Interpretations have been widely used in the study of provenance of queries on semiring-annotated databases. Here, we consider two different interpretation-based semantics for first-order formulas in negation normal form, namely, the canonical-interpretation semantics and the compatible-interpretation semantics. We show that the resulting query languages cannot express the monus operation on semiring-annotated relations, when the annotations come from the bag semiring or the tropical semiring or the fuzzy semiring. Consequently, the semantics of SQL cannot be captured using the interpretation-based semantics considered here.
ML code should run where researchers choose, not where it was first written. Today, machine learning code mainly lives in two ecosystems, PyTorch on NVIDIA GPUs and JAX on Google TPUs. Migrating repositories between them means building and testing across frameworks and hardware. This migration is (1) a practical need, since it unlocks different hardware for researchers, and (2) a natural benchmark: it involves different frameworks and hardware, covers whole repositories, and is long-horizon and challenging. We introduce XStack, a benchmark that evaluates agents on migrating ML repositories between these two ecosystems. Each agent receives a PyTorch repository and a clean TPU machine and must deliver a JAX repository. Its output passes if it meets our grading criteria, based on the source repository's published result, authenticated and calibrated by us. Migration by agents remains unreliable: Claude Opus 5 passes 75%, GPT-5.6-sol 45%, and every other agent at most 40%. XStack is a step toward freeing ML code from its ecosystem. We release XStack to make progress toward reliable migration across frameworks and hardware measurable.
Interpretability, AI auditing and assessments of machine consciousness increasingly rest on mechanism-level quantities: functionals of a system's causal transition law that describe how it computes, not what it outputs. Experiments see that law only through finite, partial and noisy interventions. We ask when such a quantity is identifiable from an experiment's access, continuous in the mechanism and certifiable from finite data, and answer exactly for a deliberately demanding case - the integrated information $\varphi$ of integrated information theory - in stochastic networks of four and five units with known ground truth. Behavior can be silent: a recurrent and a feed-forward network with identical input-output laws at their response delay carry 0.28 and 0 bits, yet internal recordings separate them within 4-53 trials. Partial access can be just as blind: in our examples, units left out of a one-step recording impose precision floors of 0.30-1.02 bits that no sample size lowers, and in all-but-self parity networks, recordings of any length see several hidden units only through the product of their fidelities - a symmetry that one intervention broke in exact checks. The measure has sharp edges: because $\varphi$ selects a partition, and the cause and effect it specifies, by one criterion and reports another, infinitesimal changes of mechanism that cross an edge change it by 25-100% at 99% of the edges we found in random networks, and about 1% of surrogate models that fit interventional data almost perfectly misreport it by more than 20%. One-sided claims survive: the same data certify a lower bound on both sides of an edge, and we prove $\varphi>1.004$ bits throughout a 64-dimensional region of mechanisms and certify it from about $10^7$ controlled transitions with false-certificate probability at most $α$. Measurability is thus a design question with computable answers.
The canonical cut hierarchy recursively partitions a graph along Tutte-Nash-Williams partitions, choosing the partition with the most number of parts at each step. We give a randomized almost linear-time algorithm for computing this hierarchy in undirected graphs with polynomially bounded capacities via reduction to max-flow. This yields randomized almost linear-time algorithms for computing partition connectivity, strength, both arboricity and fractional arboricity, both integral and fractional spanning tree packing numbers, and implicit representations of the principal partition sequence and a maximum fractional spanning tree packing.
