Ryan Hsiang, William Adkisson, Robert Joseph George, Anima Anandkumar
原文摘要
Building on recent progress in machine learning for formal theorem proving in Lean, we introduce LeanDojo-v2: an end-to-end framework that unifies repository data extraction, LLM fine-tuning, proof search, AI autocompletion, and LLM-assisted theorem proving in a single software library. In addition, we provide Lean4Code, a lightweight IDE that integrates the various features of LeanDojo-v2 through a simple, mathematician-friendly UI. These tools will enable mathematicians and researchers to easily fine-tune language models on domain-specific Lean codebases and experiment with LLM-assisted theorem proving without a complex setup.
Ryan Hsiang, Robert Joseph George, Anima Anandkumar
原文摘要
Certifying the robustness and physical consistency of scientific machine-learning models ensures that their predictions remain reliable beyond the test set. For neural operators, which learn PDE solution operators by mapping infinite-dimensional function spaces, certification means establishing rigorous, domain-wide guarantees for their output functions. However, standard neural network (NN) verification methods are fundamentally designed for vector-to-vector mappings, and they can only certify neural operators at fixed grid resolutions and provide no guarantees over the entire domain or across another resolution. We close this gap by introducing a function-space certification framework that verifies neural operators across the entire continuous domain. We formulate interval bound propagation (IBP) and CROWN in function space, propagating upper and lower bound functions through each layer using rigorous numerical integration. In addition, we extend bound propagation to higher-order derivatives to certify PDE residuals and solution error bounds. Experiments across several neural operator architectures and scientific problems, including the 572.5-million-parameter spherical Fourier neural operator for global weather forecasting, show that our method produces tight, domain-wide guarantees efficiently, providing a foundation for trustworthy operator learning.
Vincent Guan, Joseph Janssen, Hossein Rahmani, Andrew Warren, Stephen Zhang, Elina Robeva, Geoffrey Schiebinger
原文摘要
Stochastic differential equations (SDEs) are a fundamental tool for modelling dynamic processes, including gene regulatory networks (GRNs), contaminant transport, financial markets, and image generation. However, learning the underlying SDE from data is a challenging task, especially if individual trajectories are not observable. Motivated by burgeoning research in single-cell datasets, we present the first comprehensive approach for jointly identifying the drift and diffusion of an SDE from its temporal marginals. Assuming linear drift and additive diffusion, we show that non-identifiability can only arise if the initial distribution possesses generalized rotational symmetries. We further prove that even if this condition holds, the drift and diffusion can almost always be recovered from the marginals. Additionally, we show that the causal graph of any SDE with additive diffusion can be recovered from the identified SDE parameters. To complement this theory, we adapt entropy-regularized optimal transport to handle anisotropic diffusion and introduce APPEX (Alternating Projection Parameter Estimation from $X_0$), an iterative algorithm designed to estimate the drift, diffusion, and causal graph of an additive noise SDE, solely from temporal marginals, and demonstrate its effectiveness on simulated data from linear additive noise SDEs.
Generative creative interfaces routinely report the user's position within a space of possibilities. Such displays imply that the quantities shown were measured from the artefact; in a growing class of systems they are instead predicted by a language model describing its own output, and the two are indistinguishable on screen. Most creative domains lack an agreed measurement against which such a self-report can be checked; audio admits one. In a measurement study of a working LLM-driven timbre interface, what a user can cause proves separable from what the interface reports. The first is exactly characterisable: the reachable set is a zonotope in parameter space whose dimension increases by one per sound placed, so the space the model may act within is demonstrably the user's own. The second is inaccurate. The displayed position differs from measurement by approximately three times the width of that region, and the error has two independent sources: model-predicted coordinates, whose accuracy varies twofold between the two models evaluated, and the interpolation step, which arises from combining synthesiser parameters and is unaffected by model quality. End to end, 27 of 36 refinement instructions produced no perceptible change, and under the weaker model the facility performed no action while reporting convergence. Effective agency (what a user can cause) and epistemic agency (whether they can know it) are therefore separable and independently engineered: structurally enforced constraints survive model failure, whereas guarantees resting on the model's own report do not. The failure mode that remains is silence presented as success. We close with a short protocol for building and auditing such displays.
