The paper introduces Reflection-aware Gaussian Splatting (RGS), a physically-based deferred rendering framework that improves novel view synthesis for reflective objects. RGS leverages a powerful 3D foundation model to provide a strong geometric prior and employs cross-view shape consistency regularization to prevent surface collapse and reduce geometric hollows. Additionally, a reflection-aware densification strategy captures specular variations across views, resulting in higher-quality renderings of reflective objects.
By Xiaobiao Du, Yida Wang, Cheng Bi, Kun Zhan, Xin Yu
The paper introduces CalfVO, a monocular visual odometry system that operates without camera intrinsics, test‑time optimization, bundle adjustment, or loop closure. Using a transformer, it predicts relative poses with separate rotation and translation confidences over overlapping image windows, then aggregates these predictions via a confidence‑weighted module to produce a single trajectory. CalfVO achieves the highest accuracy among calibration‑free methods across five benchmarks and runs at 53 FPS, outperforming all baselines.
By Vladimir Yugay, Duy-Kien Nguyen, Theo Gevers, Cees G. M. Snoek, Martin R. Oswald
BioPhys-Bridge is a newly released benchmark dataset designed to evaluate language models on evidence‑grounded scientific reasoning within biophysical literature. Each of its 500 cases includes evidence blocks, stable IDs, quantitative values, units, equations, assumptions, mechanisms, and next‑step decisions, covering six biological domains and nine physical model families. The dataset enforces strict quality gates and has already been evaluated against several models, with DeepSeek‑V4‑Flash achieving the highest evidence‑ID F1 score of 0.360.
By Qingyang Xu
The paper introduces a 202-scenario benchmark to evaluate how large language models (LLMs) handle safety-critical authorization decisions for vehicle voice commands. It tests two local open-weight models and three API-based LLMs, finding alignment scores ranging from 40.1% to 89.1% and noting persistent false execution errors. The study concludes that structured LLM decisions alone are insufficient for safety, recommending an independent enforcement layer to verify tool permissions and vehicle-state constraints before any vehicle function is invoked.
By Diba Afroze, Xingli Zhang, Yazhou Tu, Xiali Hei
When2Think introduces a post‑training framework that dynamically allocates reasoning depth in Large Reasoning Models based on instance difficulty. The method uses Instance‑level Difficulty‑Aware Control (IDAC) to shape rewards with pre‑computed accuracy and token usage statistics, enabling stable, critic‑free optimization without learned reward models. Experiments on mathematical benchmarks show that When2Think improves accuracy‑efficiency trade‑offs, achieving higher Pass@3 scores while reducing token usage compared to baseline models.
By Jaejun Shim, HyunJin Kim, Young Jin Kim, JinYeong Bak
The paper evaluates three approaches—LLM-Z3 full replanning, IPyHOPPER hierarchical repair, and iTIMO local-revision—for revising travel itineraries after disruptions such as flight cancellations or hotel unavailability. Using two TREK-derived benchmark sets (500 single-disruption cases and 200 compound-disruption cases), the study compares effectiveness, plan stability, and computational cost. Results show LLM-Z3 with Gemini achieves the highest compound-disruption success, IPyHOPPER nearly matches single-disruption success while preserving more of the original itinerary, and iTIMO makes fewer edits but consumes more tokens, offering practical guidelines for balancing feasibility recovery, commitment preservation, and computational cost.
By Xiaofei Yuan, Yan Zhang, Shaobo Qiao, Huangleshuai He, Leyan Ni, Mingchen Ju, Lujia Yang, Sijia Xu, Yifu Tang, Zhengyi Yang
FedeRICo is a federated traffic forecasting framework that addresses heterogeneity across client sensor subgraphs by combining gradient-level collaboration with boundary-aware residual communication. It uses a dual-branch architecture: a globally guided branch for transferable forecasting structure and a private residual branch that preserves client-specific corrections and incorporates boundary residual signals. Experiments on four real-world traffic benchmarks show that FedeRICo outperforms state‑of‑the‑art federated spatial‑temporal baselines while keeping training runtime competitive.