Towards interpreting any residual stream direction by scaling activation inversion
Celeste De Schamphelaere, Juan J. Vazquez, Ari Spiesberger, Tomáš Gavenčiak, Gavin Leech, Euan Ong, Jiahai Feng
AI 速读 基于摘要
提出 Maximally-Activating Example Metamodels(MAEMs),用无标签强化学习把残差流方向映射为能强烈激活该方向的文本样例,以可验证的方式解读任意方向。
cs.LG · cs.AI
查看原文摘要
To interpret a direction in a language model's residual stream, we can look for text that strongly activates it. But when such text is found by scanning a corpus, it is limited to what that corpus contains. We develop Maximally-Activating Example Metamodels (MAEMs), language models which map residual stream directions from a subject model to text exemplars that strongly activate those directions. Our objective is to maximise the cosine similarity of a supplied residual stream direction with the activations of the text generated by the MAEM. This label-free RL objective helps to scale MAEMs on diverse sources of residual stream directions. Empirically, we find the resultant metamodel produces informative exemplars: a Qwen3.6-27B MAEM inverts held-out activations better than corpus search or a natural-language autoencoder (NLA), beats corpus search (at 10M tokens) on a majority of held-out languages/domains, and activates 89% of held-out SAE features. It also identifies concepts behind steering vectors about as well as NLAs, recovers the payloads of LoRA backdoors more often than corpus search, and can even verbalise some model workspace inner monologue. Unlike explanations produced by other metamodels (e.g. NLAs), MAEM exemplars can be verified with a forward pass on the subject model, making the MAEM objective a grounded alternative for scaling the training of metamodels.
Vision-Language-Action (VLA) models can perform a wide range of robotic manipulation tasks, but often fail during deployment. Teaching them to recover from these failures requires substantial corrective data: existing approaches learn to recover from failures by directly associating corrective actions with the observations in which they were demonstrated. For instance, DAgger-like fine-tuning can require tens to hundreds of interactions, yet the resulting policy may still fail to generalize the learned corrections beyond the demonstrated scenarios. We hypothesize that semantics can capture the underlying reasons for failures and their corrections, enabling policies to learn from only a handful of corrective demonstrations and generalize those corrections to novel objects, and scene variations. We propose OopsieRecover, a framework that uses abduction to infer the intent behind a small set of corrective demonstrations and encodes the inferred knowledge as dense spatial representations and conditional costs. These costs capture when a behavior is undesirable and steer the policy toward more desirable action regions. We experiment across 6 tasks and variations in object poses, scenes, and related tasks, and find that only a handful of corrective demonstrations can enable a VLA to overcome failures across a broad range of novel situations, without requiring new corrective data for each variation. Please refer to https://robin-lab.cs.utexas.edu/oopsierecover for videos.
Chaithanya Rayudu, Jun Takahashi, Ojas Parekh, Andrew Zhao
原文摘要
Quantum Monte Carlo methods are widely used to solve quantum many-body problems. However, rigorous guarantees for their performance are poorly understood, especially for simulating interacting fermions. In this work, we develop a quantum Monte Carlo algorithm for a broad family of fermionic systems exhibiting Kramers time-reversal symmetry, and prove that their partition functions can be estimated in polynomial time. This family, which contains many important classes of Hubbard-type models, is known to both avoid the sign problem and obey a Lee-Yang zero-freeness theorem. Thus our results suggest that these two properties together may enable efficient classical algorithms for quantum many-body systems more broadly.
Learning dexterous manipulation from limited visual demonstrations is challenging because policies must acquire both perceptual grounding and precise control, while reinforcement learning (RL) in simulation can acquire rich control behaviors from large-scale interaction with privileged information. We introduce \textbf{Latent RL Prior}, a two-stage framework that reuses this control knowledge for data-efficient visual policy learning. During privileged pretraining, we distill large-scale RL rollouts into a flow-matching action decoder conditioned on proprioception and latent task context. During visual adaptation, we freeze the decoder and learn a visual interface that maps images to its latent context using action supervision alone, without privileged labels or latent targets. The same decoder can further be shared across arms by learning coordinated visual contexts for bimanual manipulation. Across three simulated tasks, our method outperforms full-parameter fine-tuning of $π_{0.5}$ and GR00T N1.7 in the low-data regime; on door lifting and bimanual assembly, it surpasses full-data baselines using $10\times$ and $5\times$ fewer demonstrations, respectively. Further analysis shows that direct visual-to-latent conditioning improves adaptation performance and training stability over routing visual predictions through the pretrained state encoder. Robustness to unseen mass variation and greater linear accessibility of contact-force information in decoder representations further provide evidence of retained RL-acquired control knowledge. Project website: https://yixiaowang7.github.io/latent-rl-prior-page/.
Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
Zixin Jessie Chen, Zhuo Chen, Archer Wang, Jeff Gore, William T. Freeman, Congyue Deng, Marin Soljačić
AI 速读 基于摘要
提出 SKILD,用尺度作为扩散动力学的显式坐标,在单一无条件框架内统一图像生成与连续超分辨率。
cs.CV · cond-mat.stat-mech · cs.AI · cs.LG
查看原文摘要
Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as reversing information loss across scales. We introduce $\textbf{SKILD}$, a $\textbf{S}$cale-invariant $\textbf{K}$-Space $\textbf{I}$mage $\textbf{L}$earning $\textbf{D}$iffusion model that unifies generation and continuous super-resolution within a single unconditional framework. Both natural images and critical physical systems exhibit scale invariance, and we leverage it to design a forward process that attenuates image content from fine to coarse scales while injecting spectrum-matched Gaussian noise, making scale an explicit coordinate of the diffusion dynamics. The same trained reverse process performs generation and continuous super-resolution by varying only the starting timestep: $\textit{no task-specific architecture, no conditioning branch, no classifier-free guidance, no retraining per scale factor}$. Empirically, SKILD reaches FID $2.61$ and Inception Score $9.65$ on unconditional CIFAR-10, performs $2\times$--$8\times$ super-resolution on ImageNet from a single unconditional checkpoint while outperforming conditional models across perceptual metrics, and reconstructs critical Ising models whose connected four-point correlations closely track the ground truth.
Adversarial Training (AT) is an important method for improving model robustness. We study the dynamics of deterministic Gradient Descent (GD) in AT. Most existing works in this direction focus on the small or vanishing step sizes regime, where GD resembles a continuous-time flow. However, such step sizes can make training inefficient and are rarely used in practice. In this paper, we study the AT dynamics of GD with large constant step sizes. We first study GD in adversarial linear logistic regression, focusing on two aspects: where the model parameters converge (implicit bias) and how quickly the losses decrease (optimization). We then turn to neural networks training and study how the sharpness of losses evolve during AT. Our results advance the understanding of the behaviors of GD with large step sizes in AT and highlight three key differences from its behavior in Standard Training (ST): (i) the implicit bias gap between AT and ST, previously established only for small step sizes, persists for arbitrarily large constant step sizes, (ii) different from ST, there is no uniform rate of convergence for the optimization error in AT, and (iii) sharpness can exhibit two-stage dynamics that differ from the Edge-of-Stability behavior observed in ST.
Generative AI and agentic coding are accelerating software development, leading to concerns about technical debt. But two less visible forms of debt, cognitive debt and intent debt, are emerging as key risks to software health. Cognitive debt is the absence or erosion of a team's shared understanding where no one can confidently explain how a system works or predict the impact of a change. Intent debt is the lack of clearly articulated goals, constraints, and rationale that explain what the system is for and guide how it should evolve. This paper presents Cognitive Tours, a tool designed to mitigate and repair cognitive and intent debt. Cognitive Tours is a web-based prototype for creating and following curated paths connecting user needs, design decisions, code, tests, and open questions. AI-assisted skills help audit existing waypoints and tours for possible problems or staleness and suggest candidates for new ones; humans decide what matters, verify relationships, and construct the narrative. This division of work deliberately preserves productive friction: the sensemaking involved in selecting, explaining, and revising a tour, which is intended to foster and share understanding. Our demonstration uses a tour of Cognitive Tours itself to introduce the tool and illustrate its design decisions and interaction mechanisms. A proposed evaluation agenda concludes the paper. A demo is available at https://cognitive-tours-demo.vercel.app/
We determine the sharp order of discrepancy in Tusnády's problem in every fixed dimension $d\ge 2$. The largest combinatorial discrepancy of $N$ points in $\mathbb{R}^d$ with respect to axis-parallel boxes is $Θ_d((\log N)^{d-1/2})$, extending Wei's planar result and matching Nikolov's upper bound. More strongly, with high probability, this lower bound holds simultaneously for every subset obtained by deleting at most a sufficiently small fixed fraction of a uniform $N$-point sample. We apply this geometric estimate to online thinning of two independent samples of size $n$ from an unknown common distribution, where observations must be kept or discarded upon arrival. For every fixed dimension $k\ge 1$ and expected deletion budget $ρn$, with $0<ρ<2$, we prove that the minimax expected prefix discrepancy over lower orthants is $Θ_{k,ρ}((\log n)^{k+1/2})$. In dimension one, the optimal terminal discrepancy is instead $Θ_ρ((\log\log n)^{3/2})$, giving a sharp separation between the prefix and terminal objectives. For $k\ge 2$, we obtain terminal bounds differing by a factor of $\log n$. The lower bounds are based on Gaussian small-ball estimates for box-incidence matrices, while the upper bounds use stationary Metropolis thinning and, in one dimension, a terminal cancellation procedure.
