搜索结果：Retrospective

Trajectory prediction is critical for autonomous driving, enabling safe and efficient planning in dense, dynamic traffic. Most existing methods optimize prediction accuracy under fixed-length observations. However, real-world driving often yields variable-length, incomplete observations, posing a challenge to these methods. A common strategy is to directly map features from incomplete observations to those from complete ones. This one-shot mapping, however, struggles to learn accurate representations for short trajectories due to significant information gaps. To address this issue, we propose a Progressive Retrospective Framework (PRF), which gradually aligns features from incomplete observations with those from complete ones via a cascade of retrospective units. Each unit consists of a Retrospective Distillation Module (RDM) and a Retrospective Prediction Module (RPM), where RDM distills features and RPM recovers previous timesteps using the distilled features. Moreover, we propose a Rolling-Start Training Strategy (RSTS) that enhances data efficiency during PRF training. PRF is plug-and-play with existing methods. Extensive experiments on datasets Argoverse 2 and Argoverse 1 demo

LLM-based agents trained with reinforcement learning optimize step-wise action prediction but lack metacognitive awareness of task progress, inducing a gap that hinders long-horizon scaling. A pilot study reveals that online progress prompting hurts performance while retrospective demonstrations help, yet this capability cannot emerge from outcome-reward training alone. We present RePro, Retrospective Progress-Aware Training, a framework that trains agents to self-generate progress signals via a forward-then-reflect rollout paradigm: the agent executes actions online, then retrospectively reassesses its step-wise progress given the completed trajectory and known outcome. RePro initializes with a Retrospection Warmup that teaches reflection format from minimal external demonstrations, then further trains through RePro-PO with a composite reward that produces self-generated signals without continuous external supervision. Experiments on WebShop, ALFWorld, and Sokoban show that RePro enhances the Qwen family's performance, with up to $12\%$ absolute success rate gains.

Retrospective novel view synthesis (NVS) of dynamic scenes is fundamental to applications such as sports. Recent dynamic 3D Gaussian Splatting (3DGS) approaches introduce temporally coupled formulations to enforce motion coherence across time. In this paper, we argue that, in a synchronized multi-view (MV) setting typical of sports, the dynamic scene at each time step is already strongly geometrically constrained. We posit that the availability of calibrated, synchronized viewpoints provides sufficient spatial consistency, and therefore, explicit temporal coupling, or complex multi-body constraints seems unnecessary for retrospective NVS. To this end, we propose an approach tailored for synchronized MV dynamic scene. By initializing the SfM-derived point cloud at the start time and propagating optimized Gaussians over time, we show that efficient retrospective NVS can be achieved without imposing a temporal deformation constraint. Complementing our methodological contribution, we introduce a Dynamic MV dataset framework built on Blender for reproducible NeRF and 3DGS research. The framework generates high-quality, synchronized camera rigs and exports training-ready datasets in stan

Search-engine date filters are widely used to enforce pre-cutoff retrieval in retrospective evaluations of search-augmented forecasters. We show this approach is unreliable across two major search engines: auditing Google Search's before: filter and DuckDuckGo's date-range filter, we find that at least one retrieved page contains major post-cutoff leakage for 71% of questions on Google and 81% on DuckDuckGo, and the answer is directly revealed for 41% and 55%, respectively. Using gpt-oss-120b to forecast with these leaky documents, we demonstrate inflated prediction accuracy (Brier score 0.10 vs. 0.24 with leak-free documents). We characterize recurring leakage mechanisms, including updated articles, related-content modules, unreliable metadata, and absence-based signals, and argue that date-restricted search on these engines is insufficient for credible retrospective evaluation. We recommend stronger retrieval safeguards or evaluation on frozen, time-stamped web snapshots.

