TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksAPI
Fields · this week
All fields3248Multimodal519Agents496Frontier LLMs428Inference & serving257Image segmentation1733D scene154Learning verifiable rewards151Graph learning147Voice AI97Classifier & causal discovery85Forecasting time77Evals72Flow matching69Teacher policy distillation49Federated learning48All 32 fields

Open problems across fields

  • 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.

Rising research topics

Coming with more sources: more tagged papers
  • Small LLMs10+400.0%
  • Training & fine-tuning48+200.0%
  • Robotics24+200.0%
  • AI safety35+191.7%
  • Computer vision37+164.3%
  • Image & video generation27+125.0%
  • Evals72+100.0%
  • RAG10+100.0%

Papers

  • arXiv cs.LGOct 17

    DeliMF: Gated Cross-Attention Fusion of Structured Time Series and Clinical Text for Early Intensive Care Delirium Prediction

    Yibo Yang, Zerui Huang, Haomiao Yang, Zixia Wang

    Delirium affects a large fraction of intensive care unit (ICU) patients and foreshadows longer stays, lasting cognitive decline, and higher mortality. Flagging the patients who will become delirious within the first day of admission would give clinicians a window to intervene. Yet state-of-the-art predictors rely only on the structured electronic health record (EHR) of vital signs, laboratory values, and medications, while overlooking the free-text clinical notes written in the same window, which carry information the numbers cannot encode. To this end, we present DeliMF, a multimodal framework that fuses the structured time series with clinical text. It encodes the structured signals with a temporal Transformer and the time-stamped radiology reports with a clinical text encoder, and fuses the two through a gated cross-attention module. The gate learns a per-patient weight on the text; when a patient has no note the gate closes and DeliMF reduces to its structured-only form, giving robustness to missing text by construction. On an incident-only MIMIC-IV cohort, DeliMF improves significantly over the baselines, particularly on patients who carry clinical text, while losing nothing…

    PDF
  • arXiv cs.AIOct 17

    Concordance Plausibility Check for Intervention-Conditioned Human Digital Twins

    Saeed Farzi, Christopher Kipps, John McBeth, Gabriela Czanner, Sofia Michopoulou +5

    Intervention-conditioned human digital twins predict treatment alternatives that cannot be observed in the same patient. Ordinary predictive accuracy therefore cannot establish counterfactual credibility. We propose the Concordance Plausibility Check (CPC), a claim-centered framework combining real-world evidence, qualified simulation and clinical knowledge. CPC matches evidence to the causal claim, audits contradictions and shared dependencies, and reports Pass, Fail or reason-coded Indeterminate.

    PDF
  • arXiv cs.SDOct 17

    ASR Personalization in Pathological Voice: Accuracy, Efficiency, and Duration Effects

    Giuseppe Giaimis, Sergei Katkov, Muhammad Azfar Yaqub, Antonio Liotta

    Automatic Speech recognition (ASR) struggles with Pathological speech due to persistent speaker-specific mismatch. In clinical and accessibility scenarios, only limited target-speaker data is typically available, making full model retraining impractical. We present a component-level analysis of LoRA adaptation in Whisper, investigating how adapter placement interacts with the model size, training efficiency and utterance-duration in single-speaker settings. Our experimental comparative study shows that while scaling reduces errors, it does not eliminate mismatch. Furthermore, the full attention LoRa provides the most reliable accuracy, and the best time--accuracy trade-off. Improvements vary across utterance length, with medium-length recordings benefiting the most, while short and long utterances remain challenging. These findings highlight the importance of adaptation placement and duration-dependent evaluation, under challenging, data-scarce personalization scenarios.

    PDF
  • arXiv cs.LGOct 17

    Representations Have Trajectories: Characterizing Temporal Representation Dynamics in Neural Networks

    Shivaprasad B. Gowda, Sparsh Mittal

    Recent work has shown that deep neural networks exhibit an implicit low-rank simplicity bias. In this paper, we investigate the questions that naturally arise from this observation. What are the temporal consequences of low-rank simplicity bias during optimization? How does representation geometry evolve throughout optimization rather than only at convergence? Do different neural architectures exhibit distinct geometric optimization behaviors? To answer these questions, we conduct a large-scale empirical study tracking representational geometry throughout training. We find that neural networks follow three recurring geometric trajectories: persistent high-rank, collapse-and-recovery, and persistent low-rank. We further identify Destructive Representation Collapse (DRC) as a pathological regime in which representations collapse to rank-one and fail to recover, leading to a sustained loss of representational capacity. While collapse-and-recovery is consistently associated with successful optimization in controlled settings, experiments on real-world models show that the relationship between geometric trajectories and optimization outcomes is configuration dependent. Overall, our…