On-policy distillation (OPD) trains a student on its own rollouts under a frozen teacher's per-token supervision. Does this dense signal reduce the training FLOPs needed to reach a target accuracy compared with reinforcement learning? We systematically compare vanilla reverse-KL OPD with Group Relative Policy Optimization (GRPO) across task difficulty, student and teacher size, domain, and optimization choices, measuring held-out accuracy against training FLOPs. With an external post-trained teacher, OPD generally loses to GRPO in accuracy per training FLOP at matched settings, even when the teacher is further trained with GRPO, and often suffers response-length inflation. Yet a different teacher changes the picture: when the teacher is the student's own GRPO checkpoint, OPD recovers that checkpoint's accuracy on math with $50\times$ fewer distillation FLOPs than GRPO needs to reach the same accuracy. Following the same teacher setting, we consistently observe this high efficiency with a larger student, on code, and in a second model family. On a single domain, however, the GRPO checkpoint is already the desired model, so distilling it adds to total compute. Across domains, separate GRPO checkpoints hold different capabilities, and no single checkpoint serves every domain. Multi-teacher OPD (DeepSeek-AI, 2026) consolidates per-domain GRPO experts into a single student that matches each expert's accuracy, with the distillation stage costing only 5.2% (on 2 domains) and 8.0% (on 4 domains) of the specialist training FLOPs. Counting specialist training and distillation together, this pipeline reaches joint GRPO's performance on the 2-domain mix with 42.0% fewer total FLOPs.
ReproBridge: Building Reproducibility into ML Research Artifacts
Yubo Wang, Rui Meng, Jaehyun Nam, Tomas Pfister, Jinsung Yoon
AI 速读 基于摘要
作者提出一套标准化可复现工件设计与智能体工作流 ReproBridge,并构建 ReproBridge-Bench 基准,报告精炼工件能提升编码智能体独立复现实验的成功率并降低 API 开销。
cs.AI
查看原文摘要
Reproducing machine learning experiments requires reconstructing procedures from information scattered across papers, released code, and supporting artifacts. For coding agents, reproduction success can therefore depend on their ability to fill in missing details, rather than on the released artifacts alone. We ask whether preserving recovered procedures and decisions improves subsequent independent reproduction. We define a standardized artifact design comprising a refined codebase, environment setup, experiment launchers, and a reproduction guide, and introduce ReproBridge, an agent workflow for constructing these refined reproducible artifacts. ReproBridge-Bench provides 1,029 tasks from 387 experiments across 36 papers, anchored by five human-verified reference scores per task. Agents attempt tasks in fresh sessions with raw code or refined artifacts; a separate Auditor checks execution evidence. Across four evaluated models, refined artifacts raise mean reproduction success from 76.4% to 92.6% and reduce downstream API spending by 19.7% on average. The cross-model success-rate spread narrows from 21.6 to 3.9 percentage points, with all four models achieving mean success rates above 90%. Removing any component reduces success in the ablation study, with the largest losses from code and environment removal. These results suggest that preserving execution knowledge helps even models with lower raw-code success reproduce experiments more reliably and at lower API cost.
