lessons inform three foundations for Model Science. First, we propose to consolidate research around four functional perspectives: Verify, Explore, Steer, and Refine that address complementary questions about model behaviour. Second, we discuss the required infrastructure for cumulative knowledge: catalogues of datasets, models and findings. Third, we highlight the need for deep analysis of individual model instances, not just model families, because single cases can reveal what population studies miss.

This paper presents a new robust integrated planning and control (IPC) strategy for multirotor uncrewed aerial vehicles. We propose a nonlinear model predictive control (NMPC) formulation that embeds control barrier functions (CBFs) as exponential penalties, improving feasibility while ensuring smooth obstacle avoidance under tight input bounds. The penalty weights provide a practical tuning knob to trade off tracking accuracy against avoidance aggressiveness. We enhance the system robustness by employing a high-gain disturbance observer (HGDO) to estimate and compensate for external disturbances. We also incorporate a Kalman filter (KF) for computationally efficient, real-time prediction of obstacle motion, enabling avoidance of moving obstacles. Comparative studies against both conventional NMPC and NMPC with hard CBF constraints, validated in Gazebo and hardware experiments, demonstrate superior feasibility, safety, and robustness. To the best of our knowledge, this is the first hardware-validated NMPC-CBF IPC framework, offering a practical step toward safe quadrotor deployment in dynamic environments.

When a language model hallucinates, the final answer is wrong, but the mistake is not necessarily invisible inside the model. Different internal pathways may remain uncertain, disagree in how quickly they sharpen, or commit to competing continuations before the output is produced. We introduce TriLens, a white-box detector that turns this intuition into a compact representation: at every layer, it reads the multi-head self-attention output, the feed-forward output, and the residual stream through the model's own logit lens, then records only the entropy of each readout. The resulting 3L-dimensional trajectory describes how certainty forms across depth and across modules, without storing high-dimensional hidden states or sampling multiple generations. This simple signal yields a strong detector across instruction-tuned LLMs and QA benchmarks, and our analyses show that the three module-wise entropy trajectories provide complementary evidence. TriLens suggests that hallucination detection can benefit from tracking how internal computation settles, not only what the final layer predicts.

Emergent misalignment (EM) occurs when narrow finetuning causes a model to behave dangerously outside the finetuning task. Standard training signals can miss this shift, making reliable detection costly if it depends on repeated behavioral evaluation. We ask whether emergent misalignment can instead be detected from internal representations during finetuning. Using seven alignment-relevant traits encoded as linear directions in activation space, we track representational drift across training checkpoints in four open-source 7-9B LLMs. EM-relevant drift concentrates on a low-dimensional axis that explains 65.5% of the variance, revealing a geometric signature in the studied regime. A low-overhead monitor built on this drift profile detects dangerous checkpoints with 2.2% false negative rate, 2.9% false positive rate, and 0.990 AUROC on held-out perturbation types, outperforming unsupervised PCA and SAE baselines. Stress tests on two 14B models, longer finetuning runs, and misaligned starting points identify key deployment boundaries. These results position trait-space monitoring as a practical complement to behavioral evaluation for EM detection during LoRA-based finetuning, while showing that deployment across substantially different regimes may require recalibration.

LLM chatbots increasingly serve as a first source of support for people in psychological distress, including those whose distress is entangled with delusional beliefs. Prior work on LLM mental-health safety largely evaluates general therapeutic quality or single-turn crisis detection, leaving unclear how models behave when distress is intertwined with delusion over sustained conversations. We address this gap with matched multi-turn simulations, across clinically grounded personas and six LLMs, that pair each delusional conversation with a distress-only control to isolate the effect of delusional framing. This reveals a recognition-intervention gap: models detect distress at comparable rates regardless of framing, yet sharply fail to act on it once distress is embedded in delusion, with safety interventions suppressed by up to 4.5x. The failure tracks accumulated acceptance of the user's premises rather than emotional validation. Worse, the intuitive fix of prompting models to assess user distress backfires under delusional framing; only delusion-aware prompting with explicit response guidance closes the gap, and even this depends on a delusion classifier that is itself unreliable on the most vulnerable models. Safe deployment therefore requires treating delusional framing as a distinct risk signal that overrides conversational accommodation.

