Research

• General in-context learning for embodied agents1 paper raises it · 0 address it

  Enables models to adapt to new tasks and environments without retraining, improving robustness in real-world deployment.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Cost and latency in embodied control loops1 paper raises it · 0 address it

  High computational and time costs limit real-time applicability of agentic systems in dynamic environments.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Physical-state verification and failure recovery1 paper raises it · 0 address it

  Agents must reliably detect and correct errors in physical interactions to avoid irreversible failures in real-world tasks.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Long-horizon task preservation in embodied agents1 paper raises it · 0 address it

  Maintaining progress over extended sequences is critical for complex, multi-step tasks in robotics and navigation.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Open-source stacks for generalist computer-use agents1 paper raises it · 1 addresses it

  Closed systems hinder reproducibility and systematic study of agent design for real-world computer tasks.

  • OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.CVOct 17

  Unifying Amplitude-Phase Coupling and Reliable Endogenous Priors for Low-Light Image Enhancement

  Tongshun Zhang, Zixuan Zhong, Pingping Liu, Jin Kuang, Yubing Lu +2

  Frequency-domain methods have shown strong potential for low-light image enhancement (LLIE) because they can effectively regulate global illumination. However, most existing methods assume that amplitude and phase can be restored independently, while overlooking their inherent spectral coupling. This artificial decoupling often leads to information inconsistency and structural distortions. To address this issue, we propose a frequency-spatial framework that jointly models spectral interaction and reliable prior guidance. We first empirically analyze the coupling between amplitude and phase and develop an Amplitude-Phase Adaptive Compensation Fusion (APACF) module. Instead of enforcing a hard separation between the two components, APACF enables their bidirectional interaction, resulting in spectrally coherent restoration. In addition, directly extracting priors from raw low-light inputs is unreliable, since severe noise and underexposure destroy critical visual content. To alleviate this problem, we introduce an Endogenous Reliability Prior (ERP). Specifically, we treat an intermediate result, preliminarily restored in the frequency domain and already close to the ground-truth…

  PDF
• arXiv cs.AIOct 17

  Learning to Compose: Recursive Self-Improvement of Shared Executable Stacks for Zero-Shot Long-Horizon Robot Manipulation

  Yangzhi Chen, Feiran Liu, Zishuo Wang, Zijian Jin, Xin Zhu +2

  Individually competent robot skills can fail when composed: tools may lack a required capability, completion signals may misrepresent physical progress, and one skill may leave a state that violates its successor's prerequisites. We introduce Recursia, a recursive self-improvement framework that treats the shared executable stack, rather than individual task programs, as the persistent unit of improvement. The stack integrates tools, skills with execution contracts, handoffs, and verifiers. Source-side execution traces guide failure attribution and the generation of missing tools or repairs to existing shared components. Generality checks, mechanism tests, and paired selection and regression gates determine which changes become the next parent. The resulting stack is frozen and reused through declarative task adapters, allowing source-derived changes to support new compositions without target-side code repair. Experiments cover LIBERO-Pro Long simulation and a physical Franka FR3 equipped with a Franka Hand. In simulation, Recursia improves success over ASPIRE by 5.8 percentage points under Pos perturbations and 15.1 points under Task perturbations. Across three physical…

  PDF
• arXiv cs.CVOct 17

  O-SCD++: Replay-Free Online Scene Change Detection via Recursive Evidence Fusion

  Chamuditha Jayanga Galappaththige, Jason Lai, Lloyd Windrim, Timothy Patten, Donald G. Dansereau +2

  Online scene change detection requires an agent to detect what has changed in a previously mapped environment while it is still on site, observing from unconstrained viewpoints and without access to future observations. This causal setting is strictly harder than its offline counterpart, and online methods have consistently trailed offline accuracy. O-SCD closed that gap by treating change as a persistent property of a 3D Gaussian splatting map of the reference scene, surpassing the strongest offline methods in change detection accuracy while operating at over 10 frames per second. O-SCD optimizes a change field over the Gaussians of the reference map, refitting it to all past cue maps at every frame, a step that consumes more than half of the per-frame budget and forces accuracy to be traded against speed. We present a replay-free formulation that eliminates this trade-off. Because the reference map stays fixed, rendering the change field is a linear operation. Each new observation can therefore be carried onto the map's Gaussians directly, by a single backward pass of the renderer, which reduces multi-view fusion to an exact two-scalar recursion per Gaussian. Past observations…