As robots are deployed in the real world, they will inevitably make mistakes. Human interventions provide valuable feedback for improving their behavior, enabling them to adapt online to new scenarios. However, studying human-in-the-loop robot learning is difficult: real-world experiments are slow and expensive, so most algorithm development relies on simulated human models. We show that common human modeling assumptions do not match how real people intervene in practice. Through analyzing intervention data from human participants, we find that humans tend to intervene when agent progress stalls, and that their corrective actions are often suboptimal. Motivated by these findings, we introduce a progress-based model of human intervention that achieves higher rank correlation with real-user algorithm rankings, enabling realistic algorithm benchmarking and development in simulation. Building on these insights, we propose Q-OIL, a method that adds optimistic bonuses to intervention transitions in reinforcement learning and softly guides exploration toward human corrections. We find that decoupled critics are critical for stability because they prevent the bonuses from backing up to pre-intervention states. As a result, Q-OIL learns more efficiently than competitive baselines, achieving 10-50% higher success in simulation and on real robots, and improving pretrained VLAs on two bimanual manipulation tasks. As we ground both evaluation and algorithms in realistic human behavior, this work provides a practical path toward scalable robot learning from interventions.
Models for physical AI tasks, such as robotics and autonomous driving, need not reason solely in language. They can use visual plans--points, bounding boxes, and trajectories--to represent spatial goals and anticipate motion. However, autoregressive vision-language models generate these plans one coordinate token at a time, making richer predictions increasingly costly. We introduce VFlash, a method for fast, accurate visual planning through Flash Primitive Decoding. VFlash exploits the known structure of visual primitives to predict their coordinates jointly, using a lightweight drafter that generates an entire primitive in one forward pass. The layout adapts to the primitive's type, dimensionality, and length, supporting compact boxes and long, variable-length trajectories. Crucially, spatial accuracy need not require reproducing an autoregressive model's exact token sequence. VFlash therefore trains on annotated primitives and directly accepts structurally valid predictions without target-token agreement. Across the evaluated 2D and 3D robot trajectory tasks, VFlash consistently reduces prediction errors relative to autoregressive decoding. Preliminary single-rollout measurements indicate approximately 25x faster generation for 3D point motion forecasting. A world action model conditioned on VFlash plans achieves 70.2% average success across four MolmoSpaces task suites, compared with 62.6% for the baseline.
State-of-the-art feedforward reconstruction models perform poorly on in-the-wild object-centric photo collections. They are trained largely on single-session object captures whose images vary in viewpoint while the object and its environment remain nearly fixed. Public photo archives contain a different form of multi-view data. They hold found photos of the same object or design: photos taken independently by many people across years, environments, cameras, and sometimes physical units. In this work, we introduce Trainspotting, a dataset of 12,068 objects and 311,886 photos from Wikimedia Commons. We reconstruct each object to recover camera poses, multi-view stereo depth, and object masks. We categorize the objects into three regimes: objects fixed at one site, objects that move between sites, and designs shared by many physical units. Evaluating recent feedforward reconstruction models on Trainspotting shows that they fail most severely in the last two regimes. Fine-tuning VGGT-$Ω$ on Trainspotting significantly improves camera pose, depth, and 3D geometry on held-out objects. We observe similar improvements on the independent NAVI in-the-wild benchmark, which contains photos of each object in different environments. Performance on conventional benchmarks remains largely unchanged.
Lee-Yang theorems are a powerful tool for studying many-body systems, with applications ranging from analyzing phase transitions to proving the efficiency of certain classical and quantum algorithms. In this work, we prove a Lee-Yang zero-freeness theorem for the partition function of a broad class of interacting fermion models, implying the existence of a provably efficient quantum algorithm for estimating their ground-state energies. This class includes several well-known models such as the attractive Hubbard model, repulsive Hubbard model on bipartite graphs, and the interacting Hofstadter model. Our results also rigorously establish the nonexistence of phase transitions in these models in the presence of a nonzero local external field.
