Papers

Generating a correct answer does not mean that a language model will select it. We separate factual recall into three steps: generating a correct candidate, ranking the available candidates, and selecting the final answer. Pre-generation readouts predict factual recall and which questions sampling will cover across three model families, but say little about whether an available correct answer will ultimately be selected. Explicit verification with $P(\mathrm{True})$ improves within-question ranking over mean log-likelihood in Gemma, Qwen3, and Llama, with AUROC gains of $0.08$–$0.12$. In a prospectively defined Gemma cohort, verification raises plurality accuracy by about $5$ points, and still gains about $2$ points over chat-template likelihood, a stronger generative baseline. The advantage is strongest for relations with common-answer priors and depends on access to the entity; masking the entity removes the ranking advantage in larger Qwen models. Finally, the measured benefit depends on how correctness is defined: recall-oriented reference matching can credit option lists favored by likelihood and substantially understate the improvement seen under human semantic judgments. Prior work shows that models can carry latent factual knowledge and judge candidate answers; we show that these capabilities do not collapse into a single notion of “knowing,” and trace where information is gained, lost, or mismeasured between availability, ranking, and final choice.

Agentic AI is increasingly being embedded in software applications to provide natural language interfaces to features and functionality. In most cases these agents are powered by enterprise (100+ billion parameter) or frontier class large language models that require substantial computational resources run and depend on cloud hosted inference to handle the task of transforming natural language inputs into actionable software operations. This reliance on cloud-hosted inference introduces substantial network latency on top of LLM inference times, creates data privacy concerns, and, given the costs of running these models, can rapidly escalate expenses associated with supporting agentic features. This paper introduces a novel means of converting the NL-to-Action problem from a generative one into a classification-centric formulation via on-device operation caches. These caches allow an agentic system to handle frequently occurring classes of actions completely on-device – reducing latency, enhancing privacy, and lowering operational costs. We show that for a classic NL-to-Formula task, generating Excel Formula in response to user requests, this approach reduces total inference cost by 56% when compared to cloud-only model-routing based inference and, on cache hits, reduces the latency to response latency by 5x.

Recovering physical properties of unknown objects through non-prehensile interaction is challenging because no single manipulation primitive reveals all relevant parameters. Planar pushing couples mass and friction, while conventional tipping cannot recover friction and may fail entirely when low-friction or curved-base objects slide or rotate instead of tipping. We introduce a multi-modal estimation framework that combines a sliding interaction with a press-and-pull tipping primitive to recover object mass, center of mass height, and surface friction. The press-and-pull interaction increases the object-table sliding threshold and stabilizes the pivot, enabling controlled tipping without any prior geometric object model. Wrist force/torque sensing, RGB-D perception, and robot proprioception are fused to estimate the physical parameters from the two complementary interaction modes. Experiments on an ABB IRB120 across four objects with varied geometry, mass, center of mass, and friction achieve low relative error, while successfully operating on curved-base objects that fail under conventional forward tipping. The results demonstrate that complementary non-prehensile interactions can recover a compact set of physical parameters without grasping, a prior object model, or learned interaction dynamics.

On-policy distillation (OPD) trains a student to match a teacher's next-token distributions on student-generated trajectories. However, privileged information supplied to the teacher for OPD training may contain sensitive data. Whether the student leaks private information about the records supplied to the teacher during distillation remains poorly understood. To the best of our knowledge, we present the first systematic study of membership inference in this setting. We find that fresh student trajectories expose sparse membership signals that fixed reference-answer losses often miss. These signals are mixed with probability changes caused by training on other records. We introduce Leaky, which samples fresh trajectories from the target model and compares its token log-probabilities with the maximum across matched reference models trained without the candidate records. It applies Leaky ReLU to the resulting gaps, preserving positive gaps and downweighting negative gaps as an approximate correction for incidental positive gaps in non-members. Across fifteen targets spanning mathematics, medical question answering, and code generation, Leaky outperforms all evaluated baselines and achieves mean AUROC 0.875, compared with 0.614 for the strongest baseline on each target in the main evaluation. On the same sampled trajectories, the strongest baseline achieves mean AUROC 0.826. These results show that students trained through OPD can expose the membership of records used for teacher supervision, even when fixed reference-answer losses provide little evidence of membership.

