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.

• Training & fine-tuning63+6200.0%
• Evals105+3400.0%
• Computer vision49+2350.0%
• Code models23+2200.0%
• Image & video generation36+1100.0%
• Federated learning49+28.9%
• Quantum machine learning240.0%
• Character recognition OCR170.0%

• arXiv cs.CLOct 18

  Self-Distillation for Supervised Fine-Tuning

  Wenxuan Zhu, Bang An, Shuming Liu, Wenqing Cui, Tianqi Xu +4

  Supervised fine-tuning treats the expert demonstration or gold response as a one-hot target, suppressing valid alternative continuations that the model would otherwise assign probability to. We propose Gold-Conditioned Distillation (GCD), a method that turns expert demonstrations into model-native supervision. GCD uses one model as both teacher and student: the teacher conditions on a prompt containing the gold response in context, the student conditions on the original prompt as at inference, and the student is trained to minimize the forward KL divergence to the teacher's next-token distribution at each gold response token. This lets the model use its prior knowledge to teach itself the new task: correctness is anchored by the gold response, while the soft target preserves plausible alternatives. Across various training tasks on Qwen and Llama models, GCD improves new-task accuracy over SFT and generally reduces degradation on general benchmarks.

  PDF
• arXiv cs.AIOct 18

  From Proposal to Execution: Modeling Interaction Semantics in Shared Autonomy

  Shashank Shekhar, Laurent Jeanpierre, Abdel-Illah Mouaddib

  In many human-AI systems, candidate actions are not executed directly but are first evaluated by another decision-making entity under a potentially different objective or decision model. Standard decision-theoretic frameworks do not require this interaction to be represented explicitly, as they define transition dynamics directly over state-action pairs, allowing evaluation to be absorbed within the transition model. We introduce a semantics-aware decision framework in which a candidate action is proposed, evaluated under an interaction context, and then resolved into an executed outcome. We formalize this through a joint action language and an interpretation function that maps each joint action and context to a semantic outcome. Transition and reward dynamics are induced through these semantic outcomes, thereby introducing an explicit representational layer for interaction semantics. Semantic outcomes provide explicit units for organizing interaction principles, which can be instantiated through application-specific evaluation mechanisms and reused across distinct interaction instances. This provides a structured interface for specifying context-dependent evaluation separately…

  PDF
• arXiv cs.LGOct 18

  Probabilistic Limit Order Book Forecasting with Conditional Diffusion Models

  Junyu Chen, Franklin Liu, Moshu Xu, Lijian Yang

  Modeling limit order book (LOB) dynamics is central to market forecasting and execution-strategy evaluation. While diffusion models achieve strong empirical performance, existing LOB snapshot models typically lack a learned recurrent encoder and formal statistical guarantees. We introduce LOBGrad, a conditional DDPM framework for probabilistic LOB forecasting that combines an autoregressive RNN encoder with a diffusion-based generator. In particular, we establish an excess-risk oracle inequality for the one-step DDPM noise-prediction objective under exponential mixing and regularity assumptions. We further show that, under contractive dynamics, the dependence on the conditioning-window length can be reduced to a dependence on the latent-state dimension. Experiments on BTC/USDT, GOOGL, and META show that LOBGrad improves on its encoder-free diffusion ablation across all reported queue metrics and obtains competitive results against other baselines. It also reproduces the key stylized facts of LOB microstructure, and yields reasonably calibrated queue-based predictive intervals. A stylized downstream task illustrates the potential value of the generated forecasts.