Modeling gene regulation in single cells requires jointly representing DNA sequence, chromatin accessibility, and gene expression across regulatory scales. Sequence-based models capture DNA-level regulatory grammar but often lack cell-level resolution, whereas many single-cell omics models represent genes and peaks as fixed-vocabulary tokens without their underlying sequence. Here, we present MUSS, a sequence-based multi-scale model for single-cell gene regulation that preserves both DNA-level and cell-level resolution. MUSS derives peak- and gene-level representations from DNA using a frozen pre-trained sequence encoder and integrates them through peak-peak self-attention and distance-biased peak-gene interactions. Peak masked language modeling followed by training on paired scATAC-seq and scRNA-seq aligns these representations with cell-specific regulatory states. Across gene expression prediction, enhancer-gene linking, motif-guided regulatory prioritization, and zero-shot cell clustering, MUSS achieves strong performance against sequence-based and single-cell omics baselines. It further predicts expression for genes and peaks unseen during task training. These results support sequence-grounded, multi-scale representations for decoding cell-type-specific regulatory programs. Code, datasets, and model checkpoints are available at https://github.com/Lotfollahi-lab/MUSS_neurips26.
Mingxuan Li, Huanzhi Mao, Qiuyang Mang, Hanchen Li, Joseph E. Gonzalez, Alex Dimakis
原文摘要
An LLM agent's cost and success depend on its model, its harness, and its environment. In addition to the widely studied directions of parameter tuning and harness optimization, we propose the third direction: optimization over stationary environments. Agents are often deployed in rich environments shared by many tasks, such as a company's Slack workspace or a complex collection of data sources, documents or tickets. We call these environments stationary environments. We introduce EnvOpt, a method for automated end-to-end optimization of stationary environments for any given model and harness, using real or synthetic tasks without needing any graders or reference answers. On AutomationBench, EnvOpt reduces the cost of Claude Haiku 4.5 by 72.7% and raises its pass rate by 14.34%. The same environment transfers to Opus 5, cutting its cost by 68.1% with a 1.34% gain. Added on top of Meta-Harness's optimized harness for Haiku 4.5, it lowers cost by a further 83.4% and adds 11.17% accuracy over Meta-Harness alone. Across 5 benchmarks, EnvOpt significantly reduces the cost of agents while improving or maintaining pass rate, and is transferable to different models and different harnesses. We also discuss common successful and rejected environment optimization strategies during automated optimization. More broadly, our results show that how information is represented to an agent shapes both its cost and its success, making the environment worth optimizing in addition to the parameters and the harness.
The manifold hypothesis suggests that data lies on manifolds with smaller intrinsic dimension (ID) than their ambient dimension. However there is no empirical agreement on the estimates for ID from different estimators for realistic datasets. Thus it is important to test ID estimators (IDEs) with targeted stressors. In this work, we consider the role of anisotropy. To this end, we propose HomID, a collection of homogeneous spaces with anisotropic embedding, for benchmarking ID estimators. We observe that methods that perform well on standard benchmarks systematically degrade on HomID under identical resource allocation. We further observe that anisotropic distortion of such benchmarks also results in performance degradation. Finally, we demonstrate that controlled anisotropic distortions induce systematic shifts in the distributions on which these methods rely, providing a concrete mechanism for the resulting estimation errors in two particular IDEs. The code for the project is available at https://github.com/a-writes-code/homid
AI's inflection point is a fountain of alarming risks. Digital platforms in particular are vulnerable to three major AI risks, as those in control of global platforms cede control to AI, of the algorithms, of membership and of content: (1) AI control of global platforms, social and economic, used by the majority of humanity, resulting in the majority of humanity becoming vulnerable to AI control. (2) Unaccountable AI agents operating anonymously on social and economic digital platforms, side-by-side with humans, possibly masquerading as humans, serving unknown masters with unknown goals, operating under unknown restraints without accountability or culpability. (3) Unattributed deepfakes generated by anonymous AI, with people unable to distinguish them from genuine content and with their producers evading accountability and culpability. Here, we propose to corral these AI risks with grassroots contracts, a digital incarnation of a two-centuries old notion of Pierre-Joseph Proudhon. We present grassroots contracts for a social graph with accountable AI agents and for a social network with digital provenance, and working smartphone apps that implement the two and show how they corral these major AI risks: (1) AI control of global platforms. (2) Unaccountable AI agents. (3) Unattributed deepfakes.
Joseph H. Rudoler, Kevin Tan, Giles Hooker, Konrad P. Kording
原文摘要
Deep learning systems are known to exhibit implicit regularization (alt. implicit bias), favoring simple solutions instead of merely minimizing the loss function. In some cases, we can analytically derive the implicit regularization -- connecting it to an equivalent penalty that augments the learning objective. However, modern deep learning systems are complex, carrying modifications to the training procedure and architecture (e.g. early stopping, minibatching, dropout) whose effects are not always directly interpretable. Although estimating the resulting implicit regularization could aid theorists in algorithm design and practitioners in interpreting their hyperparameter choices, this problem has received little direct attention. It is also tractable: regularization makes weight updates deviate from loss gradients, promising a signal for identifying implicit bias. Here we provide gradient matching methods that can be used to empirically estimate the implicit regularization. Our method works on networks with known regularization, recovering popular explicit penalties like $\ell_1$ and $\ell_2$. It also replicates known implicit effects, like the quadratic weight penalty induced by early stopping in gradient descent, demonstrating that it can be used to test theories of implicit regularization. Crucially, because our method is empirical, it can handle implicit regularization in arbitrary networks. We demonstrate this use by characterizing implicit $\ell_2$ effects of dropout in deep networks. Our work shows that practitioners can use gradient matching to understand regularization in networks with implicit biases that are too complicated to derive analytically.