Retrospective meetings play a vital role in agile development by facilitating team reflection on past work to enhance effectiveness. These meetings address various social aspects, including team dynamics, individual performance, processes, and technologies, ultimately leading to actions for improvement. Despite their importance, limited research has explored how these meetings handle forms of social debt, particularly Community Smells -- recurring dysfunctional patterns in team dynamics, such as poor communication or isolated work practices. This study seeks to understand how retrospective meetings address a few core Community Smells, examining whether these meetings help identify smells, make it possible to formulate refactoring strategies, support the monitoring of refactoring actions, and contribute to preventing the most prominent Community Smells. We conducted semi-structured interviews with 15 practitioners from diverse organizations who regularly participate in retrospective meetings. The interviewees shared their experiences with retrospectives, the challenges discussed, and subsequent improvement actions. The study focused on the four most cited Community Smells in the lit

Humans can infer hidden physical processes from sparse observations, yet current evaluation protocols for Vision Language Models fail to assess whether such physical reasoning is genuinely captured. To address this gap, we introduce Retrospective Physical Process Reasoning, a new evaluation paradigm to reason backward from outcomes under explicit physical constraints. Building on the paradigm, we present RetroHolmes, the first real-world benchmark for Retrospective Physical Process Reasoning, comprising object-centric image pairs annotated with reachability labels and causal step sequences across diverse physical transitions. Using RetroHolmes, we analyze state of the art Vision Language Models and uncover systematic failure modes, including judgment bias in reachability assessment and belief dominance over physical evidence, mirroring sycophancy behavior observed in large language models. We further demonstrate a simple analysis-by-synthesis instantiation with visual simulation as an intermediate step, validating the diagnostic value of RetroHolmes and highlighting the importance of physically grounded intermediate representations for physical reasoning.

Large Language Models have demonstrated profound utility in the medical domain. However, their application to autonomous Electronic Health Records~(EHRs) navigation remains constrained by a reliance on curated inputs and simplified retrieval tasks. To bridge the gap between idealized experimental settings and realistic clinical environments, we present AgentEHR. This benchmark challenges agents to execute complex decision-making tasks, such as diagnosis and treatment planning, requiring long-range interactive reasoning directly within raw and high-noise databases. In tackling these tasks, we identify that existing summarization methods inevitably suffer from critical information loss and fractured reasoning continuity. To address this, we propose RetroSum, a novel framework that unifies a retrospective summarization mechanism with an evolving experience strategy. By dynamically re-evaluating interaction history, the retrospective mechanism prevents long-context information loss and ensures unbroken logical coherence. Additionally, the evolving strategy bridges the domain gap by retrieving accumulated experience from a memory bank. Extensive empirical evaluations demonstrate that Re

Wildfires threaten biodiversity, carbon stocks, and management capacity in the Brazilian Cerrado, where Conservation Units and their official buffer zones must allocate prevention resources under a strong dry-season fire regime. This work develops a retrospective daily active-fire detection benchmark for the Cerrado portion of Minas Gerais, Brazil, using INPE BDQueimadas reference satellite labels (AQUA_M-T), constrained pseudo absences with same-year MapBiomas Collection 9 land-cover filtering, and four nested covariate stages extracted through Google Earth Engine. Logistic Regression, Random Forest, and XGBoost are evaluated under five-fold time-series cross-validation on a global training base and on independent imbalanced test sets spatially held out to Parque Estadual do Pau Furado and Parque Estadual da Serra do Cabral with their official buffer zones. AUC-PR is the primary metric, with AUC-ROC, threshold precision and recall, SHAP explanations, and retrospective score maps used as complementary diagnostics. Temporal cross-validation showed the highest mean AUC-PR at the complete temporal-memory stage for all three model families. Held-out AOI tests were weaker under the stri

Retrospective causal questions ask what would have happened to an observed individual had they received a different treatment. We study the problem of estimating $μ(x,y)=\mathbb{E}[Y(1)\mid X=x,Y(0)=y]$, the expected counterfactual outcome for an individual with covariates $x$ and observed outcome $y$, and constructing valid prediction intervals under the Neyman-Rubin superpopulation model. This quantity is generally not identified without additional assumptions. To link the observed and unobserved potential outcomes, we work with a cross-world correlation $ρ(x)=cor(Y(1),Y(0)\mid X=x)$; plausible bounds on $ρ(x)$ enable a principled approach to this otherwise unidentified problem. We introduce retrospective counterfactual estimators $\hatμ_ρ(x,y)$ and prediction intervals $C_ρ(x,y)$ that asymptotically satisfy $P[Y(1)\in C_ρ(x,y)\mid X=x, Y(0)=y]\ge1-α$ under standard causal assumptions. Many common baselines implicitly correspond to endpoint choices $ρ=0$ or $ρ=1$ (ignoring the factual outcome or treating the counterfactual as a shifted factual outcome). Interpolating between these cases through cross-world dependence yields substantial gains in both theory and practice.