  PDF
• arXiv cs.CVOct 18

  GroundedVDR: Grounding Video-to-Web Evidence Dependencies in Video Deep Research

  Xiyuan Liang, Yu Wang, Zuhao Yang, Ziting Wang, Duo Li +5

  Video large multimodal models have improved at identifying cross-frame visual evidence and conducting open-web retrieval, as reflected in recent video deep research (VDR) benchmarks. However, existing VDR benchmarks primarily evaluate tool-use trajectories and final responses without verifying whether a model actually uses the temporal video information or the retrieved web evidence. To fill this gap, we introduce \method{}, an evidence-grounded benchmark with three features. First, it combines human review with restricted-access probing across multiple models to exclude questions answerable from parametric knowledge or a single information source. Second, each question carries structured video-to-web evidence annotations that link the relevant video segments to their supporting web evidence. Third, its evaluation protocol separately scores video grounding, web evidence grounding, and final-answer correctness. Across eight multimodal agent systems, the best reaches 76.0\% answer accuracy, yet none recovers the complete required web evidence for more than 8\% of questions. Our benchmark is publicly available at \url{https://huggingface.co/datasets/hh721/vdr_temp}.

  PDF
• arXiv cs.CVOct 18

  SlimFormer++: Token Mixing Where It Matters for Efficient 3D Medical Image Segmentation

  Yang Hong, Lei Zhang, Zhihong Liu, Jianqing Mo, Xujiong Ye

  To determine where computation is needed in volumetric segmentation networks, we analyze block-level redundancy and stage-wise token-mixer contribution. Centered Kernel Alignment reveals high input-output representational similarity within blocks of representative convolutional, hybrid, and Transformer-style segmentation networks. Similarity-guided pruning reduces their parameter counts by 39-75% while decreasing mean Dice by less than 0.4 percentage points. To examine token mixers within blocks, we introduce Anatomical Relation Distortion, which quantifies how bypassing a mixer distorts feature relations between labeled anatomical positions. Applied to an unpruned candidate architecture, Centered Kernel Alignment indicates high representational redundancy in intermediate encoder mixers, whereas Anatomical Relation Distortion shows that they contribute little and the bottleneck mixer most. These findings motivate SlimFormer++, which uses Selective Mixing blocks with windowed Mamba mixing in the first encoder stage and only residual channel MLPs in deeper stages. At the bottleneck, Augmented Mixing injects similarity-weighted sparse long-range context into the axial taps of a…

  PDF
• arXiv cs.CVOct 18

  PCXR-Copilot: Device-aware pediatric chest radiographic analysis with segmentation, suppression, and edema-related cues

  Xueyang Li, Alec Girten, Peng Zeng, Mingze Jiang, Shaoyang Huang +4

  Patients admitted to pediatric ICU and cardiac ICU often require intensive perioperative support and frequent chest radiography to monitor support devices, extravascular lung water, and body-wall edema. Radiographic interpretation and analysis is often difficult due to superimposed anatomic and iatrogenic structures that obscure clinically relevant signals. While deep learning can provide decision support, translation to pediatric radiographs is still limited by high device burden and scarcity of pediatric datasets with clinically grounded device annotations. To address this gap, we first introduce PediaDeviceSeg-1K, a curated dataset of 1,000 anterior-posterior radiographs of pediatric CICU patients with clinically grounded, fine-grained annotations of common ICU devices. To our best knowledge, this is the first publicly available pediatric CICU CXR resource with clinically grounded device annotations for device-focused benchmarking. Building on PediaDeviceSeg-1K, we further present PCXR-Copilot, a device-aware pipeline that outputs lung and device masks, optional device-suppressed views, and edema-related visualization maps and scalar indices. The full pipeline has been…

  PDF
• arXiv cs.CVOct 18

  PRIMA: Pose Refined Inductive Motion Adapter for Zero Shot Social Bodily Behavior Recognition

  Mingcong Ding, Babette Bühler, Tim Fütterer, Ulrich Trautwein, Enkelejda Kasneci

  Recognizing fine-grained bodily behaviors, such as self-grooming, postural shifts, and backchanneling, is a useful intermediate step for computational social signal analysis. But the behaviors that matter vary across social contexts, and retraining a model for each new taxonomy is expensive. Vision-language models (VLMs) can adapt to new categories through text prompts, yet they lack sensitivity to body structure and often confuse subtle postural distinctions. We propose PRIMA (Pose Refined Inductive Motion Adapter), a lightweight module that injects a body-structure prior into frozen VLMs using human pose as a training-time supervisory signal, requiring no pose input at inference. PRIMA separates a model-specific projection head from a shared core that encodes transferable body-configuration knowledge; adapting to a new VLM requires retraining only the head. We train PRIMA on a micro-action dataset and evaluate entirely through zero-shot prompting. The adapter improves recognition on its training domain, transfers to additional VLM backbones at different scales with the core frozen, and generalizes to two unseen target datasets from social psychology and daily activity…