By Fermin Orozco, Man Luo, Johan Wahlstr\"om
KoNeoBench is a curated dataset designed to evaluate large language models’ understanding of Korean neologisms. It contains 1,785 recently attested Korean words from online news since 2020, each accompanied by usage examples, word‑formation analyses, and dictionary‑style definitions. The authors define four evaluation tasks, report results from recent models and a human baseline, and find that current LLMs struggle with recovering source components, distinguishing semantic categories, and generating accurate definitions.
By Soha Lee, Soojin Lee, Heesung Yang, Hyunju Song, Hyunji Lee, Jinsan An, Jeongwan Shin, Jin Hyun Park, Jun Lee, Hyeyoung Park, Kilim Nam
PointEvent introduces serialized motion evidence accumulation for event-based tiny object detection, treating motion continuity as an ordered evidence propagation process. The method organizes event streams into locality‑preserving spatiotemporal paths and chronology‑preserving temporal paths, alternating serialized scans across complementary orders to consolidate fragmented motion evidence. A lightweight event‑wise state‑space framework with a high‑resolution event branch and compact context modulation achieves state‑of‑the‑art performance with the fewest parameters and fastest inference among compared methods.
By Zongze Wu, Baofeng Jia, Weiqi Yan, Jingyuan Zhang, Yu Zang, Xiaoyu Chen, Jing Han
FacetCRS is a conversational recommender system that tackles the filter‑bubble problem by learning multi‑faceted user preferences—entity, word, context, and review facets—through natural language interactions. The framework adaptively models these preference facets and incorporates external knowledge to provide diverse recommendations. Experiments on two benchmark datasets show that FacetCRS outperforms existing methods in reducing filter bubbles and improving recommendation quality.
By Yongsen Zheng, Ziliang Chen, Jinghui Qin, Liang Lin
SCGFM-ART is a structure‑centric graph foundation model that aligns arbitrary graphs onto a shared relational atlas using Amortized Relational Transport (ART). The atlas, defined by a finite set of relational landmarks, provides a universal coordinate system, while ART predicts end‑to‑end graph‑to‑base transport plans, eliminating costly runtime Gromov‑Wasserstein optimizations. The framework decomposes graphs into global relational response coordinates and local node‑to‑role structural correspondences, enabling unified representations that resolve structural and semantic heterogeneity across diverse graph domains.
By Xiaodong He, Xincheng Wang, Zhao Kang
SCICONVBENCH is a benchmark designed to evaluate large language models (LLMs) on multi‑turn clarification tasks in computational science. It focuses on two key abilities: eliciting missing information (disambiguation) and resolving contradictory requests (inconsistency resolution) across four domains—fluid mechanics, solid mechanics, materials science, and partial differential equations. The benchmark pairs a structured task ontology with a rubric‑based evaluation framework, measuring LLM performance in clarification behavior, conversational grounding, and final‑specification fidelity, and reveals that even top models only resolve about 52.7% of disambiguation cases in fluid mechanics while often making ungrounded assumptions.
By Nithin Somasekharan, Youssef Hassan, Shiyao Lin, Gihan Panapitiya, Patrick Emami, Anurag Acharya, Sameera Horawalavithana, Shaowu Pan
The paper investigates how reinforcement learning can be effectively applied to diffusion models for visual tasks, focusing on the role of likelihood estimation. By systematically separating policy‑gradient objectives, likelihood estimators, and rollout sampling schemes, the authors find that using an evidence lower bound (ELBO) based likelihood estimator computed from the final generated sample is the key factor for stable and efficient RL optimization, outweighing the choice of loss function. Experiments on SD 3.5 Medium across multiple reward benchmarks confirm that this approach improves GenEval scores from 0.24 to 0.95 in 90 GPU hours, outperforming existing methods such as FlowGRPO and the current state‑of‑the‑art without reward hacking.
By Jaemoo Choi, Yuchen Zhu, Wei Guo, Petr Molodyk, Bo Yuan, Jinbin Bai, Yi Xin, Molei Tao, Yongxin Chen
The paper introduces a new Bayesian optimization approach tailored for generative models used in de novo discovery pipelines. By employing a linear surrogate model constrained to a spherical domain—where high‑dimensional latent vectors naturally concentrate—the authors derive nearly closed‑form solutions for both surrogate modeling and acquisition, achieving at least a 100‑fold speedup over existing methods. This acceleration enables Bayesian optimization to be used as a practical drop‑in component in pipelines that previously found it too slow to consider.
