Dynamic Important Example Mining (DIEM) adaptively selects and weights training data throughout reinforcement fine-tuning, combining a gradient-alignment importance estimator that…
This paper augments the Aardvark Weather deterministic end-to-end AI forecasting model with probabilistic capability by adding learned, input-dependent noise at…
This paper presents a taxonomy for analyzing multilingual multimodal misinformation on social media, built from a large-scale seven-language Twitter/X dataset…
VLAct is a vision-language-action model using representation-centric continued pre-training on diverse robot data, applying VLM-prior preservation, multi-head action co-supervision, and…
Code-as-World represents physical environments as executable code, capturing object states, physical parameters, and dynamics in a compact, quantitatively grounded format.…
J-Zero is a self-improving language-model framework built from three co-evolving components — a Challenger that generates difficult tasks, a Solver…
Puro-2B presents an open-source pretraining recipe for affordable language-model training, demonstrating a 1.5B-parameter model trained from scratch on up to…
ABot-Recon is a streaming 3D reconstruction model that caches only the preceding 11 frames of features rather than maintaining extensive…
This paper introduces the Falcon family of fast-weight attention mechanisms for continual learning, compressing expanding context into fixed-size recurrent states…
Intention Distillation (INDI) trains vision-language-action models using a frozen teacher vision-language model to distill behavioral intent into the action decoder,…
LayerRecall is a memory-routing mechanism for video generation that selectively retrieves historical context and injects it into specific transformer layers…
Parallel Tube Decoding (PTD) is a generative approach to spatio-temporal video grounding that decomposes localization into a temporal block followed…