Customer experience (CX) agents use tools and large language models to address customer requests and guide conversational interactions with an organization's products. Improving these agents, especially in regulated industries, is difficult: they must detect intent, follow complex operational policies and use tools reliably. Manual end-to-end testing offers limited coverage, while live experiments expose customers to failures that can erode trust. We present a hypothesis-driven simulation workflow for screening candidate CX agents before deployment. Synthetic customers react to agent responses and simulated tool outputs enable multi-step agentic workflows without invoking production backends. We use the Snowglobe simulator on Nubank's Card Delivery agent and its expanded successor, Card Management - Nubank's highest-volume chat-support agent in Brazil. Across 4 deployed versions, simulated and production version-level binary evaluator scores show high correlation. Simulation-guided iteration increased transactional net promoter score (tNPS) by 36.69 points in a live A/B test. We also screened open-weight configurations in over 16,000 simulated conversations. In a subsequent live A/B test, the selected model increased self-service rate (SSR) by 8.82 percentage points to the highest level observed at Nubank, with no statistically significant change in tNPS. Simulation made broad exploration of models, reasoning settings, and prompts feasible without customer exposure, enabling production improvements that would have been impractical to pursue through live experimentation alone.
A defender anticipating an attacker needs a probability distribution over the attacker's next action from information available before that action occurs. Two structures complicate this: the attacker's behavioral regime persists and can switch within an episode, and each action combines an operation with state-dependent arguments whose feasible values change over time. We capture both with a hidden Markov model whose latent state is the active regime and whose regime-conditioned action law is defined on a feasibility-masked tree of executable actions. The same likelihood forms the next-action distribution and updates the regime belief once the action is seen, and a partially observed prefix contributes its resolved local factors. Estimation separates into convex logistic fits that Baum-Welch reuses when regimes are unlabeled. We derive a reach-weighted nodewise KL expression for regime information, a sequence-wise log-loss bound for switching regime paths, and a uniform fallback guarantee. On the CAGE 2 cyber defense benchmark the filtered latent state is worth 0.8 nats per step, and after a controller switch the loss begins to fall in three steps against ten for a recurrent baseline.
For bounded-error randomized query complexity, we resolve the composition conjecture up to logarithmic factors. The general upper bound $R(f\circ g) = O\!\left(R(f)R(g)\log(R(f)+1)\right)$ was already known. Although Meiburg recently disproved constant-factor multiplicative composition for total Boolean functions, the conjecture allowing polylogarithmic losses remained open. We settle this question by proving that, for all (possibly partial) Boolean functions $f$ and $g$, \[ R(f\circ g) = Ω\!\left(\frac{R(f)R(g)}{\log(n+1)}\right), \] where $n$ is the input size for $f$.
Polynomial-time classical simulation of boson and fermion sampling under thermal loss
Armando Angrisani, Hela Mhiri
AI 速读 基于摘要
作者提出统一框架,证明在任意固定非零总损耗率下,若干玻色子与费米子采样任务可被多项式时间经典模拟。
quant-ph · cs.CC · math-ph · physics.optics
查看原文摘要
Sampling experiments are a leading approach to demonstrating quantum computational advantage, yet their robustness to experimental noise is not completely understood. We develop a common framework for classical simulation of boson and fermion sampling under thermal loss, including pure loss. For Fock-state boson sampling, Gaussian boson sampling with fixed uniform squeezing, and fermion sampling with magic inputs, we obtain polynomial-time sampling at inverse-polynomial total variation error, for any fixed nonzero overall loss rate, and with high probability over Haar-random interferometers. A milder flatness assumption on the ideal output distribution suffices for quasipolynomial-time simulation without Haar randomness. With constant thermal loss per layer, the same flatness assumption gives polynomial-time simulation at logarithmic depth. Our bounds for Fock-state boson sampling cover both dilute and saturated regimes and become stronger near full input filling: when only a bounded number of input modes are empty, the noisy output for Haar-random interferometers converges, as the number of modes grows, to a distribution independent of the interferometer.