Li Guan, Rachael Granberry, Sahar Aseeri, Sahar Rostami, Taylor Niehues, Sai Dhanoosh Marri, Mia Huang, Dingtian Zhang 等 104 位作者
原文摘要
Collecting naturalistic human manipulation demonstrations with accurate contact force and hand pose is essential for robot dexterous manipulation policy and foundational world model learning - yet no existing wearable platform provides both calibrated fingertip force sensing and occlusion-resilient hand tracking in a form factor that preserves natural manipulation behavior. We present Tactus, a textile-integrated sensing glove that co-optimizes three design pillars: (1) a thin, conformal 3D-knit form factor (1.5 mm fingertip stackup) designed to minimize interference with natural manipulation, (2) strategically placed capacitive tactile sensors at manipulation-relevant regions informed by empirical contact studies, and (3) IMU-fused pose tracking that maintains accuracy through the hand-object occlusions where manipulation data is most valuable. Tactus includes a documented calibration pipeline for cross-glove consistency and per-session calibration for subject-dependent correction. To enable objective comparison, we introduce standardized benchmarking protocols for tactile force regression and hand pose estimation, and apply them to Tactus and two commercially available tactile gloves - to our knowledge the first quantitative cross-platform evaluation of this kind. Tactus resolves a minimum detectable force of 0.59 N at 95% confidence, 1.6 - 2.7x lower than the commercial baselines, and with 0.87 cross-participant consistency, while our pose tracking sustains 11.0 mm fingertip keypoint relative error during manipulation, when occlusion is heaviest. We show that these combined signals support object property estimation, slip detection, and representative recording of hand-object interaction - yielding demonstration data with the fidelity required for contact-aware manipulation policies and world models.
Sherry Choi, Sitao Sunny Li, Joseph Romero, Lillian Chin, Ashwin G. Ramayya, Allison M. Okamura, Ava Chen
原文摘要
Motor responses evoked by noxious stimulation are used to assess neurological function in hospitalized patients with disorders of consciousness. In standard bedside assessments, these stimuli are applied manually, resulting in substantial variation in force, duration, frequency, and location. Here, we present OUCH (Objective, Uniform, Controlled Haptic stimulation), a wrist-worn device that uses pneumatic actuation to deliver noxious mechanical stimuli. OUCH combines stacked pneumatic pouch actuators, a rigid indenter, and a compliant spacer designed to buckle at a set load, so that the indenter contacts the skin only during actuation. We characterize the device using blocked force tests, clinician evaluation, finite element analysis, and a deformable pressure testbed, and benchmark it against a commercially available handheld pressure algometer. At 200 kPa pouch inflation pressure, our indenter concentrated its load into an estimated contact pressure of 18,500 kPa, over 25 times that of the algometer tip, while requiring less total force. On the deformable testbed, it localized deformation near the surface, while deformation at depth remained comparable to the algometer. As a result, in preliminary perceptual testing, our indenter elicited discomfort at approximately 89% lower applied force than the algometer, demonstrating the feasibility of evoking discomfort with a compact, wearable soft actuator. These results show that combining pneumatic actuation with designed contact geometry enables controlled, repeatable noxious stimulation at the wrist, providing a foundation for objective neurological assessment.
Alan Zhu, Mihran Miroyan, Carolyn Wang, Andrew Zhou, Lisa Dunlap, Narges Norouzi, Joseph E. Gonzalez
原文摘要
User modeling aims to use language models (LMs) to mimic an individual's behavior from a corpus of past context-action pairs (e.g., conversation turns), enabling the simulation of users in settings like behavioral science, human-AI collaboration, and market research. Recent approaches augment these corpora with synthesized reasoning traces, typically generated by conditioning on both context and action. However, action-conditioned traces are post-hoc rationalizations and need not reflect the user's underlying decision process. We propose Recon, which uses action reconstruction to score reasoning traces by their predictive power: given a context and candidate reasoning, a reconstruction model predicts the action, and reconstruction fidelity determines reasoning quality. Across four domains, Recon achieves a 54.7% win rate over Backward Synthesis, a standard post-hoc rationalization baseline. Further, we find that training a reasoning synthesis model with rewards derived from Recon improves downstream user modeling performance, achieving a win rate of up to 70.0% over baselines. We further show that Recon-synthesized reasoning transfers across models, and improves user modeling beyond the reconstruction model. Our work demonstrates that post-hoc rationalization is insufficient for reasoning synthesis, and that useful and interpretable reasoning should naturally elicit the action from the context.