By Donney Fan, Colin Doumont, Aleksandra Kalisz, Paul Duckworth, Jacob R. Gardner, Henry Moss, Geoff Pleiss
CoRe is a model‑agnostic learning objective for direct multivariate time‑series forecasting that replaces pointwise errors with two output‑space constraints: a frequency coherence loss aligning predicted and target spectra, and a low‑rank relational graph loss matching pairwise differences in a PCA subspace. The objective introduces no trainable parameters and can be applied to existing forecasting backbones by changing only the loss. Experiments on standard benchmarks show that CoRe improves strong baselines, compares favorably with recent forecasting objectives, and remains effective across different backbones, datasets, and hyperparameter settings.
By Xiaoyu Lin, Huiran Duan, Yining Liu, Zhixiang Wu, Chu Lin, Lin Lu
The paper introduces a simulation-driven framework for diagnosing transformer faults using dissolved-gas analysis. It employs a variational quantum classifier (VQC) with a two-qubit representation, domain-aware feature modeling from Duval geometry, and a hybrid ZX-YY feature map to capture nonlinear gas interactions. Extensive simulation, noise-aware emulation, and limited hardware tests show high diagnostic accuracy, strong generalization, and robustness to realistic noise while using minimal quantum resources.
By Huy Hoang Le, Ba Tu Phung, Dai Huynh, Kim-Anh Nguyen
The paper introduces GPUB, a large-scale benchmark for grounded product understanding in e‑commerce livestream videos, featuring 3,000 livestreams, 31K fashion products, and multi‑moment temporal annotations. It defines three evaluation tasks, with the main task (GPrU) requiring simultaneous product identification and moment localization. Existing multimodal models perform poorly on GPrU, prompting the authors to develop UniPro, which improves performance by learning product‑aligned, temporally structured representations.
By Xinyu Zhang, Junjie Chen, Jiawei Ge, Qianlong Li, Libin Ma, Baokun Pan, Yahui Luo
The paper introduces REVEAL, a diagnostic benchmark that stresses Video‑Language Models (VidLMs) on five controlled probes—camera‑motion sensitivity, cross‑frame integration, video sycophancy, language‑only shortcuts, and temporal expectation bias—to assess how well these models encode and use visual evidence. Experiments on 12 VidLMs reveal systematic failures: some visual signals are never reliably encoded, while others are overridden by model priors, leading to performance below chance on several probes that humans solve with high accuracy. Mechanistic probes further pinpoint where and why visual evidence is lost, demonstrating that under assertive prompts a model’s output becomes nearly invariant to real versus random video input, rendering visual evidence causally inert.
By Sethuraman T V, Savya Khosla, Aditi Tiwari, Vidya Ganesh, Rakshana Jayaprakash, Aditya Jain, Vignesh Srinivasakumar, Onkar Kishor Susladkar, Srinidhi Sunkara, Aditya Shanmugham, Rakesh Vaideeswaran, Abbaas Alif Mohamed Nishar, Simon Jenni, Rohan Maheshwari, Derek Hoiem
The paper introduces a visual odometry frontend that automatically and continuously adapts its parameters using an image-conditioned reinforcement learning policy. The policy selects key tuning values—FAST detection threshold, KLT patch size, and RANSAC rejection threshold—based on a lightweight image embedding and frontend statistics, with a privileged critic aiding training. Trained on synthetic data, the approach transfers zero‑shot to real-world benchmarks, improving the tracking‑computation trade‑off by up to 8% in accuracy and 57% in runtime compared to static configurations.
By Simone Nascivera, Leonard Bauersfeld, Jeff Delaune, Davide Scaramuzza
The paper introduces a hybrid quantum-classical neural network (HQNN) for predicting peptide-HLA binding, a key step in personalized cancer immunotherapy. HQNN combines biological feature encoding, quantum feature extractors, and a quantum-enhanced classifier, outperforming a classical CNN baseline on two HLA alleles across all training sizes, especially when data are scarce. Ablation studies and noise-aware simulations confirm the benefits of the quantum components and the robustness of the approach under realistic hardware noise.
By Chenyan Jia, Cong Guo, Siyue Chen, Pengpeng Ye, Xiaochun Chen