    PDF
  • arXiv cs.LGOct 17

    No-Regret Revenue Maximization in Sequential Market Making Under Inventory Constraints

    Davide Maran, Marcello Restelli, Francesco Emanuele Stradi

    Market makers keep trading efficient by setting bid and ask prices for buyers and sellers. In sequential market making, trades happen independently based on price thresholds, requiring the market maker to maintain balanced, low-risk inventory over T rounds. This paper studies how to maximize revenue with unknown buyer and seller valuations using regret minimization. When the market maker only sees trade success or failure, an algorithm achieves regret and inventory bounds proportional to T to the power of 2/3. When full order book data is available for failed trades, regret and inventory limits improve significantly to the square root of T. We also establish a fundamental trade-off via a lower bound, by proving that tighter round-by-round inventory limits strictly force higher minimum regret.

    PDF
  • arXiv cs.CVOct 17

    Controllable Multi-Object Insertion for Detection Data Augmentation

    Jiyang Huang, Tianwei Zhang, Xiaoqin Zhang, Ling Shao, Shijian Lu

    Controllable object insertion provides a targeted approach to augmenting object detection datasets that require category--count fidelity, annotation alignment, and source-content preservation beyond visual realism. Several approaches have been proposed to address this grand challenge, but most suffer from different constraints in precise category--count requests and visual consistency, limited coordination across categories and instances, and poor localization of multiple objects of specific category and count. We design SceneP2F, a two-stage trainable framework that connects scene-aware joint planning with layout-aligned generation leveraging explicit instance-level layouts. SceneP2F consists of two novel designs. The first is ScenePlan which allocates one class-labeled query per requested instance, jointly predicts scene-compatible object centers, and separately estimates box sizes conditioned on the planned centers and scene context. The second is SceneAlign-Fill which combines geometry- and appearance-aware conditioning, box--class-guided regional attention, and an annotation-region-weighted flow-matching objective to render the planned objects while limiting unintended…

    PDF
  • arXiv cs.CLOct 17

    From Stories to Features: Scaling Concept Vectors for AI Alignment & Interpretability

    Dmitry Scherbakov, Oleg Chernikov, Victoria Khamash, Kirill Afendulev, Alexey Dontsov +3

    We study feature vectors: directions in a language model's activation space that correspond to human-interpretable concepts, such as honesty or deception. Existing unsupervised methods like sparse autoencoders attempt to recover the whole feature space, often at the cost of feature quality and interpretability. We take a more pragmatic route: focusing on concepts relevant to AI safety and alignment, we generate synthetic concept-antagonist story pairs and use the difference of their mean model activations as a feature vector. We scale this approach to 1,036 alignment-relevant concepts using 2M synthetic stories across multiple languages and genres, which we publicly release. Across six models from three model families, our feature vectors reliably generalize to detecting their corresponding concepts in chat dialogues and web text. They form an interpretable geometry shared across models and can causally steer model behavior when injected into activations. We further use these features to analyze model representations during jailbreak attacks, mathematical and agentic reasoning. Our targeted feature construction thus offers a scalable route to studying concepts in language models,…

    PDF
  • arXiv eess.IVOct 17

    Codec-Compatible Learned Compression for 3D Gaussian Splatting

    Feiyang Yu, Qi Yang, Wenjie Huang, Yunfeng Guan, Yiling Xu +1

    Video-based 3D Gaussian Splatting (3DGS) compression methods provide a practical route by representing Gaussian attributes as 2D maps and coding them with standard video codecs. Among these maps, high-dimensional non-DC spherical harmonics (SH-AC) maps contain the largest number of channels and account for a dominant portion of the bitstream. However, their statistics differ substantially from those of natural images, and the nonlinear dependencies among SH-AC coefficients remain insufficiently exploited. To address these issues, we propose CCT-GS, a Codec-Compatible learned Transform framework for 3DGS compression. CCT-GS first learns a generalized SH-AC transform that captures cross-scene regularities and converts SH-AC maps into compact codec-friendly bottleneck maps. It further introduces LoRA-based scene adaptation to recover scene-specific appearance details with lightweight side information. Experiments on MPEG GSC sequences demonstrate that CCT-GS consistently outperforms representative video-based baselines, achieving an average BD-rate reduction of 51.30% over the video-based anchor.