Long-context LLM inference pushes modern GPU serving stacks into an attention-bound regime, where both compute and memory are dominated by the softmax-GEMM pipeline. On NVIDIA Blackwell GPUs, FP4 Tensor Cores offer high matmul throughput, but we find that fully FP4 attention often fails to translate this throughput into end-to-end speedups due to non-matmul costs: online quantization after softmax, tensor/shared-memory data movement, and contention on the softmax path. We present MpFA, a training-free FlashAttention kernel optimized for Blackwell. Guided by hardware characterization, MpFA uses mixed precision: NVFP4 for QK and FP8 for PV (QK4PV8). This preserves low-bit QK throughput while avoiding the conversion and scaling overheads of FP4 PV. To recover accuracy without further stressing the softmax pipeline, MpFA introduces rank-one smoothing compensation implemented as an additional Tensor Core MMA. MpFA further improves performance with a fine-grained asynchronous pipeline, tensor-memory reuse, and adaptive parallel partitioning across prefill and decode. On an NVIDIA B200 and across 16K-128K contexts, MpFA improves prefill throughput over state-of-the-art BF16/FP8 baselines and increases end-to-end output throughput by 2.81$\times$ over BF16 FA4 across Llama-3.1-8B and Qwen3-14B. Across five benchmark suites and two models, rank-one compensation recovers 62.5% of the accuracy loss with about 2.0% kernel overhead.

Reasoning models generate long chains of thought before they answer, yet it is debated whether the content of these chains does real computational work or is largely decorative. We study this question by viewing a transformer as a shallow circuit. One forward pass through a fixed number of layers has constant depth, so any procedure that runs the model a constant number of times is a shallow circuit. We call the best accuracy that a shallow circuit can reach on a task the ceiling of the task, and a task is serial if its ceiling lies below one. We prove three results on serial tasks that hold for every transformer, no matter how it was trained. Necessity: replacing the chain by anything that does not depend on its content, such as filler tokens or a restatement of the question, drives the accuracy down to the ceiling, and on a maximally serial task down to chance. Depth: no shallow computation can write the chain of a model whose accuracy exceeds the ceiling, not even approximately. Locality: the answer is one shallow pass away from the finished chain, so all of the serial reasoning happens in the chain. On word problems of finite groups, whose ceilings are known, small transformers trained from scratch, with or without reinforcement learning, attain the predicted numbers: chain-trained models solve every input length and fall to chance when the chain is erased, chainless models collapse to the ceiling as the input length grows, and open-weight reasoning models given the same problem in words return to the baseline without their chain. On MATH-500 and AIME, erasing the chain costs open reasoning models 0.52 to 0.82 accuracy, a sentence shuffle is harmless, and a token shuffle is as harmful as erasing; the same holds for checkpoints trained by GRPO with a correct or a random reward. The ceiling of a task therefore answers when a transformer can succeed without its chain of thought.

Training long-context LLM policies with RL requires re-evaluating groups of sampled responses under the updated policy, an update-stage attention workload that differs sharply from pre-training: each group shares one long prompt that fans out into multiple response branches. Standard context parallelism (CP) flattens each prompt–response pair into a linear sequence, so the same prompt key–value (KV) states are recomputed—or repeatedly rotated through the network—once per response branch. We present AugTree, a CP execution scheme built around this replay stage. AugTree separates the replay into two phases: a prompt-prefill phase that computes the shared prompt KV state once, and a response-replay phase that schedules the independent response branches over a bounded set of replay lanes. The replay phase instantiates two communication semantics, chosen by a lightweight online planner that enumerates CP degrees, schedules, and placements before GPU dispatch: rotating KV shards within response-local lanes when responses dominate, and moving response queries to stationary prompt-KV owners with a partial-softmax reduction when prompts dominate. The shared prompt state remains fully differentiable—response losses backpropagate into it and the accumulated prompt gradients propagate through the original prefill graph—so AugTree preserves exact training semantics rather than performing detached, inference-style KV caching. On four real post-training workloads and up to 64 accelerators, AugTree improves average training-stage step time by 1.18$\times$ over dynamic CP (up to 2.23$\times$), 2.63$\times$ over a Megatron ring CP baseline with prompt reuse, and 7.08$\times$ over the baseline without reuse.