  PDF
• arXiv cs.CVOct 18

  Multimodal-Conditioned Latent Diffusion Models for Spatiotemporal Brain MRI Forecasting

  Antonio Scardace, Silvia Ingala, Sebastiano Battiato, Daniele Ravì

  Spatiotemporal forecasting of 3D anatomical changes is a critical generative vision challenge for modeling Alzheimer's Disease (AD) progression. While brain MRI forecasting from single-modality data has advanced, other key complementary multimodal biomarkers remain underutilized. In this work, we propose the Multimodal-Conditioned Latent Diffusion Model (MC-LDM), a novel framework for patient-specific brain MRI synthesis. MC-LDM leverages multimodal biomarkers---MRI, tau-PET, Clinical Dementia Rating (CDR), and APOE4---during training, but relies only on baseline MRI, APOE4, and patient metadata at inference, reflecting realistic clinical availability. Our contributions are threefold: (1) a Latent Diffusion Model (LDM) fine-tuned via Low-Rank Adaptation (LoRA) for data-efficient learning; (2) a multimodal conditioning that integrates molecular and clinical signals to model heterogeneous disease trajectories; and (3) auxiliary predictors estimating unobserved multimodal biomarkers from MRI features and patient covariates to condition the diffusion model, removing the need for these assessments at inference. Trained on 1,355 visits from 852 subjects in the Alzheimer's Disease…

  PDF
• arXiv cs.LGOct 18

  Consistent LLM Call Handling Across Java Frameworks: A Reference Implementation and Benchmark

  Oleksandr Klymenko

  Java applications reach large language models (LLMs) through an integration framework, and rely on it to handle a failing provider: to retry what can be retried and nothing else, to wait as long as the provider asks, never to present a truncated answer as complete, and to record each failure in the application's metrics. We state these expectations as a six-clause reliability contract and measure Spring AI 2.0.1 and LangChain4j 1.21.0 against it with a scripted OpenAI-compatible provider: fifteen failure scenarios, synchronous and streaming, three repetitions. LangChain4j meets it in 47 of 77 applicable cases with its defaults and in 51 of 83 when configured explicitly, Spring AI in 72 of 77 and 76 of 83; both deliver a stream that ended without its terminator as a complete answer. We then place one implementation of the contract beneath both frameworks, at the HTTP boundary - an OkHttp interceptor for Spring AI, an HttpClient for LangChain4j, and a java.net.http transport for code without a framework - sharing a 725-line core that depends only on the JDK and the Micrometer Observation API. With it, all three clients behave identically and meet the contract in 90 of 91 cases; the…

  PDF
• arXiv cs.CVOct 18

  Test-Time Scaling of Text-to-Image Flow Matching Models with Noise-Rejuvenated Sequential Monte Carlo

  Wenyi Lian, Zheng Zhao, Thomas B. Sch{ö}n

  Test-time scaling of diffusion models with sequential Monte Carlo (SMC) has become a promising strategy for sampling under user-specified rewards, such as human preference scores. However, the standard SMC framework typically relies on stochastic proposals and therefore does not directly transfer to flow matching models, in which inference is governed by deterministic ODEs. In this work, we introduce noise-rejuvenated SMC, an inference-time scaling method tailored for text-to-image flow matching models. Our key idea is to perturb each resampled particle by changing its source noise and constructing a new intermediate state using its current endpoint estimate. This moves the particle to another state that remains representable under the flow-matching interpolation form, enabling particle exploration without converting the sampler to an SDE. We further introduce a look-ahead mechanism to refine resampled particles before weighting. Experiments on Stable Diffusion 3, FLUX.1-dev, and Z-Image demonstrate consistent improvements in reward-guided generation, while ablation studies validate the contributions of noise rejuvenation and look-ahead refinement. Code is available at…