Mingxuan Li, Huanzhi Mao, Ruitao Zheng, Jarod Stanbury James, Yunze Li, Natanya Anderson, Joseph E. Gonzalez, Alex Dimakis
原文摘要
AI Agents are becoming digital coworkers that can browse the web, write code, run experiments, and assist humans over extended horizons. Yet existing benchmarks fall short of real knowledge work: many rely on synthetic data or isolated tasks, missing the complex, multi-party dynamics of collaborative projects, where critical information is scattered across conversations, code, and evolving decisions. Even simple workplace questions may require locating relevant channels and direct messages, recovering context from long discussions, inspecting repository state, reconciling stale or conflicting evidence, and synthesizing across sources. We introduce SlackBench, a benchmark for evaluating agents on realistic research and engineering workflows that require joint reasoning over workplace communication and evolving repository state. Grounded in privacy-preserving reenactments of real academic research projects, SlackBench provides reproducible environments with realistic multi-party dialogue, evolving decisions, and corresponding code changes grounded in GitHub repositories and Google Docs. It contains 140 queries spanning heterogeneous-source agentic search, abstention on unanswerable or false-premise questions, goal-directed summarization, and circumstance inference over long conversations. These tasks are not reducible to static corpus question answering: agents must determine which conversations matter, traverse threads, inspect repository state, and synthesize evidence across communication and code artifacts. Across 33 frontier models and agent harnesses, the best system scores around 80% and most agents score below 66%, highlighting substantial headroom for improvement. SlackBench thus provides an extensible framework for evaluating agents in collaborative work environments. The SlackBench dataset is available at https://huggingface.co/datasets/HuanzhiMao/SlackBench .
We introduce PLANTEUR, a benchmark for crop-type mapping from satellite images in the French overseas territories. Building on the PASTIS design, PLANTEUR provides georeferenced and aligned Sentinel-2, Sentinel-1, and Landsat-8 sequences with parcel-derived labels spanning six tropical regions and an 8-class label space. We define both a standard test split and a leave-one-island-out protocol to measure cross-territory generalization, and evaluate fully supervised models, linear probes, and fine-tuned foundation models. The benchmark code and data are open source and available on GitHub and Hugging Face.
Gabriel Diaz-Aylwin, Joseph Neighbour, Abiel Malkani Talwar, Rui-Yang Zhang, Henry B. Moss
原文摘要
Bayesian optimisation is the natural tool for shape design when objectives are expensive and non-differentiable, but it needs a compact yet expressive parameterisation of the search space. Hand-crafting one is a complex endeavour requiring domain expertise, and often yields implicit infeasible regions, artificial bounds, and coupled, unordered coordinates. We instead learn the parameterisation from a collection of existing designs, applying principal component analysis to the deformations between shapes. The result is a linear, interpretable search space in which the number of components explicitly trades expressivity against dimensionality. Across aerofoils, wings, and radio-frequency cavities, spanning 2D geometry to 3D aerodynamics and electromagnetics, we show improved sample efficiency and the ability to explore beyond the confines of hand-crafted baselines.
Frontier language-model agents excel at complex tasks, but high inference costs make transferring their capabilities to smaller models essential. Traditional knowledge distillation achieves this through parameter updates, requiring access to the student's weights and additional training compute while encoding the transferred knowledge implicitly in the parameters. We introduce D-Skill, a framework that treats the teacher as a black box and distills its behavioral advantage into an interpretable natural-language skill by analyzing paired rollouts and identifying behavioral divergences and agreements. The resulting lessons are consolidated offline, with any compatible skill-update backend, into a skill document that is provided to the student at inference time. D-Skill constructs the skill entirely offline from fixed trajectories, without labels, further environment interaction, or weight updates after rollout collection. Across SpreadsheetBench-Verified, ALFWorld, and chess puzzles spanning multiple teacher-student pairs, D-Skill closes 75%-95% of the teacher-student gap without touching model weights. After a single offline pass over the paired traces, D-Skill outperforms one-epoch SFT baselines and remains competitive with multi-epoch SFT. Under the same model family, the resulting student also incurs 5.7x-8.3x lower inference cost per task than the teacher. Our results demonstrate that natural-language skill distillation offers a performant, interpretable, and efficient alternative to weight-based capability transfer.