Recent advances in quantum computing are opening new opportunities for computationally intensive decision problems. This paper studies how quantum computing can improve Monte Carlo tree search (MCTS) in the fixed-confidence setting, where the goal is to identify a near-optimal move in a given game tree with high probability while minimizing query complexity. We first formulate MCTS under a quantum oracle model. We then develop a quantum MCTS algorithm (QMCTS) that combines threshold-based elimination on the search tree with quantum Monte Carlo estimation to reduce the cost of evaluating stochastic leaf values. We establish an instance-dependent lower bound on the query complexity and derive a corresponding upper bound for QMCTS. The lower-bound analysis introduces a new quantum phase-testing result that may also be useful beyond MCTS. We validate the theoretical results through simulation experiments and further demonstrate the feasibility of QMCTS on real quantum hardware.

Black-box Optimization (BO) is a powerful framework for optimizing expensive objective functions or unknown functions with a limited number of evaluations. A central step of standard BO such as Bayesian optimization is the optimization of a surrogate-based acquisition criterion, which is commonly performed using nonlinear optimization or heuristic search. Therefore, conventional black-box optimization generally does not guarantee global optimality in candidate selection. In this study, we propose Integer Linear Programming-based Black-box Optimization (ILP-BO), a quasi-Bayesian optimization framework that transforms kernel-based surrogate optimization over discrete domains into an Integer Linear Programming (ILP) problem. The key idea is to represent nonlinear kernel functions exactly on finite discrete distance levels by introducing binary one-hot auxiliary variables. This transformation converts the nonlinear surrogate into a linear objective with linear constraints and binary variables. To incorporate exploration while preserving the linear structure, we further introduce a Hamming-distance margin that excludes neighborhoods around previously observed points. We derive the proposed formulation for several standard kernels and obtain an analytical upper bound on the Hamming-distance threshold based on the measure in the binary search space. The resulting candidate-selection problem can be solved by integer programming solvers with certificates of optimality. Thus, our methodology has the potential to serve as a highly transparent black-box optimization framework. Experiments on synthetic and discrete optimization benchmarks show that ILP-BO achieves competitive optimization performance compared with practical Bayesian optimization methods.

As the bridge between protein modality and discrete modeling, protein structure tokenization still largely relies on heavily engineered training objectives tailored to specific downstream tasks and large training datasets, which hinders its transfer to broader application scenarios. To address this issue, we propose ProFiT, a lightweight flow matching tokenizer. With simple training strategies that encourage healthy codebook utilization, ProFiT can be trained efficiently and naturally learns semantically meaningful representations without any manual semantic alignment, while achieving reconstruction quality and generalization that match or surpass those of substantially larger tokenizers. We conduct extensive evaluations across a wide range of settings and demonstrate that ProFiT is a plug-and-play tokenizer adaptable to diverse downstream tasks. This study further reveals the significant potential of the flow matching tokenizer paradigm. Our code is publicly available at https://github.com/QDKStorm/ProFiT.

Hyun, Kim, Wu and Yue constructed optimal and minimal binary linear codes from order ideals of hierarchical posets with two levels. Two different generalizations of the underlying antichain (simplicial complex) setting to odd characteristic are known: down-sets of $\mathbb{F}_p^n$ under the componentwise order, and support-closed subsets of $\mathbb{F}_q^m$. No generalization of the poset setting itself has appeared. We introduce generalized order ideals of a poset of order $p-1$, obtained by attaching multiplicities in ${0,\dots,p-1}$ to the elements of a poset, and study the two natural notions of order ideal that arise for hierarchical posets with two levels. Whenever the ideal meets the upper level, the resulting defining sets are neither down-sets nor support-closed. We determine the weight distributions of the associated complement codes, exhibit a family of Griesmer codes in which the upper element carries an arbitrary multiplicity, and, via the characteristic function of a generalized order ideal, obtain an infinite family of minimal $p$-ary codes of length $p^n-1$ and dimension $n+1$ violating the Ashikhmin–Barg condition.