  PDF
• arXiv cs.AIOct 18

  P(Yes): 15$\times$ Improvements via Test-Time Scaling of Decision Models

  Lev Stambler

  Decision models answer typed questions, such as multiple-choice or yes/no questions, with a probability for each option. We add test-time search to frozen decision models, with no training: we show the model a complete proposed answer, read off its probability of saying "Yes" to the proposal's correctness, and search for answers that it rates higher. The search is done either by editing one answer at a time or by joint optimization, which changes several answers at once. Search raises accuracy for every model and test set we tried, and the gains are largest for exact correctness on logic puzzles, where every answer in a task must be right. On 128 such puzzles, it takes Qwen3.8-27B from 2 to 30 exactly correct puzzles ($15\times$) and its per-blank accuracy from 27.8% to 48.5%. On a shared set of 47 puzzles, searching over each model's own Yes/No score raises the per-blank accuracy of StartLux Instant, Perplexity Decider, Clef, and JEV, which we reach only through its public API, by 4.0 to 13.0 percentage points, and raises the number of puzzles they get exactly correct, out of 47 and averaged over three search seeds, from 10 to 35, 9 to 26, 2 to 11, and 9 to 31.7 respectively.

  PDF
• arXiv cs.CLOct 18

  SZED at ArGuard Shared Tasks: Multi-Task Label-Attention and Cross-Modal Fusion for Arabic Hateful Meme Detection

  Selma Khelili, Zohra Abdeli

  We present SZED's submission to ArGuard 2026 Track A: Arabic hateful meme detection. The task has two parts: binary classification (A1) and fine-grained multi-label tagging (A2). For A1, we fuse MARBERTv2 and CLIP ViT-L/14 embeddings, comparing concatenation, self-attention, and ensemble heads. For A2, we use a multi-task label-attention architecture with per-class query vectors and an auxiliary head for cascade calibration. We reach macro-F1 = 0.7597 on A1 and 0.3142 on A2 (averaged over 10 active classes). We report reproducibility across runs, per-class error patterns, and the effect of cascade calibration on the long-tailed A2 label space.

  PDF
• arXiv cs.AIOct 18

  A failure of Imagination: VLMs fail to use visual representations for text, but self-distillation can help

  Shashwat Singh, He He, Tal Linzen

  Vision-language (VL) models are typically built by fine-tuning a language model to attend to visual features in service of a Visual Question-Answering objective. We ask whether this alignment changes how language models represent text---especially on tasks where visualization would help, like geometry questions posed in words. We distinguish weak multimodality (the model can answer questions about an input image) from strong multimodality (the model's text representations themselves become vision-aligned, improving performance on text-only tasks with latent visual structure). To test for strong multimodality, we construct a task of shape-counting problems with paired equivalent text and image specifications. This task is trivial when the image is provided, but requires visualization when specified in text as line coordinates. We compare instruction-tuned Qwen-2.5 and Mistral models against their vision-aligned counterparts on the text variant of the task. We find that the multimodal models do no better in this setting, despite strong performance on the image version of the task. Probing experiments corroborate this: vision-aligned decoder embeddings carry no more visual structure…