Spike activity has been the dominant neural signal for behavior decoding due to its high spatial and temporal resolution. However, as brain-computer interfaces (BCIs) move toward high channel counts and wireless operation, the high sampling frequency of spike signals becomes a bottleneck due to high power and bandwidth requirements. Local field potentials (LFPs) represent a different spatial-temporal scale of brain activity compared to spikes, offering key advantages including improved long-term stability, reduced energy consumption, and lower bandwidth requirement. Despite these benefits, LFP-based decoding models typically show reduced accuracy and often rely on non-causal architectures that are unsuitable for real-time deployment. To address these challenges, we propose REALM: a retrospective distillation framework that enables causal LFP decoding. Inspired by offline-to-online distillation strategies in speech recognition, REALM transfers representational knowledge from a pretrained multi-session bidirectional LFP model to a causal version for real-time deployment. We first pretrain a bidirectional Mamba-2 teacher model using a masked autoencoding objective. We then distill thi

Since the seminal work by Prentice and Pyke (1979), the prospective logistic likelihood has become the standard method of analysis for retrospectively collected case-control data, in particular for testing the association between a single genetic marker and a disease outcome in genetic case-control studies. When studying multiple genetic markers with relatively small effects, especially those with rare variants, various aggregated approaches based on the same prospective likelihood have been developed to integrate subtle association evidence among all considered markers. In this paper we show that using the score statistic derived from a prospective likelihood is not optimal in the analysis of retrospectively sampled genetic data. We develop the locally most powerful genetic aggregation test derived through the retrospective likelihood under a random effect model assumption. In contrast to the fact that the disease prevalence information cannot be used to improve the efficiency for the estimation of odds ratio parameters in logistic regression models, we show that it can be utilized to enhance the testing power in genetic association studies. Extensive simulations demonstrate the a

Recent advancements in Large Language Models (LLMs) have demonstrated substantial capabilities in enhancing communication and coordination in multi-robot systems. However, existing methods often struggle to achieve efficient collaboration and decision-making in dynamic and uncertain environments, which are common in real-world multi-robot scenarios. To address these challenges, we propose a novel retrospective actor-critic framework for multi-robot collaboration. This framework integrates two key components: (1) an actor that performs real-time decision-making based on observations and task directives, and (2) a critic that retrospectively evaluates the outcomes to provide feedback for continuous refinement, such that the proposed framework can adapt effectively to dynamic conditions. Extensive experiments conducted in simulated environments validate the effectiveness of our approach, demonstrating significant improvements in task performance and adaptability. This work offers a robust solution to persistent challenges in robotic collaboration.

In Agile/Scrum software development, the idea of retrospective meetings (retros) is one of the core elements of the project process. In this paper, we present our work in progress focusing on two aspects: analysis of potential usage of generative AI for information interaction within retrospective meetings, and visualisation of retros' information to software development teams. We also present our prototype tool RetroAI++, focusing on retros-related functionalities.

Lidar odometry aims to estimate the ego-motion of a mobile platform from a stream of lidar scans. Traditional scan-to-map approaches register each scan against a single, evolving map, which propagates registration errors over time. To mitigate this, we propose a multi-submap approach where the current scan is registered against multiple overlapping submaps instead of a single static map. By optimizing the resulting constraints in a pose graph, our method enables not only precise estimation of the current pose, but also retrospective refinement of the submaps' anchor points, which improves short-term consistency and long-term accuracy. We demonstrate that our approach achieves significant accuracy gains over several state-of-the art lidar odometry methods on a variety of automotive datasets while simultaneously maintaining real-time performance. Ablation studies confirm the critical role of multiple registrations and retrospective refinement of the map as core factors for our accuracy gains. Code and raw results are available on our public GitHub at https://github.com/Fusion-Goettingen/RAL_2026_Kurda_Online.