Offline-to-Online Reinforcement Learning (O2O RL) has emerged as a practical paradigm that pre-trains the policy using static offline datasets and subsequently adapts the policy through online interactions. Existing O2O methods primarily address the transition through value calibration, while generally treating the offline-trained policy as a given initialization. We instead study O2O adaptation from the perspective of network plasticity, asking whether the offline-trained policy remains sufficiently adaptable for online learning. Controlled experiments show that prolonged optimization on static offline data progressively reduces network plasticity even after offline performance has largely saturated, and that lower plasticity is associated with weaker subsequent online improvement. Motivated by these observations, we propose REstoring plasticity via Fresh Initialization and policy Transfer (REFIT), a lightweight model-level method for the O2O transition. Before online fine-tuning, REFIT distills the offline policy into a freshly initialized student while temporarily freezing a random subset of student units, transferring the learned offline behavior to a more plastic policy initialization. Extensive experiments on D4RL and OGBench demonstrate that REFIT consistently achieves higher aggregate performance than existing O2O plug-in methods across both Cal-QL and IQL backbones, while plasticity diagnostics and ablations provide further evidence of restored network plasticity.

Group-relative reinforcement learning (RL) relies on reward variation among sampled responses to estimate informative relative advantages. As language models become increasingly capable, existing training data can become reward-saturated: all sampled responses to the same problem might receive equally high rewards, where the group-relative learning signals vanish and leave previously useful data obsolete. In this work, we investigate whether useful learning signals can be recovered from such saturated data. We study interventions at four levels of group-policy RL pipelines—data, rollout, reward, and advantage—and conduct extensive RL training on saturated reasoning data only. While standard GRPO on saturated data would almost always yield near-0 advantages and near-noise signals, diverse interventions successfully recycle and repurpose such data: among the proposed strategies, interventions at rollout generation are consistently most effective: nudging the policy to generate “high-quality”, incorrect solutions introduces rollouts with poor rewards into saturated groups as negative samples, which turns out to improve GRPO by 6.4% to 9.0% across Qwen3-1.7B and 4B. Other interventions such as increasing rollout temperature or adding auxiliary rewards can also restore non-zero advantages, but yield less consistent gains. Further analyses show that effective negative rollouts require informative negative trajectories, that the method remains effective alongside unsaturated data, and that it supports iterative recycling of newly saturated examples. While increasingly stronger LLMs would render more data as saturated, our results demonstrate that don't waste your saturated data: with the right strategies they can be recycled into useful RL training signals in an increasingly data-scarce world.

Co-training offers a straightforward way to build a multi-task vision-language-action (VLA) policy, but can fall short of the performance achieved by training each task independently. The challenge is to retain these task-specific gains in a multi-task policy without joint post-training. Combining independently trained experts through model merging is a natural approach, yet strong individual experts do not necessarily yield a strong merged policy. We identify one source of this incompatibility: task-specific changes to the action interface, comprising action normalization and the action encoder and decoder. We propose PolicyWeave, combining merge-compatible post-training with context-guided sparse merging. During post-training, all experts retain the common base policy's action interface, while task adaptation is restricted to LoRA updates in the hidden layers of the action model. This makes the experts more compatible with existing model merging methods. However, merging all experts can still introduce interference from unrelated tasks at deployment. PolicyWeave scores each expert's LoRA updates using the initial visual-language context, determines the expert set through leave-one-layer-out ranking stability, and forms a sparse weighted merge of the selected updates that remains fixed for current task. We evaluate PolicyWeave with GR00T N1.5 on 18 RoboCasa365 tasks, using only 10% of the target-task demonstrations for supervised fine-tuning (SFT). Preserving the shared action interface raises the average success rate across four static merging methods from 17.0% to 52.8%. PolicyWeave achieves 64.7% success with these SFT experts and 74.1% after task-specific reinforcement learning (RL), compared with 60.7% for joint RL. Further evaluations on LIBERO-10 and an AgileX Piper arm support the deployment of independently learned skills in long-horizon and real-world manipulation.