  PDF
• arXiv cs.LGOct 18

  Near-Optimal Last-Iterate Convergence of SGD in the Smooth Interpolation Regime

  Matan Schliserman, Tomer Koren

  We study the last iterate of stochastic gradient descent (SGD) with a constant stepsize on smooth convex objectives in the low-noise and interpolation regimes, where the variance $σ_\star^2$ of the stochastic gradients at the optimum is small or zero. We establish that after $T$ steps of SGD on $β$-smooth convex losses with any constant stepsize $0<η<2/β$, the last iterate attains expected excess risk $\widetilde O\bigl(\tfrac{1}{η(2-βη)^3T}+\tfracη{(2-βη)^4}σ_\star^2\bigr)$, which gives the rate $\smash{\widetilde O(1/T)}$ for every constant stepsize in the interpolation regime ($σ_\star=0$), matching the $Ω(1/T)$ lower bound up to logarithmic factors and improving upon the $O(1/\sqrt T)$ rate of Attia et al. (2026) for $η=1/β$. Our analysis is based on a new technique, which compares the second moments of the stochastic gradients along the SGD trajectory across only logarithmically many time scales. For quadratic losses in the interpolation regime, an adaptation of this technique gives an $O(1/T)$ rate for every constant stepsize, extending the recent optimal rate for the randomized Kaczmarz method of Derezinski and Dong (2026) to stepsizes above the greedy stepsize with an…

  PDF
• arXiv cs.AIOct 18

  On Reasoning Correctness Directions

  Munachiso Samuel Nwadike, Zayd M. K. Zuhri, Rifo Genadi, Abzal Nurgazy, Ali Mekky +3

  We present experimental evidence suggesting that information about whether a model's reasoning is on the right track can be linearly decodable without defining a causally useful direction for steering. To study this, we introduce ChainSearch, a controlled arithmetic reasoning task that extends Countdown with explicit search and backtracking. We train a 3-million-parameter model to solve this task. Its compact size allows us to study internal model correctness directions in detail using linear probes, mean activation differences, and direct optimisation, as part of a rigorous search for internal reasoning-correctness directions. We find that while the model contains statistically significant internal directions of reasoning correctness, none of the resulting directions consistently improves reasoning under causal intervention. This calls into question whether the linear representation hypothesis is sufficient for identifying causally useful directions in the context of reasoning. Our code is made available together with this work.

  PDF
• arXiv cs.CLOct 18

  DiaLong: Benchmarking Reminiscence in Long-Context Dialogues

  Owen Bianchi, Samer Aslan, Ryunosuke Saito

  How well can transformer-based Large Language Models (LLMs) retain and recall memories in long contexts of dialogue? LLMs are known to forget long-range factual information in their context, yet the field lacks a comprehensive benchmark to quantitatively assess these shortcomings. We present DiaLong, a long-context dialogue dataset and accompanying memory task that standardizes evaluation in this space. It consists of 100 unique conversations created by humans and then augmented with LLMs, extending beyond lengths found in existing datasets. Our selected memory task is fact recall: classify 40 candidate facts about a dialogue as true or false. This task directly probes the model's ability to actively retain and retrieve information, serving as a critical measure of memory within extended conversational contexts. In testing both the latest LLMs and proposed memory enhancements on DiaLong, we demonstrate that more work needs to be done to enable LLMs with better memory performance. By enhancing memory capabilities, LLMs can improve in maintaining coherence, relevance, and human-like interaction over extended conversation. Improving these capabilities will help LLMs fulfill diverse…

  PDF
• arXiv eess.IVOct 18

  Reliability-Preserving Compression for Deployable Medical Image Segmentation

  Sagar Kumar, Shailja Sharma, Tirthajit Baruah, Punit Rathore

  Post-training compression of pretrained medical segmentation models commonly uses quantization, pruning, or distillation to reduce model size and computational cost. Existing medical segmentation quantization studies mainly evaluate Dice, model size, memory, and latency, but this is incomplete for safety-critical use because compressed models should also preserve uncertainty signals that indicate unreliable predictions. We study this problem in compressed MRI/CT segmentation and formalize why Dice can remain stable while uncertainty changes. Motivated by this failure mode, we propose score-guided aggregate-validated mixed precision (SGAV-MP), a post-training compression framework that selects layer precisions under reliability constraints. SGAV-MP ranks quantization actions with a compact benefit-risk score and accepts them only after full-model reliability validation on a calibration set. Across five 2D backbones and three 3D benchmarks, SGAV-MP preserves FP32-level Dice and high uncertainty-map agreement, achieving $3.59\times$--$7.8\times$ compression in 2D and $4.73\times$--$7.82\times$ in 3D. We also report backend-supported TensorRT deployment measurements separately to…