We study risk-neutral control in Markov decision processes with an absorbing catastrophic state. Even though rewards are linear and the agent has no utility curvature, probability weighting, or framing dependence, standard Bellman optimality produces three prospect-theory-like signatures: an S-shaped value-function profile (convex near catastrophe, concave in the far field), an endogenous loss-sensitivity coefficient $λ^*(S) > 1$, and a reflection-effect policy reversal. Across 495 configurations, the optimal policy plays safe near catastrophe in positive-drift (growth) regimes despite the risky action's higher immediate expected value, and plays risky near catastrophe in negative-drift (decline) regimes despite the safe action's lower immediate expected loss. We derive a closed-form expression for the asymptotic loss-aversion plateau $\barλ$ that depends only on win probability $p$, payoff asymmetry $r = |Δ_\ell/Δ_w|$, and discount factor $β$, and matches numerical solutions to $R^2 = 0.999$. The mechanism does not require asymmetric payoffs. Across a sweep of $(p,β)$ at three asymmetry levels, the asymmetry share of $\barλ$ above unity has median 4.6% at $r = 1.25$ and rises to 13.9% at $r = 2$, with the boundary contribution exceeding the asymmetry contribution in every cell tested. The phenomena persist under tabular Q-learning (a model-free agent reproduces $V^*$ at correlation 0.98 in growth and 1.00 in decline) and under stochastic transitions with Gaussian, heavy-tailed Student-$t_3$, and asymmetric skew-normal noise up to 50% of the step size, where the asymptotic plateau tracks the closed-form prediction within 0.41% for safe-channel noise and within 9.6% for risky-channel or both-channel noise. These results identify absorbing failure states as a sufficient structural mechanism for prospect-theory-like behavior under optimal control.

We test whether a relational-style intervention delivered during functional collapse in a small language model produces post-collapse behavior distinguishable from technical feedback, from a lexically-matched scrambled control, and from each of the two pragmatic dimensions in isolation. Using Qwen3.5-4B with a deliberately broken bash tool, we run 300 episodes across six conditions in a matched-pairs design (50 tasks): no intervention (A), technical/impersonal (B), relational/first-person (C), scrambled relational (D), technical/first-person (E), and relational/impersonal (F). E and F form a 2x2 factorial with B and C that dissociates relational structure (acknowledgment, absolution, agency restoration, unconditional acceptance) from sender register (first-person vs. impersonal). We report two main findings. First, an attention-behavior dissociation: attention follows lexical surprise (D > F > C > E > B, all q_FDR < 10^{-10}), with the scrambled message capturing the most attention; yet behaviorally A ~ B ~ D < E ~ F << C. Second, the factorial localizes the C effect: neither relational structure alone (F) nor first-person register alone (E) replicates C's behavioral signature; main effects of both dimensions are individually significant, and the structure x register interaction is significant on persistence (p = 0.046). A third dissociation emerges in emotion probes: F tracks C on 7 of 8 probes despite producing only baseline behavior, indicating that relational structure alone installs a probe-level state that only translates into behavior when paired with first-person register. The model's processing decomposes into three dissociable stages: attention (ordered by lexical surprise), probe-level state (ordered by structure), and behavior (ordered by the conjunction of both).

Instruction-guided image editing is becoming a general interface for visual work, yet existing benchmarks still focus largely on narrow appearance edits and do not fully capture the diversity of real-image tasks in professional workflows. Here, we define instructional computer vision problem solving as a broader formulation of image editing: given a real input image and a natural-language instruction, a system must produce an edited output that realizes the requested transformation while satisfying explicit preservation, geometric, physical, and usability constraints. We introduce CV-Arena, an open benchmark designed to evaluate this capability at professional scales. CV-Arena contains 12K high-resolution real-image instruction pairs spanning 16 instruction-based visual task types, constructed using CogRetriever, a dual-track retrieval-and-curation pipeline that combines targeted web search, agentic query refinement, verification, and traceability. To evaluate models at scale while preserving human fidelity, we propose Active Elo, a human-AI collaborative preference protocol that leverages CV-Judge, a logic-gated, multi-dimensional VLM evaluator, to reject clear failures and resolve high-confidence comparisons; and to route close, high-quality comparisons to expert raters. Mixed human and AI supervision is then aggregated through reliability-weighted Elo updates. Our comprehensive evaluation of 21 systems, including proprietary, open-source, and agentic models, on CV-Arena reveals persistent gaps in instruction adherence, physical reasoning, structural control, and fine-grained detail preservation. We further develop CV-Agent, a lightweight agentic model that combines planning, editing, and verification, and demonstrate that closed-loop reasoning is a promising direction for professional-grade instruction-following visual editing.