  PDF
• arXiv cs.LGOct 17

  Measuring Empowerment from Offline Data for Intrinsically Motivated Exploration

  Ishir Garg, Vivek Myers, Qiyang Li, Catherine Ji, Benjamin Eysenbach +1

  Large, unlabeled datasets of prior experience have become increasingly available for agentic tasks in domains such as robotics and coding. A common recipe for these tasks is to train a policy using the prior data, and then further improve it with online rollouts. But while much work has studied how to use both the offline and online data for policy extraction, far less work has been done to understand how the prior data can be used to efficiently \textit{explore} during the online learning phase. Previous work has attempted to formalize this idea by defining the \textit{empowerment}, a measure of how many future states an agent can realize; states with higher empowerment require more exploration as there are more futures to explore. However, existing methods for estimating empowerment require online policy rollouts in the environment. We propose the first method for estimating empowerment from unlabeled prior data, without any environment interaction. By jointly learning an empowerment-maximizing policy together with its discounted state-occupancy measure, our estimator can be trained on unlabeled trajectories generated from any unknown policy. We demonstrate that our empowerment…

  PDF
• arXiv cs.LGOct 17

  Generative Retrieval for Reverse Target Fishing with a Proteome-Scale Benchmark

  Zhichao Deng, Haichuan Tan, Xin Hong, Huaizhi Wang, Tao Huang +2

  Reverse target fishing identifies protein targets for a query molecule and is central to drug discovery and repurposing. Discriminative approaches adapted from virtual screening face sparse, long-tailed associations and missing-not-at-random measurements: treating unrecorded pairs as negatives can suppress genuine targets. We reformulate the task as generative retrieval and introduce GenFish. Residual vector quantization converts frozen protein language model features into shared semantic identifiers. Given a molecular fingerprint, GenFish autoregressively models codes conditioned on the query and preceding code, ranking proteins by identifier likelihood without explicitly labeling unrecorded pairs as negatives. We introduce ProTargetBench, the first proteome-scale benchmark for reverse target fishing to jointly support measured-panel discrimination and full-catalogue recovery of experimentally recorded positives. Covering 20,431 UniProt-reviewed human proteins, it integrates curated bioactivity evidence and distinguishes experimental inactivity from unmeasured associations. On 198 held-out molecules, GenFish achieves higher mean performance across all three full-catalogue…

  PDF
• arXiv cs.GTOct 17

  Tree Plurality Veto: Voting in Few Rounds with Efficient Communication and Low Metric Distortion

  Gabriel Chen, Yu Cheng, Alice Wang

  We consider the metric distortion framework for voting, where $n$ voters and $m$ candidates are embedded in an unknown metric space. A voting rule selects a candidate using only voters' ordinal preferences, and its distortion is the worst-case ratio between the social cost of the selected candidate and the minimum social cost. We study how round complexity trades off against total communication in deterministic voting protocols with low distortion. Deterministic rules can achieve the optimal distortion of $3$ in one round by eliciting complete rankings using $Θ(nm\log m)$ bits, while a direct sequential implementation of PluralityVeto achieves the same distortion using only $O(n\log m)$ bits but requires $Θ(n)$ rounds. Our main result is TreePluralityVeto, a deterministic voting protocol that, for every $r\ge 2$, achieves distortion at most $2r-1$ using at most $r$ rounds and $O(n\log m+n s^{1/(r-1)}\log s)$ bits of total communication, where $s = \min\{n, m\}$. The protocol runs PluralityVeto on a hierarchical partition of the voters, collecting restricted rankings in parallel at each level. The branching factor controls the tradeoff between rounds and communication, and a…

  PDF
• arXiv cs.AIOct 17

  MELD: Recursive Self-Improvement via Hierarchical Coordination for Multi-Agent Scientific Discovery