Tool-Integrated Reasoning (TIR) with search engines enables large language models to iteratively retrieve up-to-date external knowledge, enhancing adaptability and generalization in complex question-answering tasks. However, existing search agent pipelines typically depend on reinforcement learning based optimization, which often suffers from sparse outcome rewards, leading to inefficient exploration and unstable training. We introduce CriticSearch, a fine-grained credit-assignment framework that supplies dense, turn-level feedback via a retrospective critic mechanism. During training, a frozen, asymmetric critique LLM retrospectively evaluates each turn using privileged information from the full trajectory and gold answers, converting these assessments into stable, dense rewards that guide policy improvement. Experimental results across diverse multi-hop reasoning benchmarks demonstrate that CriticSearch consistently outperforms existing baselines, achieving faster convergence, improved training stability, and higher performance.

Understanding how users authentically interact with Large Language Models (LLMs) remains a significant challenge in human-computer interaction research. Most existing studies rely on self-reported usage patterns or controlled experimental conditions, potentially missing genuine behavioral adaptations. This study presents a behavioral analysis of the use of English-speaking urban professional ChatGPT in India based on 238 authentic, unedited user prompts from 40 participants in 15+ Indian cities, collected using retrospective survey methodology in August 2025. Using authentic retrospective prompt collection via anonymous social media survey to minimize real-time observer effects, we analyzed genuine usage patterns. Key findings include: (1) 85\% daily usage rate (34/40 users) indicating mature adoption beyond experimental use, (2) evidence of cross-domain integration spanning professional, personal, health and creative contexts among the majority of users, (3) 42.5\% (17/40) primarily use ChatGPT for professional workflows with evidence of real-time problem solving integration, and (4) cultural context navigation strategies with users incorporating Indian cultural specifications in

Continuous Medical Education (CME) plays a vital role in physicians' ongoing professional development. Beyond immediate diagnoses, physicians utilize multimodal diagnostic data for retrospective learning, engaging in self-directed analysis and collaborative discussions with peers. However, learning from such data effectively poses challenges for novice physicians, including screening and identifying valuable research cases, achieving fine-grained alignment and representation of multimodal data at the semantic level, and conducting comprehensive contextual analysis aided by reference data. To tackle these challenges, we introduce Medillustrator, a visual analytics system crafted to facilitate novice physicians' retrospective learning. Our structured approach enables novice physicians to explore and review research cases at an overview level and analyze specific cases with consistent alignment of multimodal and reference data. Furthermore, physicians can record and review analyzed results to facilitate further retrospection. The efficacy of Medillustrator in enhancing physicians' retrospective learning processes is demonstrated through a comprehensive case study and a controlled in-l

The intrinsic capability to continuously learn a changing data stream is a desideratum of deep neural networks (DNNs). However, current DNNs suffer from catastrophic forgetting, which interferes with remembering past knowledge. To mitigate this issue, existing Continual Learning (CL) approaches often retain exemplars for replay, regularize learning, or allocate dedicated capacity for new tasks. This paper investigates an unexplored direction for CL called Retrospective Feature Estimation (RFE). RFE learns to reverse feature changes by aligning the features from the current trained DNN backward to the feature space of the old task, where performing predictions is easier. This retrospective process utilizes a chain of small feature mapping networks called retrospector modules. Empirical experiments on several CL benchmarks, including CIFAR10, CIFAR100, and Tiny ImageNet, demonstrate the effectiveness and potential of this novel CL direction compared to existing representative CL methods, motivating further research into retrospective mechanisms as a principled alternative for mitigating catastrophic forgetting in CL. Code is available at: https://github.com/mail-research/retrospectiv

Physical inactivity is the fourth leading risk factor of mortality globally. Hence, understanding the physical activity (PA) patterns of youth is essential to manage and mitigate non-communicable diseases. As digital citizen science approaches utilizing citizen-owned smartphones to ethically obtain PA big data can transform PA surveillance, this study aims to understand the frequency of PA reported by youth using smartphone-deployed retrospective validated surveys compared to prospective time-triggered mobile ecological momentary assessments (mEMAs). Using a digital citizen science methodology, this study recruited youth citizen scientists (N = 808) in 2018 (August 31- December 31) in Saskatchewan, Canada. Youth citizen scientists (age 13 to 21) reported their PA using prospective mEMAs and retrospective surveys over an eight-day period. A significant difference was found in reporting the frequency of PA retrospectively vs. prospectively via mEMAs (p < 0.000). Ethnicity, parental education, and strength training were associated with prospective PA frequency; however, no associations were significant with retrospective PA frequency. With access to ubiquitous digital devices growi