    PDF
  • arXiv cs.MAOct 17

    CARVS: A Congestion-Aware Algorithm for Online Multi-Agent Pickup-and-Delivery in Human-Collaborative Warehouses

    Chaoran Li, Zeyuan Zhao, Shao Zhang

    Intelligent warehouse systems have transformed logistics by integrating robots with minimal infrastructure changes, boosting efficiency and optimizing workflows compared to traditional human-only operations. However, human-robot collaboration introduces new challenges, particularly due to human uncertainty, which leads to dynamic interactions and unpredictable behavior. To address these complexities, this paper presents the Multi-Agent Pickup-and-Delivery with Human Collaboration (MAPDwHC) problem, an extension of the Multi-Agent Pickup-and-Delivery (MAPD) problem that incorporates human unpredictability. This problem adds key constraints, such as dynamic obstacles caused by robots temporarily blocking paths when interacting with humans, and the need for real-time responsiveness. We formalize the MAPDwHC problem with additional constraints and properties. Based on this problem setting, we propose the CARVS algorithm, which improves task assignment and path planning by integrating task swapping, validation checks, and random initialization. CARVS reduces congestion, enhances adaptability to human-robot interactions, and ensures real-time responsiveness. Simulation results show…

    PDF
  • arXiv cs.PLOct 17

    Proving LLM-Generated GPU Kernels Correct and Safe: Floating-Point Verification in Lean and VerCors

    Archibald Browne, Eugene Lee, Cristopher Salvi

    Modern statistical model development begins with a high-level specification in an automatic differentiation framework such as PyTorch, JAX, or TensorFlow, which is then lowered to a target backend by a compiler or implemented manually by a research engineer. In this paper, we study whether frontier language models can correctly perform the latter task by generating GPU kernels from high-level benchmark specifications. We introduce a framework in which a language-model agent uses Velvet, a program verifier for imperative programs embedded in Lean, to prove semantic equivalence between a high-level specification and a generated CUDA kernel under an explicit set of assumptions. It also asks the LLM to prove thread safety and data race freedom of the generated kernel in VerCors, a deductive verifier for parallel code. Our main contribution to the formal verification of LLM- generated GPU kernels is showing that a combination of Lean automation and language-model-guided proof construction can verify a broad set of basic neural- network building blocks over floating-point values, allowing LLMs to implement semantically correct and safe kernels. In our framework, floating-point…

    PDF
  • arXiv cs.CVOct 17

    Cross-polarization pairing for label-free few-shot thin-section classification

    Bingchen Yan

    Few-shot classifiers of rock thin sections are meta-trained on many rock types that a petrographer has identified slide by slide, and this identification is the costly step that new collections lack. We study few-shot recognition of unseen rock types when no training slide is identified, and the only information available is what the microscope records anyway: which slide an image comes from, and whether it was taken in plane-polarized (PPL) or cross-polarized (XPL) light. We first show why generic unsupervised pseudo-tasks fit this setting poorly: the positives they find without labels are either wrong or near-duplicates of the anchor, so they teach the model little. Polarized-light microscopy provides positives that avoid both problems. The PPL and XPL views of one field show the same grains, so they are correct by construction, yet they look very different. We propose cross-polarization pairing (XPP), which treats each slide as a pseudo-class and pairs its PPL and XPL views of the same field location, so that matching must rely on grain shape and texture rather than on colour. On the Nanjing University collection of 108 rock types, with support and query images taken from…

    PDF
  • arXiv cs.SEOct 17

    When Code Becomes an LLM Call: An Empirical Study of Call-Site Contracts in Agentic Systems

    Shihao Weng, Longtian Wang, Yang Feng, Mingfei Cheng, Jia Liu +4

    Software quality has long rested on specifications that state what code must do, and on testing and verification that check that the code does it. Agentic systems change this foundation: they replace parts of their logic, such as choosing the next tool, judging whether an action is allowed, or writing code to run, with calls to a large language model (LLM). The program still relies on what this logic must guarantee, but the model's behavior is not fixed by code, varies across runs, and can be steered by its input. The guarantee must therefore come from the program around each LLM call site, as a contract of pre-conditions, prompt constraints, and post-conditions. We present an empirical study of these contracts in 496 LLM call sites of 40 popular open-source agentic systems (13.4 MLOC, four languages). Using a multi-agent pipeline validated by 17,428 human judgments, we trace where every model output flows, derive an expected contract for each call site without access to its code, and compare it with the contract that the code implements. We find that 48% of LLM outputs reach control flow or execution, and 73% of these never reach a person. Programs enforce 78% of their…

    PDF
  • arXiv cs.LGOct 17

    Theory-Guided Instance-Dependent Early Stopping via Second-Order Loss Dynamics

    Ahad Bin Islam Shoeb, Jamal Uddin Tanvin, Kamrul Hasan, Alve Reduan, Imtiaz Ahmed