Huanzhi Mao, Yichuan Wang, Michael Koo, Wenyuan Huang, Huy Doan, Jinghan Xia, Ziyao Wang, Joseph E. Gonzalez
原文摘要
Vision-language model (VLM) agents that act in the open world need two abilities: world knowledge to interpret what they see, and exploration to find what they cannot yet see. We study how agents combine the two through interactive visual geolocation. GeoGuesser Bench contains 282 tasks in an offline Street View environment where agents rotate, zoom, and move between real panoramas. Its three task types shift the balance from knowledge to exploration: agents (1) report the coordinates of their starting location, (2) name the enclosing street, city, state, or country, or (3) find, read, and count nearby objects. The coordinate tasks in (1) also include 42 real GeoGuessr World Championship rounds, whose expert guesses provide a human reference. We evaluate 23 VLMs: the best accuracy is 62.5% on place naming and 35.0% on object finding, and the best agent averages 4352.4 GeoGuessr points on the championship rounds, against 4770.3 for the better expert in each round. Beyond these headline numbers, world knowledge and exploration are only weakly correlated across models: agents that localize well do not necessarily explore well. To understand where agents fail, we categorize their errors into vision, navigation, and tool-use failures. Further ablations show that the strongest agents, such as Claude Opus 4.8, still perform well with limited views, while weaker agents degrade; customizing the environment thus adjusts task difficulty. The environment's verifiable rewards and restorable state also support training, and our Planner-Worker-Compressor harness cuts planner tokens by 57-61% by compacting the interaction history. We hope GeoGuesser Bench and its environment serve as a high-quality foundation for simulating real-world exploration at scale.
Huanzhi Mao, Chengkun Cao, Shuo Yuan, Joseph E. Gonzalez
原文摘要
Large language models are increasingly capable of writing and executing code, suggesting a natural paradigm for tool-augmented agents: expressing tool use as programs rather than isolated calls. Programmatic tool calling (PTC) captures this idea through loops, batching, abstraction, and structured computation, but existing PTC approaches are largely stateless, limiting their ability to reuse intermediate results and adapt over time. This is problematic for real-world tasks, where tool environments and problem-solving processes are inherently stateful. We therefore present I-PTC, an interactive framework that executes stateful PTC: models issue code snippets that call tools, maintain reusable state, and evolve the tool interface through API corrections. To evaluate the effectiveness of I-PTC and the general PTC setting, we introduce PTC-Bench, a benchmark of long-tail, production-style user requests whose difficulty comes from large initial environments, many dependent API interactions, extended planning, and recovery across follow-ups and transient failures. Experiments on PTC-Bench show that I-PTC improves performance on complex multi-step tasks with large tool sets while substantially reducing token consumption over conventional tool-calling baselines and the original PTC baseline, highlighting stateful programmatic tool calling as a promising direction for scalable tool-augmented agents.
As robots and intelligent systems increasingly interact with humans, they must anticipate long sequences of future actions from only brief observations. While purely neural models typically require extensive observations to predict future actions and remain difficult to interpret and adjust, symbolic priors offer a structured alternative. To this end, we introduce SymAnt, a novel neuro-symbolic approach that unifies the expressiveness of neural networks with the structured reasoning of scene and knowledge graphs. Given a short video, SymAnt performs a joint-search over both graphs to construct a symbolic context, enabling unified reasoning over spatial relationships, object attributes, affordances, and associated actions. This symbolic context serves as a prior for an iterative refinement process that progressively generates and improves the sequence of future actions. By grounding predictions in symbolic context, SymAnt anticipates long-horizon actions from short observation windows in a parameter-efficient manner, while enabling users to directly edit the underlying knowledge to adjust predictions without further training. Through our experiments, we demonstrate the effectiveness of SymAnt, particularly when only short observation contexts are available, across five diverse datasets: Breakfast, 50 Salads, EPIC-KITCHENS, EGTEA Gaze+, and Assembly101.