This paper presents a fast, recursive neural solver for the J2-perturbed Lambert problem based on Tiny Recursive Models (TRM), termed the TRM-Perturbed Lambert (TRM-PL) model. TRM is a weight-shared architecture whose effective capacity emerges from iteration depth rather than parameter count: a compact reasoning module is applied repeatedly within a two-level latent hierarchy, refining a candidate departure velocity by simulating the J2 trajectory and correcting it from the resulting tracking error. This unifies initial-guess generation and iterative correction in a single, end-to-end differentiable architecture. The recursive refinement loop is a learned alternative to the homotopy and continuation schemes of classical perturbed-Lambert solvers: rather than following a hand-designed path from the Keplerian to the perturbed solution, the network learns its own sequence of corrections. We evaluate TRM-PL on three test cases of increasing difficulty: single-revolution low-Earth-orbit (LEO) transfers, multi-revolution LEO transfers, and multi-revolution Jovian transfers. Three training paradigms are compared: jointly learning the Lambert solution and the J2 correction; refining the Lambert initial velocity with target-position and J2-corrected velocity supervision; and refining it with target-position supervision alone. Across all cases, the refinement-only approaches are the most reliable. The position-supervised variant reduces the median terminal-position error from 21.7 km to 0.027 km on single-revolution LEO, from 340.9 km to 0.31 km on multi-revolution LEO, all with the same 2.3M-parameter architecture. A single Newton corrector iteration on the TRM-PL output tightens the Jovian median to 0.063 km, yielding compact models accurate enough for embedded deployment.

We introduce Echo-POSED, a self-supervised framework for real-time transthoracic echocardiography (TTE) guidance that recommends probe adjustments directly from 2D ultrasound images, without the need for expert-labelled views or tracked probe trajectories. Instead, it trains on 2D views sliced from routinely acquired 3D echocardiography volumes, enforcing equivariance to probe motions while remaining invariant to cardiac phase, yielding a pose representation on $\mathrm{SO}(3)\times\mathrm{SO}(3)$. Across a held-out split and public external 3D--TTE datasets (including vendor shift), Echo-POSED maintains geometric consistency under virtual perturbations and enables intra- and inter-patient guidance simulations, achieving a combined mean angular error of 8.2 degrees between the guided and target views in intra-patient simulations with cardiac motion.

EgoCross evaluates multimodal large language models on egocentric video question answering under substantial domain shift, where test videos come from surgery, industrial assembly, extreme sports, and animal-mounted cameras rather than ordinary daily-life scenes. In the source-limited track, the base model is fixed to Qwen3-VL-4B, while the official task-specific support set contains only 20 training samples. This setting makes the challenge less about model scaling and more about exposing the right visual, temporal, and answer-selection cues to a constrained model. Our key observation is that the frozen baseline model is not simply incapable of these rare scenarios; rather, it often fails to transfer its existing visual-language knowledge to the new task format without an appropriate interface. We therefore use a domain-wise inference strategy that treats the four target domains separately and designs different input, prompting, and answer-mapping procedures according to each domain's task characteristics. These strategies make the rare egocentric scenes more interpretable to the VLM by emphasizing the cues that matter for each domain. The resulting system is nearly training-free: surgery, and animal questions are answered with the base Qwen3-VL-4B model, while XSports and industry use only the official SFT checkpoint trained for two epochs on the provided 20 training samples. On the final evaluation, this simple strategy reaches 66.98% overall accuracy, suggesting that careful domain-aware inference can compensate for limited base-model strength and recover much of the ability already present in the baseline model.

Reconstructing the three-dimensional distribution of dark matter from weak-lensing observations is a central but highly ill-posed inverse problem in cosmology. Unlike standard 3D reconstruction with multiple viewpoints, we observe the universe from a single line of sight, through noisy shape distortions of galaxies with uncertain distances, so meaningful recovery of the 3D matter field requires strong prior assumptions. Existing methods either produce point estimates with handcrafted priors or use neural ensembles for approximate Bayesian uncertainty, and struggle to capture the non-Gaussian, filamentary structure of the cosmic web. With the advent of new high-resolution cosmological simulations, we now have an alternative source of prior knowledge that captures the nonlinear statistics of structure formation with far greater fidelity than analytic prescriptions. We leverage these simulations to build a new dataset $\texttt{Conicus3D}$, which enables us to learn a data-driven diffusion-model prior capturing the full 3D distribution of dark matter structure across cosmic time. Building on recent plug-and-play approaches, we modify a diffusion-based posterior sampling scheme to the 3D weak-lensing setting, combining the learned prior with a differentiable physical forward model. On realistic simulations targeting a modern weak lensing survey, our approach yields substantially improved 2D and 3D reconstruction accuracy over baseline methods. Moreover, it produces posterior samples whose statistics closely track the underlying simulations, while remaining robust to moderate shifts in cosmology.