Self-evolving agent harnesses continually update persistent components such as memory, prompts, skills, and tools. We call this process harness evolution. However, such evolution could introduce unexpected safety risks. Existing work studies harness misevolution and validates candidate harnesses or attributed individual component updates, leaving safety analysis of cross-component update interactions largely unexamined. To address this gap, we study compositional safety failures in harness evolution, where interactions among individually safe and utility-preserving component updates can produce undesirable or unsafe agent behavior, revealing a safety risk intrinsic to harness evolution. Across three safety-related benchmarks, we identify 43 pairwise and 18 irreducible 3-way compositional safety failures. Conventional solution incurs combinatorial complexity in validating cross-component interactions, leaving the safety checking impractical as the harness evolves. To solve this, we introduced a typed hypergraph that represents component states as nodes and safety-relevant higher-order interactions as hyperedges. When the harness changes, the hypergraph updates only the interaction neighborhood of the changed states rather than reconstructing the global composition space. Building on that, we develop a hypergraph-guided runtime monitoring mechanism. Experiments show that our method effectively mitigates compositional safety risks while preserving task utility and reducing interaction-checking costs, and further reveal an empirical safety-utility-cost trade-off across different safety mechanisms.

Computational methods have consistently struggled to determine the dominant temporal orientation of a sentence. This difficulty is especially pronounced when a sentence contains multiple embedded clauses with competing tense and aspectual information. To address this difficulty, we propose an alternative approach for identifying a sentence's past, present, or future global reference interval. Our method does not use any form of pretrained embeddings. We rather encode sentences using fixed-length inventory vectors that are comprised of part-of-speech counts, dependency relation counts, and explicit futurate pattern counts. We term this inventory vector of a sentence a "Morphosyntacton". The method does not use any padding, sequence models, or large language models. Evaluation on 1,799 syntactically complex English sentences, annotated as past, present or future, shows balanced and high accuracy multiclass classification, achieving an overall multi-class accuracy of 92%.

Electrical distribution grid operations require inference across heterogeneous networks from sparse, noisy, and incomplete time series measurements. In this work, we identify challenges and explore solutions towards a unified model that can perform diverse tasks grounded in the physics of the electric grid and generalize to unseen distribution networks. We define a unified grid ontology that represents variable sized distribution networks as heterogeneous graphs while preserving native topology, asset types, and electrical relationships across networks. We develop a physics based data simulation pipeline that combines reference and procedurally generated distribution networks with network reconfigurations, fault scenarios, and configurable sensing conditions. We present Mycelium, a heterogeneous graph transformer with structure aware communication edges and electrical reference features that encode network position and nominal phase orientation, together with task specific temporal readouts which generate per task outputs. We train Mycelium on reference as well as synthetic grids, and study its generalization on benchmark networks completely excluded from training and validation. Mycelium is observed to outperform task specific neural baselines on most reported benchmark metrics. Architectural ablations and the aforementioned studies reveal Mycelium's capability to learn representations of the underlying physics which serves to enhance cross-task performance, thereby addressing a significant challenge in unified grid models.

Medical question answering spans diverse specialties and modalities, and individual medical large language models (LLMs) exhibit distinct strengths across tasks and domains. This heterogeneity suggests that combining specialists may enable broader coverage of medical questions than relying on any single model. However, existing LLM routing methods primarily seek to balance answer quality and inference cost, leaving open how to exploit differences in specialist competence to improve medical reasoning. In this paper, we introduce MedRouter, an agentic system that uses an embedding-based multi-label router to select and query specialist LLMs, then passes their responses to a generator to produce the final answer. We further propose SCALE (Specialist Competence-Aware Learning), a two-stage training framework that first trains the Router with specialist correctness supervision and then optimizes its selections through reinforcement learning. The second stage uses a Performance Gain Reward (PGR) that measures how specialist information affects the generator's answer correctness relative to answering without that information. Experiments on eight text-based and multimodal medical QA benchmarks show that MedRouter outperforms the strongest routing baseline by 8% in average accuracy. Our analysis of specialist outputs further reveals distinct strengths and complementary question-level coverage, motivating learned routing to combine these capabilities for more comprehensive medical reasoning.

