rl_rob is an open-source Python library for teaching reinforcement learning. It implements the arc of a modern course, from tabular temporal-difference learning through linear function approximation to deep value-based and policy-gradient methods, with every algorithm written from first principles so that its update ru...
Continuous-time world models generate a latent trajectory through a single ODE integration, but adding stochastic conditioning does not ensure that the model uses it. In our teacher-forced baseline, posterior means vary by only about 1% of the prior scale, and matched and swapped latents yield indistinguishable reconst...
Mingyang Lyu, Yinqian Sun, Gongce Cao et al.· 0 citations
We study the general problem of estimating $D(\dde(S))$, the probability that an unknown distribution $D$ assigns to an event determined by a sample $S$ of $n$ i.i.d.\ draws from $D$ through a known mapping $\dde$. The estimation algorithm knows $\dde$ and $S$ but does not have access to any additional samples from $D$...
Vitaly Feldman, Satyen Kale, Vinod Raman et al.· 0 citations
We develop a divergence-kernel method for jointly optimizing neural SDE drift and diffusion fields and the initial Gaussian distribution, using losses that depend directly on the terminal density. In two- and eight-dimensional Gaussian-mixture experiments, we learn time-independent fields and obtain far fewer off-mode...
Ang-Xiu Ni· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
In pattern analysis, models trained independently for the same task often develop complementary capabilities through differences in architecture, data, and optimization. Exploiting complementarity while retaining independent deployment is central to collaborative learning. Most methods establish transfer by reducing di...
Zexing Zhang, Jichao Li, Tianyang Lei et al.· 0 citations
Why does length generalization (LG) depend so sharply on the positional encoding (PE)? Relative schemes extrapolate fixed offsets, absolute schemes fix positions, and neither handles growing offsets. We give a realizability theory for a deliberately controlled abstraction, a single positional-only attention head, that...
Results show that benchmark construction can alter a post-correction training decision and that support size alone does not characterize the remaining value of representation adaptation, and that support size alone does not characterize the remaining value of representation adaptation.
Ze-Xing Zhang, Ji-Chao Li, Tian-Yang Lei et al.· 0 citations
Multimodal federated learning (MFL) trains a shared model by aggregating client updates without exchanging raw data. Under missing modalities, clients adapt active modality encoders and a shared prediction block (fusion and classifier) to different input subsets. This raises two server-side questions: which clients sho...
In this paper, we study a general frequency principle under gradient descent training for the finite linear approximation classes. Under suitable assumptions, we prove that the learner amplitude relative to the target amplitude vanishes at high frequencies, uniformly throughout training. We also establish sufficient co...
CAP (Candidate Acquisition Policy), which models shared structure and task-specific variation in fixed historical records to sample interactive practice functions to indicate that sparse records from completed related tasks can support adaptive query decisions on new tasks, making more effective use of limited, costly...
Natural-language skills enable large language model (LLM) agents to reuse procedures across tasks, yet most systems retrieve individual skills from a flat SkillBank without explicitly modeling the high-level strategy that governs their selection and use. We introduce TalentRL, a strategy-guided reinforcement learning f...
Huancheng Chen, Xiaodi Sun, Zhaoqiong Huang et al.· 0 citations
Equivariant linear maps cannot mix non-isomorphic irreducible representations, whereas nonlinear activations can. We develop a degree-resolved version of this nonlinear interaction picture and use the resulting block inventory to construct Specht Triple, a residual on unordered graph triples. On a synthetic structural...
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.
MIT News · Artificial Intelligence· news.mit.eduOct 28, 2026
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
MIT News · Artificial Intelligence· news.mit.eduOct 27, 2026
Prabha Jha used her experience with MIT Open Learning’s program for senior executives to develop AI solutions for her employer, Verizon, and to write a book.