The speech capabilities of mobile devices have grown, but their displays still rely on a text-based chat. When resuming a voice chat after a context switch, the last messages may not convey the key points of the conversation. Autobiographical use and sessions with external participants led to design goals for a mobile-first, speech-driven, glanceable display that helps users continue their reasoning from where they left off. We implement these goals in Souffleur and evaluate it in a between-subjects study with 48 participants. Compared with a conventional chat transcript, we found no reliable difference in how easily participants followed and resumed short voice conversations, nor in effort, attention or recall, although Souffleur reduces the conversation to a few short phrases.
Cyclist fatality rates remain high despite policy support for active travel, and autonomous vehicles add complexity to mixed traffic. Neither crash statistics nor multi-model detection pipelines scale to continuous monitoring of perceived safety along a route. We present an edge-assisted crowdsensing system: handlebar cameras supply street-level frames, a vision-language model (VLM) turns each frame into structured traffic attributes through a single prompt, and an explainable boosting machine (EBM) combines them with OpenStreetMap road infrastructure and on-bike kinematics to predict a crowdsourced 1-9 safety score. Extraction belongs at the network edge: the fastest self-hosted model needs 2.49 s per frame and scoring takes 0.4 ms on a CPU. On 1,362 annotated frames from two London routes, the EBM regressor reaches 72.2 percent binary accuracy and a mean absolute error of 1.011 under five-fold cross-validation. It is within one accuracy point of black-box ensembles. Its per-feature shape functions give exact attribution: physical lane separation is worth +0.97 rating points, a painted lane +0.70 and a construction site -0.65. Planners can therefore price an infrastructure change in rating points, and the results enter cost-benefit analysis directly. We also report inter-annotator agreement (alpha = 0.4695), an attribute audit, and a sensitivity analysis linking attribute error to accuracy. With re-encoding, a 20 s sampling interval serves 1,000 riders at 54 Mbit/s at a cost of 1.4 accuracy points, making continuous monitoring practical.
In human-robot interaction, agentic robots should resolve ambiguous user requests through proactive clarification while keeping user burden low. We study this challenge in interactive instance navigation, where an agent must identify and reach the user-intended target among similar objects. Existing approaches ask open-ended questions and select a candidate that strongly matches the accumulated user-provided information. However, this process can require lengthy user responses and lead the agent to make premature decisions without distinguishing the target from distractors. To address these limitations, we propose Proactive Instance Navigation with Comparative Judgment (ProCompNav), a two-stage framework that first constructs a candidate pool and then identifies the target through Recursive Comparative Judgment (RCJ). RCJ iteratively narrows the pool by selecting an attribute-value pair that divides the candidates, asking the user a binary question, and removing inconsistent candidates, without requiring an attribute unique to the target. ProCompNav substantially improves Success Rate and reduces Response Length on an interactive navigation benchmark, and achieves the highest Success Rate among evaluated methods on a non-interactive benchmark. In two human studies, participants preferred ProCompNav's binary questions to open-ended questions and its batched delivery to interleaved interaction. Our results highlight the need to jointly consider task performance and user-friendly interaction strategies when designing agentic robots.
We introduce SM4RT, a multi-task cascade feed-forward model for dynamic scene reconstruction from RGB videos. While existing feed-forward approaches typically address geometry reconstruction and motion estimation separately--and often predict motions in a single coordinate frame that must account for camera movement--SM4RT solves these tasks sequentially by first reconstructing 3D geometry and then bootstrapping motion estimation from the predicted structure. By expressing each pixel's 3D motion in its corresponding camera frame, SM4RT reduces ambiguity arising from camera motion. To address the sparsity of real-world motion labels, SM4RT further incorporates a weakly supervised loss that regularizes unlabeled point motions using labeled point positions at the other time step. We evaluate motion estimation on three dynamic-scene datasets--Kubric, Waymo, and Point Odyssey--and SM4RT achieves the best performance on most metrics compared with prior baselines. We additionally benchmark geometry reconstruction on five dynamic scene datasets and show that SM4RT achieves competitive performance with state-of-the-art methods. Overall, our unified framework demonstrates that combining geometry reconstruction and motion estimation in a cascade not only avoids performance trade-offs but also enhances motion estimation through improved geometric reasoning.