Multimodal large language models (MLLMs) can now interpret a standard ten-second, twelve-lead electrocardiogram (ECG) with clinically grounded, reward-verified reasoning. Real cardiac monitoring is different. Ambulatory (Holter) and telemetry recordings span hours to days and are read as they stream in, and their clinically decisive findings are paroxysmal, brief episodes buried in an otherwise unremarkable trace. Such a recording cannot be held in one context at diagnostic resolution, and its future has not yet happened, so a reader must work online, deciding what to measure now, committing evidence to memory as it passes, and reporting events as they occur. We recast long-duration ECG interpretation as a long-horizon, online (streaming, causal) sequential decision process and introduce ECG-Scroll. As a benchmark, long ambulatory recordings are streamed to an agent chunk by chunk, and it must localize, quantify, and promptly flag paroxysmal events without access to future signal; because the underlying signal is retained, every answer is checkable against objective ground truth, giving rule-based rather than judge-based rewards, and the streaming formulation adds a metric batch evaluation cannot express, the detection latency between an event's onset and the moment the agent records it. As an agent environment, it is a fixed, gym-style interaction layer that exercises three competencies single-glance ECG models never touch: Memory, Tool use through signal-grounded measurement rather than reading pixels, and Planning of what to measure now and when to commit. We release 390 whole-recording instances spanning 2,536 hours of two-lead ambulatory ECG and evaluate a signal-threshold rule agent alongside off-the-shelf LLM agents online, characterizing how they use memory, tools, and planning and where the benchmark's head-room lies.

General Game Playing across arbitrary games from rules alone remains challenging due to differing algorithmic requirements across game classes and strict decision-time constraints. Rather than hand-designing search heuristics for specific domains, can we leverage Large Language Models (LLMs) to discover general game-playing algorithms? Because language models can propose and refactor structured code, they provide an expressive proposal engine for exploring the space of algorithmic designs. We introduce a multi-agent LLM meta-learning system to co-evolve game-agnostic procedural search mechanisms in C++ alongside domain heuristics synthesized directly from game rules. Controlling the compute budget, we benchmark the discovered mechanisms across more than 400 diverse environments, including OpenSpiel training and held-out games, procedural simulation engines, and games with deep neural policy-value representations trained via PPO. Evaluated via AlphaRank stationary distributions and Soft Condorcet Optimization (SCO) against 15 established MCTS baselines, the discovered search mechanisms consistently achieve top-tier ratings and pairwise ballot majorities over most baselines across independent evolutionary runs, generalizing to unseen human-designed and procedurally synthesized games and remaining competitive with baselines on frozen neural network representations.

For decades, statistical inference has largely been developed one problem at a time. Given a scientific target, such as a treatment effect or a regression function, statisticians design a problem-specific estimator together with a procedure for quantifying its uncertainty. This paper proposes a different paradigm. We focus on a classical problem in statistical inference, confidence interval construction, and develop TabCon, an amortized inference system built on a tabular foundation model that produces confidence intervals for new datasets through a simple forward pass. The key methodological ingredients of TabCon are a sparse mixture-of-experts architecture and reinforcement-learning-based post-training that calibrate the resulting confidence intervals to a desired coverage level. Across a wide range of benchmark datasets, TabCon attains near-nominal coverage while producing short confidence intervals. At inference time, it also offers considerably greater computational efficiency, running 50 times faster than the classical bootstrap procedure, even when the latter uses only 50 bootstrap samples.

As coding assistants become increasingly autonomous, developers run multiple sessions in parallel, shifting the challenge from code generation alone to coordinating and monitoring concurrent agent work. Through a formative study (N=14), we identified PILOT: five supervisory practices for Planning, Isolating, Logging, Observing, and Triaging parallel sessions. We present ParallelPilot, a design probe that instantiates PILOT through a planning interface, a run-logger, and an ambient dashboard alongside existing coding tools. In a counterbalanced within-subjects study (N=16), participants using ParallelPilot increased ticket throughput by 63% in short coding tasks and supervised an average of one more concurrent agent at peak, while their tracking effort and context switching dropped. ParallelPilot also clarified execution plans, task dependencies, and intervention cues, and 14 of 16 participants preferred it over their current setup. These gains were not accompanied by significant improvements in perceived control or perceived success in redirecting the agents. Our findings demonstrate the value of explicit supervision support and position PILOT as a scaffold for designing tools that help people supervise concurrent work within and beyond coding. We suggest that future coding assistants should pair high-level awareness with low-cost paths back to the implementation evidence developers need to judge and steer agent work.

