WeightBridge is a lightweight library that streamlines weight transfer between trainers and rollout generators in reinforcement learning systems, particularly for large language models. It automatically maps trainer and rollout weight layouts, then performs redundancy‑free, load‑balanced transfers while supporting various synchronization modes. Experiments show that WeightBridge can cut GPU stall time by up to 42× compared to leading open‑source RL frameworks, and it was easily integrated into two different frameworks by a coding agent.
By Xuanlin Jiang, Samuel Hsia, Michael Kuchnik, Zachary DeVito, Minlan Yu, Carole-Jean Wu
The paper introduces a novel, training‑free, LLM‑driven closed‑loop framework for fusing dual‑source encrypted points of interest (DSEP) to improve land‑use/land‑cover (LULC) mapping. By iteratively refining location transformations and attribute correspondences—using LLM‑based matching, particle swarm optimization, and fuzzy attribute reassessment—the method reduces matching complexity from O(N²) to O(N) and converges in about two iterations. Experiments across 31 Chinese provincial capitals demonstrate a 4.58 m average location residual and 95.12 % attribute accuracy, outperforming existing baselines by 1.77 m and 14.87 % respectively, and enabling georeferencing of encrypted vector data to WGS‑84 without ground control points.
By Chang Li, Xingtao Peng, Yongjun Zhang, Yinfei He, Cairun Huang
SpecialEduBench is a new benchmark for vision‑language models that evaluates their pedagogical competence in language intervention for autistic children across knowledge, skill, and attitude dimensions. It contains 4,537 knowledge items, 200 skill items, and 68 attitude items derived from recorded interventions, with 192 response cells for attitude items that combine pressure and monitoring. Eight leading vision‑language models were tested, none achieving full performance, especially in honesty cells, indicating that current models still struggle with situated teaching tasks.
By Jihoi Na, Taeyeong Kim, Sungjune Kong, Jaemin Jung, Min Joung Park, Kyungtae Joo, Ahhyun Kim, Shim Jaechang, Sooyoung Joo, Dongjin Ka, SeJoong Kim, Jimin Kim, HyunJin Jung, Unggi Lee
arXiv:2609.22702v1 Announce Type: new
Abstract: Accurate flood forecasts several days in advance are essential for flood control, water-resource management, and emergency response. Producing them at...
By Hong Zhang, John K. Hutchison, Rao Kotamarthi, Jeremy Feinstein, Haiwen Guan, Romit Maulik, Vijay P. Ramalingam, Jason Stock, Tom Wall
arXiv:2605.11151v3 Announce Type: replace
Abstract: Offline-to-online reinforcement learning (RL) improves sample efficiency by leveraging pre-collected datasets prior to online interaction. A key ch...
By Andrew Choi, Wei Xu
Video-HopChain introduces a new dataset of 22,550 multi‑hop video questions over 13,378 videos, each question consisting of three to six yes/no sub‑questions whose integer answers sum to a verifiable reward. Training a Qwen3‑VL‑8B model with GRPO on this dataset improves performance across eight video‑understanding benchmarks from 55.4 to 57.9, and the addition of Confidence‑Gated Exploration (CGE) raises the mean to 59.3. The authors release the dataset, checkpoint, and training code for further research.
By Trung Nguyen Quang, Yuhao Dong, Shuo Sun, Shuai Liu, Shulin Tian, Kim-Hui Yap, Ziwei Liu
arXiv:2609.25864v1 Announce Type: cross
Abstract: Visual object removal can eliminate a target from video frames, yet its acoustic trace persists in the soundtrack, causing obvious audio-visual incon...
By Xinyue Guo, Jianxuan Yang, Daiguo Zhou, Jiagao Hu, Yuxuan Chen, Fei Wang, Jian Luan
arXiv:2609.24526v2 Announce Type: replace
Abstract: Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints...
By Foundation Model, Li Auto Inc
arXiv:2609.23790v1 Announce Type: new
Abstract: Every node in a multi-agent large language model (LLM) workflow retrieves context from memory and injects it into its prompt, where those injected toke...
By Vivek Kumar Singh, Preeti Priyam, Gautam Bhowmick
Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed outcomes. Scaling their training requires diverse agentic environments, dependable...
An agent that interacts with users over long periods must recall facts, preferences, events, and changes from a continuously growing interaction history. Existing memory systems often compress interac...
Due to the limited dynamic range of conventional image sensors, captured low dynamic range (LDR) video often suffers from highlight clipping and shadow detail loss, making high-quality high dynamic ra...
Objective assessment of robotic surgery uses instrument kinematics, which must be reconstructed when only video is available. We introduce a kinematic reconstruction network for estimating instrument...
Text-to-speech systems increasingly process user-generated text (UGT) such as ppl and imo, whose pronunciation must be inferred from the canonical rather than surface form. We introduce UGTPhon, the f...
Sparse communication in decentralized zeroth-order learning requires compatible peer-state coordinates. We characterize this one-hop condition and develop \textsf{ZO-COSMO}, coupling two-query estimat...
Gaussian head avatars typically model intrinsic facial appearance as temporally static, omitting subtle cardiac-induced skin-color variation. We propose $\unicode{x1F493}$Heartian, a physiology-aware...
Current literature evaluates large language models (LLMs) on multilingual kinship understanding using multiple choice benchmarks, treating it as a recognition problem. We instead prompt five open weig...
Retraining visual perception pipelines in High-Mix, Low-Volume (HMLV) automotive manufacturing must be carried out under tight annotation, energy, and time budgets, yet most Synthetic Data Generation...
Relational Deep Learning (RDL) models multi-table databases as heterogeneous temporal graphs, and graph transformers currently achieve state-of-the-art performance on benchmarks like RelBench. However...
A key factor in deciding whether to trust an automatic prediction is its confidence score, which should be calibrated to match the actual probability of the prediction being correct. Most confidence c...