Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes. Yet LLMs exhibit systemic deficiencies in key metacognitive faculties: they hallucinate with high confidence, fail to recognize knowledge boundaries, and misrepresent their internal un...
Gabrielle Kaili-May Liu, Avi Caciularu, Gal Yona et al.· 0 citations
Federated Learning (FL) enables multiple clients to collaboratively train machine learning models without sharing their local data. However, heterogeneity in client data and the presence of unreliable or adversarial updates make effective server aggregation challenging, motivating methods that adapt client contribution...
Dario Fenoglio, Daniil Kirilenko, Martin Gjoreski et al.· 0 citations
Real-world evaluation is the gold standard for robot manipulation policies because it tests them against the physical conditions and deployment challenges they are ultimately designed to handle. However, real-world evaluation is also the bottleneck for iterating on robot imitation learning policies: it is costly, diffi...
Haoxu Huang, Tongsam Zheng, Yifan Chen et al.· 0 citations
Embodied foundation models have recently been widely used to improve robot generalization and task success rates. Previous works apply lossy efficient-inference techniques such as quantization, pruning, and asynchronous inference, accepting small action quality degradation in exchange for lower per-inference computatio...
Yujin Wang, Junli Chen, Yixuan Li et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Recursive self-training can degrade neural generative models when generated data is reused without fresh human data or external quality control. We study this risk in code LLMs, where AI-generated code can enter real repositories, later become training data, and create a repository-scale self-training loop. While softw...
Robot world models now generate synthetic manipulation videos, but evaluating them is hard: realistic-looking outputs often violate physical laws, temporal consistency or task logic, while conventional metrics and monolithic Vision-Language Model (VLM) judges return scores that do not say what failed. We present RoboGa...
Minh-Loi Nguyen, Nghiem T. Diep, Hung K. Nguyen et al.· 0 citations
SPARK is introduced, a novel framework that formulates parametric knowledge control as a latent participation policy learning problem, enabling LLMs to adaptively regulate the contribution of parametric knowledge during generation.
Ruochang Li, Peng-Cheng Huang, Zheng-Hao Liu et al.· 2 citations
Neural surrogate models offer fast approximate mappings from PDE parameters to solutions, but they typically treat solving as a purely statistical task: once trained, they struggle to correct their own constraint violations and extrapolate beyond the training distribution. Recent hybrid methods promote physical correct...
Haina Jiang, Liam Wang, Peng-Chen Chen et al.· 0 citations
Sequential user behavior modeling is widely adopted in industrial recommender systems; however, significant gaps remain in financial services, where pre-login web interactions and authenticated in-app experiences differ drastically. Specifically, pre-login web users typically explore new products, whereas logged-in app...
Dianjing Fan, Yao Li, Kyaw Hpone Myint et al.· 0 citations
Group Relative Policy Optimization (GRPO) typically requires multiple rollouts per prompt to estimate relative credit, incurring substantial sampling cost and exacerbating training asynchrony. This limitation is particularly severe for scientific reasoning agents, where each trajectory may involve long-horizon reasonin...
Dictionary learning has long been studied from both optimization and probabilistic perspectives. While formulations with element-wise sparsity regularization (e.g., L1-based sparse coding) admit well-established probabilistic interpretations, many structured variants that impose global constraints lack a clear and trac...
Reinforcement learning for robot manipulation is often bottlenecked by reward design, especially in long-horizon tasks: sparse success rewards provide weak supervision, while hand-crafted dense rewards are tedious to design and generalize poorly across tasks. Progress-based reward models offer a promising alternative b...
Pengzhi Yang, Xinyu Wang, Pengyu Jing et al.· 0 citations