Gaussian process stochastic differential equations (GP-SDEs) provide a flexible Bayesian model for unknown continuous-time state dynamics with uncertainty quantification, but learning and inference from noisy and irregular observations remain computationally challenging. To address this issue, we propose GP-SDE Matching, a simulation-free variational framework for Bayesian GP drift learning and continuous-time state smoothing. We analytically marginalize the sparse GP posterior to derive a tractable drift-matching objective that accounts for both the posterior mean and uncertainty of the unknown drift. To handle irregular observations, we further introduce an irregular-time-aware variational state posterior that incorporates the actual observation times during both encoding and continuous-time marginal querying. Experiments on the stochastic Lorenz–63 system demonstrate substantially improved drift recovery and state reconstruction under irregular observations, while five system identification benchmarks show robust forecasting under increasing observation sparsity and competitive performance against existing latent-SDE and state-space methods.

Joint-Embedding Predictive Architectures (JEPAs) provide a framework for learning compact representations without directly reconstructing high-dimensional observations. However, in parameterized physical systems, learned representations can entangle geometry with operating conditions and task-specific physical responses, limiting their reuse across prediction tasks. We introduce D-JEPA (Design-recoverable JEPA), a geometry-centric JEPA that computes a compact representation from geometry alone and reuses it across operating conditions and physical response spaces through lightweight physics-specific decoders. An explicit design-recoverability objective encourages the geometry latent to preserve information about the underlying design variables, enabling the representation to support design analysis and optimization. We further identify a case-level collapse failure mode in which target representations become nearly invariant across distinct geometries despite low reconstruction error, and mitigate it using case-level variation constraints and auxiliary target reconstruction. Across four 3D aerodynamic, hydrodynamic, and structural benchmarks, D-JEPA maintains or improves full-field prediction accuracy while achieving near-perfect linear recoverability of design parameters. The frozen geometry representation can be reused at held-out operating conditions and transferred to a structural response task with fewer trainable parameters. Finally, the representation supports differentiable design optimization, with designs validated using high-fidelity CFD, preserving the predicted ranking of candidate designs. These results demonstrate that separating a reusable geometry representation from physics-specific prediction provides a practical representation for scientific surrogate modeling and design.

Grounding is a core capability of spatial vision-language models, yet most existing work focuses only on where a referred object is. Many 3D tasks also require knowing how it is oriented. Although existing 3D VLMs may predict oriented boxes, box pose does not explicitly capture object-centric orientation or symmetry-induced ambiguities. We introduce orientation grounding, a referring grounding task that predicts an object's 6D orientation and axial symmetry from a language or box query in single-view or multi-view scenes. To support this task, we construct ReferOri, with 331K multi-view and 387K single-view orientation-grounding queries obtained through scalable reconstruction, consistency checking, and human verification. We further present OG-VLM, which adapts a 3D VLM with structured box/orientation outputs, sign and symmetry tokens, and geometry-aware auxiliary losses. Across single-view and multi-view benchmarks, OG-VLM substantially outperforms orientation-aware VLM baselines and surpasses object-level orientation foundation models on scene-level referring benchmarks, showing that explicit orientation grounding is a distinct and learnable capability beyond localization. Downstream results validate its benefit for orientation-related spatial reasoning.

Pretrained macro-placement policies can reduce repeated optimization across circuits, but deployment often exposes them to unfamiliar designs when the original training data are unavailable. Repeatedly fine-tuning a single serving model can overwrite earlier improvements, while simply saving checkpoints does not determine where they can be reliably reused. We introduce Continual Adaptation through the Reuse of Validated Expertise (CARVE), a framework that represents accumulated expertise as a frozen base policy, immutable specialists, and task-specific credentials obtained through local validation. For a new task, CARVE first checks existing specialists and trains a new specialist from the frozen base only when none qualifies. Under fixed task distributions and validation rules that control cumulative error, we establish expected-performance guarantees for repeated reuse. For bounded losses, we also derive matching worst-case bounds on the local samples needed for reliable reuse. In macro placement, a reuse-first follow-up reduces recorded training time by 58.5% (9.66 to 4.01 hours), while mean HPWL gain changes only from 8.41% to 7.86%. In a simulated receiving deployment, imported specialists are reused on six of seven new IBM circuits with no receiver-side training, achieving a 5.76% mean HPWL gain. Navigation studies provide complementary evidence on repair retention and repeated adaptation.