    Instance-dependent early stopping (IES) reduces training computation by skipping backpropagation for examples whose losses have stabilized, but the second-order loss-difference criterion used by IES lacks a theoretical justification. We develop Theory-Guided Instance-Dependent Early Stopping (TG-IES), which analyzes this criterion under explicit assumptions and derives a noise-calibrated mastery threshold and a conditional stability bound for instance exclusion. We show that second-order differencing has a favorable bias-variance trade-off over first- and third-order differences in a specific signal-to-noise regime, and that its signal contains both gradient-drift and curvature terms. TG-IES derives its stopping threshold and patience from training-run statistics rather than using the manually selected threshold of IES. Across CIFAR-10 and CIFAR-100, TG-IES saves 53-58% of backpropagation instances in its main convolutional settings while keeping accuracy within 0.1-0.9 percentage points of full training; in the primary ResNet-18/CIFAR-10 setting, this corresponds to 35.7% FLOP-normalized savings. The method also transfers to ViT-Tiny, where it achieves smaller savings and incurs…

    PDF
  • arXiv cs.CLOct 17

    EGIP: An Evidence-Grounded Interaction Protocol for Clinical Agents

    Zecheng Ren, Ruichen Cong, Yi Min Chen, Jing Zhang, Feiyang Chen +6

    Interactive clinical agents acquire evidence through patient dialogue and diagnostic examinations, yet their performance also depends on how the interaction environment exposes information, available actions, and examination results. When these conditions are implicit or inconsistently controlled, final-answer accuracy can conflate diagnostic reasoning with the effects of the interaction protocol. We propose the \textbf{E}vidence-\textbf{G}rounded \textbf{I}nteraction \textbf{P}rotocol (EGIP), which enforces role-specific information boundaries, exposes diagnostic actions without revealing their results, retrieves examination results from stored clinical records, and organizes acquired evidence for final decision-making. By separating evidence acquisition from terminal prediction, EGIP enables different decision strategies to operate on the same observations. We evaluate EGIP across two clinical-agent frameworks, five datasets, and six language models. EGIP improves diagnostic accuracy over native baselines across all primary comparisons. A clinician review further shows that the proportion of automatically scored correct responses jointly judged evidence-supported rises from…

    PDF
  • arXiv math.OCOct 17

    Accelerating Finite-Sum Bilevel Optimization with Fully First-Order Oracles

    Qihao Zhou, Shanshui Niu

    We study nonconvex--strongly-convex bilevel optimization with finite-sum objectives and fully first-order oracles. We propose Sampled Implicit Corrections for Bilevel Optimization (SICBO), which combines a penalty approximation with variance-reduced corrections for the lower-level variables. Under componentwise lower strong convexity, SICBO finds a point $x$ satisfying $\mathbb{E}\|\nablaΦ(x)\|^2\le\varepsilon^2$ within $\tilde{O}(N+\sqrt{N}κ^{7/2}\varepsilon^{-2})$ component-gradient calls, where $N$ is the total number of components and $κ$ is the normalized lower-level condition number. The bound achieves square-root finite-sum dependence using only gradients and preserves the best known deterministic fully first-order condition-number exponent for smooth problems. Our improvement follows from a curvature-dependent bound for nonlinear correction errors, which permits epochs of length $\tildeΘ(\sqrt{N/κ})$ with batches of size $\tildeΘ(\sqrt{Nκ})$. A single-level reduction shows that the dependence on $N$ and $\varepsilon$ is optimal up to logarithmic factors for fixed $κ$.

    PDF
  • arXiv cs.CVOct 17

    Write Once, Query Many: Evolving Compact Reusable Memory for Long Videos

    Kerui Chen, Jinglu Wang, Yun Wang, Xinjiang Wang, Yan Lu

    Long videos often exceed the context capacity of multimodal large language models (MLLMs), while agentic search repeats costly video processing and grounding for each query. Reusable memory can amortize this cost, but must preserve information for questions unknown during construction. We propose Video-EMem, an evolvable video memory harness built on time-anchored perceptual observations. This representation combines compact free-form text with sparse images to preserve semantic content and complementary visual details across temporal scales, supporting temporal navigation without a fixed semantic schema. A Writer encodes each video once by consolidating overlapping multiscale observations, and a Reader retrieves and organizes evidence solely from the resulting memory. With the underlying models frozen, we evolve their workflows and operators using distinct feedback: query-independent source fidelity and coverage for the Writer, and QA failures in evidence localization and utilization for the Reader. Experiments support this separation for generalization beyond development queries, with our evolution strategy improving average accuracy by 7.2% over the unevolved harness. While…