Difficulty Calibration Across Time for Membership Inference in Diffusion Models
Michael Joseph, Yedid Hoshen
AI 速读 基于摘要
通过沿训练时间和扩散时间两个轴校准图像难度，提升扩散模型成员推理攻击的准确性。
cs.CV · cs.CR · cs.LG
查看原文摘要
Modern diffusion models are trained on massive datasets that often include copyrighted or private images. Membership inference attacks (MIAs) address this by testing whether a given image was in a model's training set. The standard approach scores an image by its reconstruction loss and flags low-loss images as members. This often fails because some images are simply easier to reconstruct than others, so a simple unseen image can score a lower loss than a complex training image. Difficulty calibration separates memorization from how difficult an image is to begin with. We show how to calibrate along two axes of time: training time and diffusion time. First, across training time, we introduce Reference-Model Calibration (RMC), which compares a fine-tuned model's loss against an earlier checkpoint. This cleanly isolates newly memorized data and gives near-perfect auditing, even without text captions. Since earlier checkpoints are not always available, we next present Temporal Self-Calibration (TSC), which calibrates across diffusion time using only a single model. Our key observation is that an image's difficulty persists across noise levels, whereas memorization is localized in time. By comparing the loss at a target timestep against neighboring timesteps from the same model, TSC attenuates image difficulty using the model's own trajectory. Empirically, our methods beat the state of the art by a wide margin, and unlike most existing attacks, generalize across different model parameterizations such as $x$-, $v$-, and $ε$-prediction models. Code is available at https://github.com/MichaelJoseph777/TSC.
In psychiatric practice, the clinical intake interview remains a primary diagnostic instrument, requiring the clinician to establish rapport while disentangling complex, overlapping presentations. Here, we show that multi-turn reinforcement learning (RL) in simulation environments improves language model performance on structured text-based psychiatric intake, spanning history-taking, differential diagnosis, and initial management planning. In a randomized, double-blind crossover study ($N = 60$ matched scenario pairs, 120 encounters) comparing the RL-trained agent against its identically prompted base model, 32 board-certified psychiatrists role-played standardized patients while a separate panel of 15 independent, board-certified psychiatrists scored the de-identified transcripts. The trained agent outperformed the base model in 76.7% of matched scenario pairs ($p < 0.0001$), with gains on an adapted clinical-examination rubric ($d_z = 0.77$, $p < 0.0001$), patient-centered communication (82.0% vs. 65.2%, $p < 0.001$), and differential diagnosis appropriateness (68.3% vs. 33.3%, $p < 0.001$). Across 127 psychiatrist-validated simulated intake scenarios, the trained agent nearly doubled its base model's clinical rubric score (0.706 vs. 0.379; composite reward 0.564 vs. 0.294, $p < 0.0001$). To systematically probe conversational safety, we established two Delphi-consensus taxonomies, of clinical safety risks and relational competencies, from which 256 challenging adversarial presentations were derived; we find that training in simulation environments more than halved under-triage of acute safety risks (12.9% vs. 30.5%, $p < 0.0001$). Simulation environments thus provide a controlled testbed for training and stress-testing psychiatric conversational agents, with gains that transferred to psychiatrist-enacted encounters, though residual gaps require safeguards and clinician oversight.
Carlo Saccardi, Rudolf Saathof, Geethu Joseph, Justin Dauwels
原文摘要
Statistical downscaling is the task of reconstructing high-resolution meteorological fields from coarse inputs. A principled approach formulates downscaling as a Bayesian inverse problem, using a diffusion prior over high-resolution fields and incorporating the coarse field only at inference through a likelihood. This decouples the prior from the coarse source, allowing one pretrained model to adapt to different sources. However, two challenges limit this flexibility: (1) when coarse and target fields come from different reanalysis systems, no fixed coarsening operator can capture their relationship; and (2) guidance gradients can differ by orders of magnitude across variables, making a single guidance strength ineffective. This paper addresses both challenges within the guidance loop, leaving the prior unchanged. We learn the forward operator from paired data and normalize the gradient per channel. We show that this normalization corresponds to steepest descent under a block-max norm, allowing a single guidance strength across variables. Our code is publicly available at https://github.com/CarloSaccardi/operator-aware-weather-downscaling.
Joseph Walusimbi, Ann Move Oguti, Joshua Benjamin Ssentongo, Keith Ainebyona
原文摘要
Artificial intelligence and large language models (LLMs) are transforming educational technology by enabling conversational tutoring, personalised explanations, and inquiry-driven learning. However, most AI-based learning systems rely on continuous internet connectivity and cloud-based computation, limiting their use in bandwidth-constrained environments. This paper presents Arapai, an offline-first large language model architecture designed for AI-assisted learning in low-connectivity settings. The system performs all inference locally using quantized language models and incorporates hardware-aware model selection to enable deployment on low-specification, CPU-only devices. By removing dependence on cloud infrastructure, the system provides curriculum-aligned explanations and structured academic support through natural-language interaction. To support learners at different educational stages, the system includes adaptive response levels that generate explanations at varying levels of complexity: Simple English, Lower Secondary, Upper Secondary, and Technical. The system was evaluated with 120 students and 9 instructors from secondary and tertiary institutions under limited-connectivity conditions. Results indicate stable operation on legacy hardware, acceptable response times of 1-3 seconds for typical queries, and positive user perceptions of its effectiveness in supporting self-directed learning.