LLM-based medical assistants that follow a patient across visits need a memory that keeps the patient's clinical state correct as it changes. We examine the errors of five memory systems on longitudinal medical dialogue and find three recurring causes: the retrieved evidence gives an outdated state, includes another person's health facts, or lacks a safety fact the answer depends on. We present MedGraph, a graph memory built for these three cases. Construction extracts dated facts from each session, attributes each fact to the person it describes, and links medication, diagnosis, and measurement records into chains that keep earlier states. Retrieval ranks the patient's chains as units, reads each chain at the time the question asks about, and adds the original dialogue text; a patient profile lists every recorded safety fact with every question. On MedMemoryBench, MedGraph has the highest overall accuracy with both a GPT and a Qwen backbone, 10.5 and 10.4 points above the strongest of five baselines, with efficient memory construction and answering in the GPT setting.
This research involved the study of an application of Case-Based Reasoning (CBR) in the field of academic advising. Academic advisement has been recognised as an important function of higher education. However, there is a widespread desire to improve the advisement services provided by many educational institutions (e.g., colleges and universities) around the world. In the last ten years, CBR expert systems have made important contributions in many domains by applying CBR methodology to a variety of areas of human problem solving. However, to date, expert advisement systems have not been successfully applied to academic advisement, which seems to be a very appropriate domain for this technology. Academic advising is an important and time consuming task, and different tools and techniques must be used to make it an effective and efficient process. This thesis describes the design, development, and validation of a prototype case-based academic advisement recommender system that supplements the conventional advising process, and could eventually evolve to replace human academic advisors when its full potential is realised.
Agentic forecasting is important for decision-making in dynamic environments, but it remains challenging because agents must reason from incomplete, time-limited evidence and produce calibrated probabilities before outcomes are resolved. Memory provides a natural mechanism for transferring experience from resolved forecasts to future prediction tasks. However, existing agent-memory methods are not tailored to forecasting, as they typically store past interactions, reflections, or factual associations without explicitly representing reusable predictive factors or calibration knowledge. We propose ForecastCompass (FoCo), an adaptive factor-based memory framework for agentic forecasting. FoCo organizes forecasting experience with a hierarchical forecasting-task taxonomy, enabling retrieval task-relevant forecasting knowledge. It maintains two complementary memory components: factor memory, which captures reusable predictive dimensions, and reasoning memory, which encodes probability updating, uncertainty handling, and calibration principles. Using retrospective analyses as learning signals, FoCo iteratively revises memory through a verbalized memory-revision procedure, enabling the agent to accumulate transferable forecasting knowledge over time. Experiments on Prophet Arena and FutureX with GPT-5-mini and Gemini-2.5-Flash show that FoCo improves both probabilistic accuracy and calibration.
As society, ethics, and professional practice become increasingly integrated across the computer science curriculum, technical courses need practical ways to support ethical reasoning. Ethical essay assignments offer one approach, but little is known about how students use GenAI when writing such essays. This experience report examines GenAI use across three years of ethical essay assignments in a large first-year computer systems course. Across six post-essay surveys from 2024 to 2026, we analyzed 1,894 responses, linked survey data with essay grades in 2025 and 2026, and introduced a scaffolded responsible-use workflow in 2026. Under voluntary-use policies, AI adoption remained steady at around two-thirds of students, rising above 90% when use was scaffolded. Students reported mainly using AI for help with grammar and style, while tool use diversified beyond ChatGPT in 2026. Grade-linked analyses showed that AI use did not independently predict essay quality, while marker evaluations indicated high levels of critical engagement when use was scaffolded. Overall, GenAI's pedagogical value appears to depend on how assessment design guides students to evaluate and critically engage with AI-generated suggestions.