While action-conditioned video prediction provides an intuitive world model for robotics, purely data-driven predictors often suffer from compounding errors and physically implausible hallucinations in long-horizon rollouts, severely undermining downstream action planning. We propose VPTwin, a Real-Sim-Real video prediction framework that anchors real-world future prediction using real-synchronized simulation twins. For a target manipulation task, a VLM reconstructs an executable digital twin from a real demonstration episode. To accommodate the ill-posed estimation of unobserved physical properties, Isaac Sim simulates multiple forward dynamic rollouts across randomized physical configurations under candidate action trajectories. Using these rollouts as in-context references, VPTwin harmonizes both domains, using simulation dynamics to enforce physical plausibility while capturing unmodeled contact interactions from real video. Furthermore, we establish a predictive planning loop using VPTwin to visually verify VLM-proposed actions and guide reliable real-world execution. Evaluations show substantial reductions in physical hallucinations during video prediction and marked improvements in manipulation planning performance.

Multi-agent LLM systems are increasingly deployed for complex, long-horizon tasks or emerge as a natural consequence of agents interacting in the wild. Yet they give rise to significant safety and security risks: the flexible protocols that enable task generalization also expose novel threats, from cascading prompt injection to inter-agent collusion. Progress in defending against these threats has been slowed by a lack of shared empirical infrastructure, which forces bespoke environment development for every new defense and makes standardized comparison impossible. Existing evaluations address isolated threat models or single-agent settings, but none jointly vary attack, defense, and architecture across realistic multi-agent environments. To address this gap, we introduce ORBIT, a configurable evaluation framework for empirical multi-agent safety and security research, built on UK AISI's Inspect. ORBIT lets researchers configure communication topologies, memory, scheduling, and agent roles. It supports four threat types and four defense strategies, as well as non-adversarial failures, with a benchmark suite spanning five scenario families covering browser use, computer use, agentic coding, customer service, and cooperative allocation. Our central finding is a gap in defense transferability across threats: per-action defenses that cut a compromised agent's attack success by 60 points on multi-issue coding give no measurable protection against colluding agents, and none of the defenses we tested generalized over all attacks tested. We further demonstrate security-performance tradeoffs and interactions between architecture and defense effectiveness. We make ORBIT available open-source at https://github.com/wlanderson0/orbit.

Little is known about how to manually design agents capable of dexterous manipulation. Some design principles have been inferred from close examination of how animals manipulate objects, but these structures and behaviors have so far resisted biomimicry and may not be optimal for artificial machines. Here we evolve freeform robots to pick up, hold, rotate, and use diverse objects. Unlike other approaches to optimizing robot hands, we do not presuppose the presence, articulation, or geometry of any part of the body. Although familiar prehensile forms such as tails, beaks, paws and claws may emerge spontaneously under certain conditions–and while such conditions could be of interest to evolutionary biologists–de novo manipulator design can also reveal whole new solutions, overlooked or unknown structures which may be better suited for the task at hand. We use contrastive learning to create a highly searchable genetic embedding of design space, an autoregressive developmental model to decode designs, evolutionary strategies to find good designs, and reinforcement learning to train each evolved design. Winning designs were automatically converted into a manufacturable blueprint, printed, assembled and tested in the real world in a zero-shot manner. The results represent the state-of-the-art in evolutionary robotics in terms of performance, diversity and complexity.

Video models commonly use uniform grids even though visual complexity varies substantially across space and time. We introduce OctVideo, which approximates a video clip with an octree. This hierarchy recursively partitions a spatio-temporal volume into eight subvolumes, so that smooth regions remain coarse while detailed regions receive finer cells. Each leaf stores local RGB values and spatio-temporal gradients, supplemented by a lightweight learned residual. For reconstruction, a Conv1D VAE maps the serialized cells to a regular latent grid and selectively refines details during decoding. Our VAE achieves 36.12 dB PSNR with 38.2M parameters and 189.4 GFLOPs per clip on Kinetics-400 (K400). It also generalizes zero-shot to the high-resolution Densely Annotated VIdeo Segmentation (DAVIS) 2016 dataset with reconstruction quality comparable to the best evaluated models. On both datasets, it requires the fewest model FLOPs and achieves the fastest encoding and decoding among the evaluated models. OctVideo also supports video understanding, achieving competitive recognition performance with few input tokens when trained from scratch. By exploiting the redundancy already present in video signals and efficiently processing sparse structures, OctVideo provides an efficient representation for video.