  Sizhe Tang, Zuyuan Zhang, Zeyu Fang, Tian Lan

  Multi-agent scientific discovery with large language models raises a coupled learning problem: research assignments determine both which experiments are pursued and the experiences from which agents adapt. We introduce MELD, a unified hierarchical test-time training framework that jointly adapts a team-level Coordinator policy and agent-level individual Scientist policies within a single discovery process. The Coordinator generates a joint portfolio of search branches and research directives over a shared derivation tree, while Scientists develop hypotheses and execution plans implemented by a shared frozen Executor. Both levels receive alternating GRPO-style parameter updates under a shared smooth best-of-budget objective, allowing team organization and individual research behavior to co-evolve in a recursive self-improvement loop. Our analysis establishes objective alignment for the hierarchy, characterizes conditions for coordination gains over independent parallel discovery and the first-order benefit of private adaptation, and derives a finite-budget regret bound for adapted models. On 22 MLGym and MLE-bench tasks, MELD is best on 20 of them and achieves the highest…

  PDF
• arXiv cs.AIOct 17

  Hippo: Training-Free Agent Self-Evolution via Hippocampal Replay

  Yutong Song, Jiang Wu, Yuxuan Ren, Tony Qin, Baoyuan Wang

  Motivated by recursive self-improvement (RSI), we study how LLM agents can learn through external memory without updating model parameters. Extracting useful experience from a single attempt is difficult: flawed reasoning can produce success, while poor execution can obscure a sound strategy. Preserving its value over time is also difficult: our accumulation baseline without consolidation initially improves but eventually performs below a no-memory baseline. Our key idea is to compare attempts at the same task to identify reusable decisions and refine when they apply. We introduce Hippo, a memory framework inspired by selective hippocampal encoding and replay that learns from these comparisons when shortcomings are diagnosed. It compares the resulting experience with existing memory to merge overlaps and resolve conflicts through explicit applicability conditions. This allows prior guidance to be revised without storing every lesson as a separate entry. Experiments on SWE-bench Verified, WebArena, and Mind2Web show performance gains in all three settings and substantially fewer retained experiences than the accumulation baseline. The gains extend across the evaluated base models…

  PDF
• arXiv cs.CVOct 17▲ 3

  HumanSkill-4D: Training-Free Language Querying of Animatable Gaussian Avatars in Space and Time

  unsu Kim, Naeun Kim, Dongyoon Han, Seungryul Baek

  We introduce avatar referring segmentation, which selects regions of animatable Gaussian avatars from language queries. A query can also specify a pose or motion to select matching intervals. This lets users interact with avatars for local editing and motion inspection. However, making these selections with existing language Gaussian splatting methods poses two challenges: adjacent parts and garments are hard to separate and may be referred to indirectly (region ambiguity), while fine-grained motions can look alike in RGB (motion ambiguity). We address these challenges with HumanSkill-4D, a training-free framework that shares a multimodal large language model (MLLM) and geometric operators across avatars. For each avatar, a semantic memory links body-part and garment categories to persistent Gaussian regions and appearance descriptions. The MLLM uses category names and descriptions to select categories by appearance, relation, or function. To find matching intervals, it composes operators into programs that check query conditions on driving joint trajectories stored in a motion memory. These category choices and operator outputs make selections traceable, while composing or…

  PDF
• arXiv cs.CVOct 17

  Do 3D Large Language Models Really Use 3D Evidence?

  Yifei Zhao, Fanyu Zhao, Han Zhang, Yixuan Lin, Yuyang Hou +4

  Recent 3D Large Language Models (3D-LLMs) have shown strong performance on scene question answering with extensive post-training. Yet, existing benchmarks rarely evaluate how 3D-LLMs respond to referential ambiguity, insufficient scene evidence, or false presuppositions, obscuring whether their responses are grounded in 3D evidence. In this work, we introduce UNICORNS, a benchmark for evaluating the reliability of 3D-LLM responses across four evidence conditions. UNICORNS contains 11,387 questions across 557 ScanNet scans, covering eight challenge categories alongside answerable controls. A response passes only if it satisfies the required response behavior and contains no scene claim unsupported by the available evidence. Evaluation of six open-sourced 3D-LLMs reveals a pronounced performance gap: even the strongest zero-shot model achieves 61.22% accuracy on answerable controls, but only 40.94% across the eight challenge categories. To address this gap, we further propose HORN, an obligation-aware post-training method combining group-relative task rewards, leaf-conditioned obligation rewards, and supervised control replay. Extensive experiments demonstrate that HORN reaches…