    PDF
  • arXiv cs.LGOct 17

    A Multi-Step Inertial ADMM Algorithm for Federated Learning

    Hao Li, Qingsong Wang, Xihong Yan, Chengcheng Yan, Deren Han

    Federated learning has recently emerged as an important paradigm for large-scale distributed model training, which can be naturally formulated as a class of distributed learning problems. The alternating direction method of multipliers (ADMM) is a widely used approach for solving such problems. However, its practical performance is often hindered by significant communication overhead and system heterogeneity. In this paper, we propose a multi-step inertial ADMM algorithm, called MiFedADMM, for federated learning. The proposed method leverages multiple historical iterates on the server side to construct a higher-order extrapolation after each aggregation to accelerate the convergence behavior. Under mild assumptions, we establish convergence results for the single-step variant of the proposed method and derive an O(1/K) convergence rate. Numerical experiments on both synthetic and real-world datasets demonstrate the effectiveness and improved performance of the proposed method compared with existing approaches.

    PDF
  • arXiv cs.LGOct 17

    From Score to Diagnosis: Search-Independent Post-Diagnosis for Symbolic Regression

    Qian Li, Yuxiao Hu, Juncheng Liu, Yanhao Jia, Yuntian Chen

    Symbolic regression (SR) solvers employ diverse search mechanisms, yet most rely on the same low-information scalar fitness. Such scores provide little guidance on why a skeleton fails or how it should be revised. Recent methods develop new methods to address this bottleneck. Their enhanced feedback mechanisms are tightly coupled to their search processes and are difficult to reuse across diverse SR solvers. Instead, we ask whether a shared feedback mechanism can further improve diverse solvers facing the same bottleneck. To this end, we propose PostDiag, a search-independent feedback mechanism, which can be shared to different SR solvers. PostDiag introduces Patch-wise Feature Profiling (PFP) to capture local behavior through patch-wise features of level, trend, and roughness. Based on PFP, PostDiag quantifies Skeleton Expressiveness Risk by comparing the fitted candidate with the observations, and Skeleton Stability Risk by measuring variability of behavior after bootstrap refitting. The Diagnostic Risk Plane (DRP) combines two risks to determine whether a skeleton should be preserved, repaired, simplified, or rewritten, while the patch-wise discrepancies provide evidence for…

    PDF
  • arXiv cs.LGOct 17

    Structured Latent Dynamics for Long-Horizon Embodied World Models

    Kevin Chen, Yu-Wei Zhan, Haoran Liang, Sen Cui, Changshui Zhang

    Reliable long-horizon prediction remains a central challenge for embodied world models. Although recent generative models can synthesize visually plausible action-conditioned futures, their latent dynamics are typically learned through unconstrained transition modules, which may gradually deviate from coherent physical evolution as predictions are recursively rolled forward. We investigate whether explicitly structuring latent state evolution can improve the stability and utility of such imagined trajectories. To this end, we introduce HWM, a structured dynamics framework that represents backbone latents in a learned phase space consisting of generalized coordinates and momenta. Future states are propagated through dissipative Hamiltonian dynamics and mapped back to the original latent representation through a learnable inverse interface. The resulting formulation can be integrated into existing world-model architectures without redesigning their perception or decoding components, while multi-step transition supervision encourages the structured rollout to remain aligned with the latent trajectories induced by real observations. Controlled simulation experiments show that HWM…

    PDF
  • arXiv cs.CVOct 17

    GTSM: Gaussian Splatting with Thermal State-Space Dynamics for Spatio-Temporal Thermal Field Reconstruction and Prediction

    Yunpeng Zhao, Haoxiang Zhang, Chao Liu

    Temperature-field reconstruction and prediction are important for condition monitoring, process analysis, and state assessment in industrial and dynamic environments. This work aims to recover a four-dimensional spatio-temporal thermal state field directly from two-dimensional observations, without requiring a predefined 3D model, prescribed thermodynamic equation, or predefined heating/cooling trajectory. To this end, we propose the Gaussian Thermal State-Space Model (GTSM), which represents thermal evolution through a shared scene-level latent process and Gaussian-specific local thermal states. The resulting continuous dynamics are propagated using differentiable RK2 integration, allowing thermal evolution to be inferred from multi-view and multi-temporal observations and continuously extrapolated beyond the observed interval. GTSM is designed as a backbone-agnostic thermal dynamics module for Gaussian representations and can be integrated with both static 3D Gaussian Splatting and dynamic 4D Gaussian Splatting, supporting thermal reconstruction and prediction under both static and time-varying target geometry. The reconstructed representation further enables novel-view thermal…

    PDF
Load more