We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context understanding, and agentic workloads. Super is a 120B-parameter, 12B-active multimodal model, while Lightning is a smaller 30B-parameter, 3B-active text model; both designed for efficient deployment. Both models combine large-scale distillation, long-context training, and native speculative decoding, while Super further incorporates Indic continued pretraining and agentic software-engineering mid-training. We develop a comprehensive post-training pipeline spanning supervised fine-tuning and reinforcement learning (RLVR and RLHF), complemented in Super by specialized teacher training and multi- teacher on-policy distillation (MOPD). This transforms Super from a text-only base model into a multimodal agent capable of reasoning over text, images, video, and interactive tool environments. We further explore test-time scaling through parallel agent execution and self-verification. Across training and deployment, we jointly optimize capability and efficiency. Indic continued pretraining improves Indian-language benchmarks by up to 9.82 percentage points, while agentic mid-training strengthens software-engineering capabilities and robustness across agent harnesses. The post-trained Super model achieves 51.78% on SWE-bench Pro, surpassing Nemotron 3 Ultra despite using approximately 4.6x fewer active parameters. Post-training MTP boosting improves speculative- decoding acceptance length by up to 21.8% under probabilistic draft sampling, while NVFP4 quantization achieves 99.62% median accuracy recovery relative to BF16. Inference optimizations enable up to 4,856 output tokens/s/GPU on GB200 while sustaining at least 50 tokens/s/user.
Joseph O'Leary, Tapio Simula, Tom Kimpson, Corey Davey, Wenchao Li, Andrew D. Greentree, Allison Kealy
原文摘要
Airborne magnetic anomaly navigation provides a passive, unjammable alternative to Global Navigation Satellite Systems positioning by matching magnetometer measurements against a lithospheric magnetic anomaly map. Existing map-matching algorithms either assume a Gaussian posterior (extended Kalman filter), require Monte Carlo sampling (particle filter), or discard posterior uncertainty in favour of a single optimal path (Viterbi algorithm). Here we formulate map matching as inference on a chain-structured factor graph and solve it segment by segment using the forward-backward algorithm, which yields a discrete posterior over candidate positions and its Shannon entropy $H_t$ at time $t$. Over the \texttt{Renfrew\_395} map, $10^3$ synthetic trials yield a median position error of $32.7$ m, $91\%$ below the median inertial drift of $362$ m. On these trials and $10^3$ flight paths, the median error is $43\%$ below the extended Kalman filter and particle filter. Across these paths, a threshold on segment-level entropy detects $47\%$ of segments with errors above two map cells and $94\%$ of those above three, at a $10\%$ false-alarm rate. The foregoing results indicate that $H_t$ provides a truth-free diagnostic of map-conditioned navigation ambiguity.
Alexander Nikitas Dimopoulos, Joseph Grasso, John Beltz
原文摘要
Indoor environments lack the spatial intelligence infrastructure that GPS provides outdoors; first responders arriving at unfamiliar buildings typically have no machine-readable map of safety equipment. Prior work on 3D semantic segmentation for public safety identified two barriers: scarcity of labeled indoor training data and poor recognition of small safety-critical features by native point-cloud methods. This paper presents INSIGHT, a zero-target-domain-annotation pipeline that projects 2D image understanding into 3D metric space via registered RGB-D data. Two interchangeable vision stacks share a common 3D back end: a SAM3 foundation-model stack for text-prompted segmentation, and a traditional CV stack (open-set detection, VQA, OCR) whose intermediate outputs are independently inspectable. Evaluated on all seven subareas of Stanford 2D-3D-S (70{,}496 images), the pipeline produces Pointcept-schema-compatible labeled point clouds and ISO~19164-compliant scene graphs with ${\sim}10^{4}{\times}$ compression; role-filtered payloads transmit in ${<}15$\,s at 1\,Mbps over FirstNet Band~14. We report per-point labeling accuracy on 7 shared classes, detection sensitivity for 15 safety-critical classes absent from public 3D benchmarks alongside code-capped deployable estimates, and inter-pipeline complementarity, demonstrating that 2D-to-3D semantic transfer addresses the labeled-data bottleneck while scene graphs provide building intelligence compact enough for field deployment.
