Category
17,191 papers
The classical GMM-HMM aligner is revisit with upsampled WavLM features instead of MFCCs, explicit phone units for fillers and non-lexical vocal events trained on verbatim-annotated spontaneous speech, and a discriminative projection fitted on clean and noise-corrupted feature pairs to improve robustness.
A structure-aware kernel design is presented that removes irrelevant state coordinates and decouples state and spatial dependencies through a tensor-product covariance and allows qualitative knowledge of spatial heterogeneity to be incorporated by selecting an appropriate spatial kernel without requiring an analytical...
We study when logged contextual-bandit data can certify an upper tail quantile for a policy selected from the same sample. We construct a PAC-Bayes Bernstein lower-confidence envelope for the target cumulative distribution function (CDF), simultaneous over a predeclared threshold grid and all data-dependent posteriors....
A geometric framework that quantifies ambiguity of the input-target relation through the average kernel size, computed with data-dependent, i.e. model-independent, feasible sets derived from worst-case input and target noise is introduced.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work proposes using coupled-noise match verification for diffusion blocks, following shared-Gumbel-noise coupling approaches, and introduces Speculating Positions Order Trajectory (SPOT), which learns to predict this order.
WebMix, a mixture hypernetwork that adapts web agents to unseen interfaces by composing previously trained low-rank adapters, matches or outperforms in-context learning and LoRA baselines, often matching the average success of specialists trained directly on those interfaces.
This paper introduces Kinematic Interpolants (KI), a novel framework that extends the seminal methodology of stochastic interpolants to infer nonlinear dynamics across multiple snapshots in phase space, i.e., observables with position and velocity measurements.
This work systematically evaluates 16 PI configurations across three multi-turn agentic benchmarks and three student models that vary in scale and reasoning mode and finds that PI effectiveness depends on its content, generation source, and the student model.
This work provides a critic whose generative component is a return-conditioned policy, which can share the actor's architecture, and shows gains over leading discriminative methods, including distributional RL methods.
This paper observes that when a safe model is recursively self-distilled on its own (safe) generations while receiving an additional non-harmful cue, it becomes increasingly misaligned across a diverse set of harmful queries; it is called Progressive Misalignment.
The proposed **Lean4AgenticRL** is the first framework that grounds multi-level process rewards in the unified Lean4 formalization schema for open-ended agentic RL, and provides multi-level rewards to support more effective agentic RL with the workflow-stage-normalized GRPO algorithm.
This work introduces Sparse Autoencoder Geometric Anchoring (SAGA), which converts a Sparse Autoencoder (SAE) trained at each task boundary into local, low-rank constraints on representation drift, and establishes its local relation to latent code matching, define its spectral truncation error, and derive a conditional...
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
A Blog post by Ai2 on Hugging Face
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.
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