  PDF
• arXiv cs.ROOct 18

  BiDex-100: A Comprehensive Benchmark for Bimanual Dexterous Manipulation Across 100+ Simulation Tasks

  Yong Wang, Kecheng Zheng, Xing Zhu, Chao Xu, Yujun Shen +1

  Bimanual manipulation with dexterous hands has attracted growing attention in research on robotic action models. However, few studies have developed benchmarks specifically tailored for dexterous manipulation, leaving the dexterous manipulation capabilities of existing models insufficiently characterized. In this paper, we present BiDex-100, a simulation benchmark for bimanual dexterous manipulation that combines broad task coverage, multi-dimensional evaluation, and high-DoF hand embodiments. Concretely, the benchmark comprises 106 tasks organized along five capability axes: generalization, instruction following, limited demonstrations, long horizon, and memory. Each task is paired with an out-of-domain variant featuring controlled visual and spatial changes, allowing systematic assessment of robustness. In addition, the benchmark supports two embodiments and provides 8,080 success-validated teleoperated demonstrations, totaling 6.25 million frames. We evaluate seven recent Vision-Language-Action models under a unified protocol, establishing baselines for capability-specific performance, robustness, and data efficiency. The website is available at…

  PDF
• arXiv cs.CLOct 18

  Quality-Controlled Reply and Summary Data for Post-Training Small Language Models in AI Call-Screening Agents

  Jiaqi Gan, Tsang Ng, Ankit Raj, Tommy Duong, Xingyu Shen +3

  Small language models have improved to the point where a phone can plausibly screen its own calls, answering on an absent owner's behalf without sending call content off the device, a privacy-respecting alternative to cloud call handling. Realizing that promise takes a model that can do two things well: reply within the owner's authority during the call, and afterward tell the owner what happened and what needs attention. Released small models do neither reliably - they raise unwarranted alarms about ordinary callers and write summaries that drop material conditions or report a caller's claims as fact - and real calls supply no reference replies or summaries to learn from. We construct supervision for both tasks from synthetic calls under an information-boundary constraint: a caller writer works from a private scenario brief, a reply writer sees only the conversation up to the current turn, and a summary writer sees the completed transcript. Separate model-based reviews of the full dialogue and the summary decide which calls enter training, yielding a corpus of 3,395 calls with 15,102 targets (11,707 reply, 3,395 summary). Training a single shared LoRA adapter on both tasks, we…

  PDF
• arXiv cs.AIOct 18

  System X: An LLM Decision Model That Replies from Its Own KV Cache

  Syed Usama Khalid Bukhari, Syed Safwan Khalid, Muhammad Aamir

  Decision models return probabilities over supplied options, but a deployed agent may also need to reply in words. The present study introduces System X, a large language model (LLM) decision model that adds a text-reply option to the LLM-as-Jev readout. When this option wins, or confidence is low, the same model continues from the decision's key-value (KV) cache, avoiding a repeated prompt prefill. Qwen3-0.6B has been fine-tuned with LoRA on Reason-9k and Bitext reply rows. JevBench accuracy shows no statistically significant change (55.4% to 54.5%, p=0.87), while expected calibration error falls from 0.292 to 0.169. Held-out Bitext routing accuracy reaches 98.3%. Cache reuse saves 15-37% of latency on an Apple M4 Pro, with token-identical replies in the FP32 demonstration cases. Scoring options on copies of the prompt cache matches full-sequence scoring to within 1.4e-6 in probability. Adding dialogue, industry and complaint data (System X+) improves support-task results but lowers IFEval accuracy from 55.5% to 45.0%. System X v4 uses Qwen3-1.7B, rebalanced data and teacher-rewritten reply targets. Against its base LLM, JevBench accuracy rises from 55.0% to 61.0% (p=0.04), with…

  PDF