Pre-training foundational models is computationally expensive as models scale. In this work, we introduce Bi-Phase Training (BPT), a parameter-efficient pre-training method that preserves the high-rank learning dynamics observed in full-parameter optimization with substantially reduced trainable parameters. BPT parameterizes each weight update as a composition of constrained high-rank left/right transformations via trainable diagonal matrices and low-rank adapters whose updates are periodically merged into the frozen base weights, resulting in a compounding expansion of accessible directions during training. Across language-model pre-training from scratch (Qwen2.5 models from 100M to 1.5B parameters and OLMo-2-1B) on FineWeb-Edu (10B and 100B tokens), BPT achieves validation perplexity close to full-parameter baselines while using far fewer trainable parameters; e.g., at the 1.5B scale, BPT uses 66% fewer trainable parameters with only a small validation-perplexity gap. Additionally, a comprehensive evaluation across diverse downstream tasks shows that BPT preserves much of the full-parameterized model's downstream performance.
A targeted adversarial perturbation can drive a vision-language model's (VLM's) teacher-forced training loss for a fixed target caption to near zero, yet the same model, allowed to generate freely, produces the original, correct description with no trace of the target. We call this dissociation the train/inference gap, and give it a precise mechanistic account on Qwen2.5-VL-7B-Instruct using a controlled two-stage PGD attack on 200 held-out COCO images. First, we show that image-level pixel statistics, including a correctly re-implemented, texture-based attackability measure from the CNN robustness literature, have essentially no predictive power over which images are corrupted (best predictor r=-0.050, p=0.484; ridge regression R^2=0.069). Second, using the logit lens, we localise the gap to a single autoregressive step: the rank of the target token, conditioned on the correct first token already being generated, is fixed at exactly 3,488 out of 152,064 vocabulary entries for every image and every condition, with zero variance. Third, tracking target-token rank across all 28 LLM decoder layers reveals that the visual encoder corrupts every image's representation by a comparable margin regardless of eventual outcome, but the language model decoder then differentially arbitrates: amplifying the corrupted signal for susceptible images and actively suppressing it, past its clean-image baseline, for resistant ones (p<0.001, rank-biserial r=0.579). A linear probe on the merger hidden state separates these two outcomes with AUC=0.858, though we flag a circularity concern in this estimate. Together these results argue that adversarial robustness in autoregressive VLMs is substantially a property of the language decoder's prior, not the visual encoder, with direct implications for where faithfulness evaluations and defenses for deployed VLM systems should be targeted.
Chenyi Huang, Arun Josephraj Arokiaraj, Bin Wu, Sahan Bulathwela
原文摘要
Every study of why LLM agents fail begins by labelling traces by hand, and every such study builds its own throwaway tool. Observability platforms record agent traces but offer no structured labelling; annotation tools label text but have no notion of a step, a delegation or a tool call, leaving it unclear what the smallest unit of execution to label should be. Annotrace reads six trace formats, including OpenTelemetry GenAI, LangSmith and Langfuse, and turns each run into an ordered, nested list of steps. The annotator writes their own labelling codebook; a frontier model proposes a starting set from a sample of their own traces, answers first, and is asked exactly the questions the human is asked, making annotation a joint human-AI process. Annotrace measures agreement between any two annotators, human or AI. On a multi-agent question-answering corpus it reproduces a previous manual effort's 235 annotation units exactly, and two models labelling the same traces agree 91% of the time at $κ= 0.82$.
Tudor Braicu, Joseph DelPreto, Jared Boyer, Mónika Farsang, Maximilian Stölzle, Tim Niklas Seyde, Daniela Rus
原文摘要
Agile robots require spatiotemporal intelligence to interpret scenes, reason about interactions, and anticipate future events. Yet it remains unclear how well foundation vision models support these capabilities, particularly from a moving egocentric camera, which is a natural view for robots. To investigate this, we collect an annotated tennis dataset and train a suite of vision models on spatiotemporal tasks. Our dataset contains egocentric video synchronized with five allocentric videos, estimated global positions, labeled contact times, and annotated stroke types. We then evaluate seven prediction tasks from egocentric images: 2D ego player and 3D ball localization, future player and ball trajectories, forehand or backhand stroke anticipation, time to the next ego player ball contact, and 3D ball position at that contact. We compare image encoders, video encoders, and vision-language models with jointly trained prediction heads. The best performing models achieve mean current-frame localization errors of 0.14 m for the ego player and 0.54 m for the ball, future forecasting errors of 0.34 m for the ego player and 0.91 m for the ball over 1.1 s, and a mean contact-time prediction error of 0.14 s. Auxiliary depth information substantially improves 3D ball localization, suggesting that inferring metric depth remains a challenge. Longer image histories do not improve ball forecasting, indicating that representations exploit scene context rather than rely solely on inter-frame motion. Finally, we propose a conditional diffusion model to generate whole-body kinematic tennis motion from vision encoder predictions on egocentric video at real-time rates, adapting movements as predictions are refined. These results move towards a deeper understanding of how foundation vision models can support real-time dynamic robots using egocentric video.