  PDF
• arXiv cs.LGOct 17

  Near-Optimal Regret for Semi-Bandit Learning of Monotone Stochastic Problems

  Zhengjia Zhuo, Viswanath Nagarajan

  We consider the task of learning an (approximately) optimal policy for stochastic optimization problems where the true distributions are unknown. In each period, the algorithm plays a policy for the stochastic problem and observes semi-bandit feedback, i.e., it only receives new samples from the random variables that were selected by the policy. We obtain an algorithm that works for a large class of ``monotone'' stochastic problems, including prophet inequality, Pandora's box, series testing, stochastic knapsack and stochastic matching. We obtain $\tilde{O}(\sqrt{nkT})$ regret for ``weakly'' monotone problems and $\tilde{O}(\sqrt{nT})$ regret for ``strongly'' monotone problems, where $T$ is the number of periods, $n$ is the problem dimension (number of random variables) and $k$ is the maximum support size of any random variable. This improves over previous regret bounds by a $\sqrt{n}$ factor. In fact, our dependence on $n$ and $T$ is the best-possible due the $Ω(\sqrt{nT})$ lower bound for multi-armed-bandits. Our main technique is the use of Hellinger distance in bounding the ``error'' between the true and learned distributions, and the use of a constant-factor chain rule for…

  PDF
• arXiv cs.LGOct 17

  Transformers as Adaptive Kernel Learners across Tasks for In-Context Learning

  Zhaiming Shen, Alexander Cloninger, Rongjie Lai, Wenjing Liao

  Transformers have emerged as a dominant architecture in modern machine learning, with in-context learning (ICL) enabling models to adapt to new tasks by conditioning on prompts, without any parameter updates. To understand the attention mechanism in transformer blocks, a growing line of theoretical work interprets ICL through the lens of classical statistical estimators. Recent works have established a connection between the attention mechanism and kernel methods, while the kernel function is usually assumed to be fixed. In practice, the query and key matrices in the attention mechanism are trained, which allows the attention mechanism to serve as an adaptive kernel method. In this work, we demonstrate that transformers can act as adaptive anisotropic kernel learners. Specifically, we study ICL for low-rank linear and multi-index nonlinear regressions, and conduct numerical simulations to show that the learned attention scores closely resemble the oracle kernels for these function classes. We then develop a general framework to analyze the generalization error of ICL by connecting transformers to the oracle kernel estimator for each function class. Our theory gives an explicit…

  PDF
• arXiv cs.CVOct 17

  BodyBridge: Grounded Body Layers for Sim-to-Real Translation of Vulnerable Road Users

  Mark Azer, Fabian B. Flohr

  Simulation-to-real driving video diffusion models can translate photorealistic scenes, but they typically represent pedestrians and cyclists, vulnerable road users (VRUs), as generic object classes. This is insufficient for vulnerable road users whose safety-relevant appearance depends on articulated pose and identity. We present BodyBridge and Grounded Body Layers (GBL), a simulator-derived, pixel-aligned representation that combines scene geometry, canonical per-pixel body correspondence, and exact VRU masks. GBL provides explicit articulation to the video diffusion model, emphasizes VRU regions during control-branch post-training, and supports additive composition with scene-geometry control at inference. It also enables per-joint evaluation of generated VRUs and a failure taxonomy for identity errors. On CARLA-to-real translation, BodyBridge improves near-range PCK@0.5 by 22% over the released depth-conditioned baseline. Replacing normal-map body control with canonical correspondence reduces body flips by 18%, while composition reduces near-range facing flips by 27%. These results show that explicit body grounding complements scene-level control and improves pose-faithful VRU…

  PDF
• arXiv cs.LGOct 17

  Transport What Shares the Conduction Pathway: Normal-Anchored SPD Geometric Transport for Source-Free Patient Adaptation of Holter and Patch ECG