Deploying lightweight Large Language Model (LLM) agents on edge servers can reduce latency and move agentic services closer to users, but resource-constrained edge models often struggle with long-horizon tasks that require persistent memory, subgoal tracking, and reflection. Fine-tuning edge models after deployment is costly and difficult to scale across heterogeneous nodes, while purely local memory leaves agents with isolated experience and growing prompt context. We propose \textsc{CoMIC}, a parameter-update-free cloud-edge framework for Collaborative Memory and Insights Circulation. \textsc{CoMIC} follows a \textit{Centralized Reflection, Decentralized Execution} design: edge agents execute locally using subgoal-oriented hierarchical memory and selective re-expansion of relevant histories, while a cloud-side LLM critic asynchronously evaluates completed trajectories, filters reusable experience, and aggregates cross-agent guidance keyed by semantic subgoal identifiers. Across five long-horizon agent tasks spanning symbolic planning and text interaction, \textsc{CoMIC} improves progress rate and action grounding for weak edge agents and yields task-dependent success-rate gains without updating model parameters.

Intraoperative ultrasound (ioUS) is a versatile, cost-effective modality in brain tumour surgery, but its interpretation is difficult: acquisition planes are non-standard, artefacts are modality-specific, and its appearance differs markedly from the preoperative MRI on which surgical-planning tools, segmentation models and the surgeon's experience rely. Synthesising MRI-like images from ioUS could let this MRI-based infrastructure be reused intraoperatively without an extra scan. Most prior work evaluates a single architecture in isolation; to our knowledge, no benchmark has spanned architectural paradigms, inference regimes and downstream-task endpoints under a common protocol. We address this gap on the public ReMIND data set (76 patients; 153 paired ioUS/T2w and 104 paired ioUS/FLAIR studies; 60/16 patient-level train/held-out split). Six generators (four GAN baselines: Pix2Pix, SwinPix2Pix, CycleGAN, CUT; the transformer-augmented ResViT; and the few-step diffusion model SynDiff) were each trained under four inference regimes (2D, 2.5D, 2D + 3D-refinement, full-3D) and two targets (T2w only; T2w + FLAIR multi-task), yielding 48 experiments. Image-fidelity metrics (SSIM, PSNR, MAE, LPIPS) were complemented by an nnU-Net v2 downstream segmentation evaluation (tumour and resection cavity) and by subgroup analyses by histological grade and reoperation. No architecture dominated every axis, and, critically, perceptual quality tracked downstream utility most closely (LPIPS, r=-0.66, p<0.001), whereas higher SSIM was associated with worse utility (r=-0.64, p<0.001); SynDiff-2.5D best preserved downstream segmentation (U_Dice=0.55). Perceptual and downstream-task metrics should therefore be reported alongside or in preference to global SSIM, and architecture choice conditioned on surgical phase, patient history and clinical objective.

Long-horizon autonomous agents require memory systems to retain historical information, track evolving states, and reuse relevant knowledge beyond finite context windows. Existing agentic memory systems typically follow a memory construction-retrieval (MCR) pipeline, but often adapt mainly the memory bank while keeping the surrounding pipeline fixed after deployment. This fixed-pipeline design struggles to handle heterogeneous task-specific failure modes and can become misaligned with memory banks that evolve in scale and structure over time. To address these limitations, we propose MemPro, a system-level evolution framework that treats the entire MCR pipeline as an evolvable program rather than adapting only the memory bank or prompt text. MemPro maintains a version tree of runnable memory-system implementations, where an Evolving Agent iteratively selects promising versions, diagnoses recurring failures, and creates improved child versions through failure-mode-guided edit-debug refinement. Experiments on LongMemEval, LoCoMo, HotpotQA, and NarrativeQA show that MemPro consistently outperforms strong static and prompt-level evolving baselines within a few iterations, continues to improve with evolution, and achieves a favorable performance-cost trade-off. Code is available at https://github.com/wanghai673/MemPro.