  JinKook Kim

  Electrocardiogram (ECG) beat classifiers lose accuracy on new patients and devices, and source-free adaptation methods that assume class-balanced target batches fail on real recordings, whose label-free prefix is 87.9--98.6% normal beats. We propose Normal-Anchored Geometric Transport (NAGT, GA_NS), which estimates a closed-form symmetric positive-definite congruence map from label-free normal anchors in the first 5 min of each recording and applies it only to the normal and supraventricular prototypes, keeping the ventricular and fusion prototypes fixed. The score offsets and decision rules were set on MIT-BIH only; the rate-invariant RR head (relA) was adopted after the development databases (INCART, SVDB) had been opened; the frozen model was then evaluated once on Icentia11k chest-patch recordings under a pre-registered protocol. In 493 patients (973 recordings, 3,615,388 evaluated beats), NAGT reached an arrhythmia macro-$F_1$ $J = \frac{1}{2}(\text{S-}F_1 + \text{V-}F_1) = 48.7\%$ [95% CI 42.1, 54.7] versus 34.5% without adaptation ($ΔJ = +14.1$ [+8.6, +19.3] pp; 59.8% versus 43.9% in non-AF) and outperformed all five Holm-adjusted comparators, including AdaBN, Tent and…

  PDF
• arXiv cs.CLOct 17

  When Opposite Premises Translate Identically: A Source-Conditioned Diagnostic for Multilingual Commonsense Items

  Shuai Wang, Rui Hu

  Multilingual reasoning comparisons depend on translated premises preserving the relations in their English sources. Automatic translation scores can rank source-target pairs, but an acceptance decision alone cannot certify a counterfactual benchmark field. We test a source-contrast diagnostic for ACCORD premises: reverse the English polarity, translate both arms independently, count identical target outputs, and score each arm against its own source. Across 71 matched question identities at two containing-item depths, five target languages, and three translation checkpoints, Swahili has 63, 113, and 67 exact collisions among 710 pairs per checkpoint. At a human-reference-calibrated threshold, round-trip NLI passes both arms of 3 of the 113 NLLB-3.3B collisions, while LaBSE passes 78. Each collision proves at least one unfaithful translation, but does not identify its arm. These controlled measurements do not establish screening accuracy on spontaneous translation errors or a language-by-hop reasoning effect; the study has no native equivalence labels or answer-model evaluation.

  PDF
• arXiv quant-phOct 17

  Margin-Based Generalization for Quantum Machine Learning with Classical Data Encoding

  Ju-Young Ryu, Tak Hur, Daniel K. Park

  Understanding generalization is essential for assessing the practical viability of quantum machine learning. In many applications, quantum models operate on classical data that must first be encoded into quantum states, making the encoding part of the effective hypothesis class. We develop a margin-based generalization framework for this setting, covering both fixed and trainable quantum data encodings. For fixed encodings, the existing margin bound transfers unchanged. For trainable encodings, we derive a bound using a two-scale covering argument that combines the original margin-dependent term with an additive encoding-capacity term of order $\tilde O(\sqrt{L/m})$, where $L$ is the number of trainable encoding parameters and $m$ is the training-sample size. Across 19,440 simulated training runs spanning various image datasets, circuit architectures, and optimization settings, the inverse margin performs best among five baseline and two bound-derived complexity measures under conditional-independence and 90th-percentile sign-error criteria, within bootstrap uncertainty. These results provide a unified margin-based view of generalization in quantum machine learning with classical…

  PDF
• arXiv cs.CLOct 17

  Toward a Universal Local Speech Feature Extractor Through Distillation

  Jessica Yang, Marcelo Beramendi Caballero, Ju-Chieh Chou, Karen Livescu

  Self-supervised speech models commonly consist of a set of convolutional neural network (CNN) layers used as a local feature extractor, followed by transformer layers. The CNN layers are computationally demanding, and are also similar across models and resemble the much simpler mel spectral features. We hypothesize that the CNN layers can be replaced by a simple, universal model. To test this hypothesis, we learn a two-layer feature extractor via distillation from one or more teacher models (HuBERT, data2vec, and WavLM). Experiments on SUPERB(-SG) benchmark tasks show that our model largely retains the performance of the teacher models and can also be used in an unseen model (wav2vec 2.0). Our feature extractor requires only 3% of the MACs of the CNNs, resulting in a $>$20% overall inference runtime reduction.

  PDF
• arXiv cs.LGOct 17

  Cross-Dimension and Cross-Modality Relational Tensor Representation Learning for Multimodal Health Data Modeling

  Jiawei Guo, Meng Zhao

  Multimodal health data integrate information from heterogeneous clinical sources, creating substantial opportunities for data-driven decision support. Realizing these opportunities, however, requires effectively modeling complex dependencies that arise both within individual modalities and across modalities. This paper proposes Relational Tensor Representation (RTR), a unified framework that jointly learns dimension-specific tensor representations and cross-dimensional and cross-modality relationships. RTR introduces learnable relational bridge matrices that maintain relational information while preserving the structural identities of tensor dimensions and modalities. A structured fusion mechanism further integrates factor-level and relationship-level information into compact representations for downstream prediction. Experiments on simulated data and two multimodal neurophysiological datasets, covering emotion recognition and brain activity classification, demonstrate that RTR consistently outperforms representative tensor learning, multimodal fusion, and Transformer-based baselines. These results highlight the value of explicitly modeling cross-dimensional and cross-modality…

  PDF
• arXiv cs.CVOct 17

  S3D-Mosaic: Subgradient-Guided Cross-Band Structure Transfer for Spectral Demosaicing

  Weiqiang Zhao, Xian Li, Yuzhe Gui, Tianzhu Liu, Yanfeng Gu

  Multispectral filter array (MSFA) imaging enables snapshot spectral acquisition, but its per-band sparse sampling causes severe spatial aliasing. Although missing spatial structures can be inferred across bands, wavelength-dependent contrast variations make direct cross-band transfer unreliable. Existing model-based methods lack explicit magnitude-invariant mechanisms, and learning-based methods require layout-specific training or per-image tuning, limiting generalization. To address these issues, we propose S3D-Mosaic, a model-based spectral demosaicing method built upon a subgradient-guided cross-band structure transfer framework. We first establish a subgradient-guided regularization framework with a generalized cosine-similarity interpretation, providing a convex mechanism for magnitude-invariant information transfer. Then we design a compact Directional Sparse Equivariant Difference Convolution (DSE-DConv) for band-level extraction of orientation-selective, high-frequency structure features at low computational cost. Instantiating the framework with DSE-DConv on spectrally adjacent bands yields a cross-band self-structure similarity regularizer for spectral demosaicing,…

  PDF
• arXiv cs.CLOct 17

  Ask Less, Ask Better: Allocating User Attention in Proactive LLM Agents with Interruption Budgets

  Xuanming Zhang, Amir H. Rezaeian, Miguel Ballesteros, Weiyi Sun, Werner Geyer +4

  LLM agents can ask clarifying questions to complete tasks, but answering each question demands users' time and effort. Existing evaluations typically measure this burden by counting questions, treating necessary and avoidable questions equally. We propose an evaluation protocol that distinguishes how often agents ask from how well they ask. An interruption budget limits the number of questions, while a user-attention cost charges extra for questions that are hard to read or not worth asking, as rated by a human-validated LLM judge. Beyond question counts, this cost captures perceived effort: on conversation pairs with the same number of questions, human annotators agreed with the cost on which conversation required more effort 75% of the time. Across eight LLMs and four customer-service domains, limiting agents to one to three questions reduces user-attention cost by 36-73% while keeping 86-94% of the task reward they earn with unlimited questions. At the same budget, reviewing each question against the memory of users' earlier answers cuts attention cost by another 13% with little reward loss and yields more valuable questions. Models also differ sharply in how well they ask: at…

  PDF

• Training & fine-tuning46+155.6%
• Computer vision36+140.0%
• AI safety33+135.7%
• Robotics22+120.0%
• Evals66+57.1%
• Code models14+40.0%
• Small LLMs7+40.0%
• Federated learning48+29.7%