“Generative classifiers...can avoid this issue by modeling all features, both core and spurious, instead of mainly spurious ones.”

“HiGR delivers consistent improvements in both offline evaluations and online deployment. Specifically, it outperforms state-of-the-art methods by over 10% in offline recommendation quality with a 5x inference speedup, while further achieving a 1.22% and 1.73% increase in Average Watch Time and Average Video Views in online A/B tests.”

“RadAR significantly improves generation efficiency by integrating radial parallel prediction with dynamic output correction.”

“DyStream could generate video within 34 ms per frame, guaranteeing the entire system latency remains under 100 ms. Besides, it achieves state-of-the-art lip-sync quality, with offline and online LipSync Confidence scores of 8.13 and 7.61 on HDTF, respectively.”

“The paper introduces Embodied Reasoning Intelligence Quotient (ERIQ), a large-scale embodied reasoning benchmark in robotic manipulation, and FACT, a flow-matching-based action tokenizer.”

“The surrogate is orders of magnitude faster than SOLPS-ITER, enabling rapid parameter exploration.”

“The baseline model can compress a 20-second video into a context at about 5k length, where random frames can be retrieved with perceptually preserved appearances.”

“EntroDrop selectively masks low-entropy tokens during training and employs a curriculum schedule to adjust regularization strength in alignment with training progress.”

“Argus features a Length-Aware Semantics (LAS) module, which predicts output token lengths for incoming prompts...enabling precise estimation.”

“The skill of our distilled models scales with increasing synthetic training data, even when that data is orders of magnitude larger than ERA5. This represents the first demonstration that AI-generated synthetic training data can be used to scale long-range forecast skill.”

“EgoReAct achieves remarkably higher realism, spatial consistency, and generation efficiency compared with prior methods, while maintaining strict causality during generation.”

“WeDLM preserves the quality of strong AR backbones while delivering substantial speedups, approaching 3x on challenging reasoning benchmarks and up to 10x in low-entropy generation regimes; critically, our comparisons are against AR baselines served by vLLM under matched deployment settings, demonstrating that diffusion-style decoding can outperform an optimized AR engine in practice.”

“ARFM is able to predict complex motions, and we demonstrate that conditioning robot action prediction and human motion prediction on predicted future tracks can significantly improve downstream task performance.”

“The method achieves state-of-the-art performance in indoor benchmarks under constrained training conditions.”

“Dream-VLA achieves top-tier performance of 97.2% average success rate on LIBERO, 71.4% overall average on SimplerEnv-Bridge, and 60.5% overall average on SimplerEnv-Fractal, surpassing leading models such as $π_0$ and GR00T-N1.”

“TiDAR leverages the strengths of both diffusion and autoregressive models.”

“ManchuTTS attains a MOS of 4.52 using a 5.2-hour training subset...outperforming all baseline models by a notable margin.”

“The paper proposes a two-stage autoregressive adaptation and acceleration framework to adapt a high-fidelity human video diffusion model for real-time, interactive streaming.”

“The proposed methods yield improved coverage properties and computational efficiency relative to existing approaches.”

“DPAR reduces token count by 1.81x and 2.06x on Imagenet 256 and 384 generation resolution respectively, leading to a reduction of up to 40% FLOPs in training costs. Further, our method exhibits faster convergence and improves FID by up to 27.1% relative to baseline models.”

“ADT-Tree achieves speedups of 3.13x and 3.05x, respectively, on MS-COCO 2017 and PartiPrompts.”

“The model's free energy serves as a robust, regime stability metric.”

“Knot Forcing enables high-fidelity, temporally consistent, and interactive portrait animation over infinite sequences, achieving real-time performance with strong visual stability on consumer-grade GPUs.”

“Autoregressive video modeling encodes effective representations.”

“Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning.”

“The research focuses on the fast simulation of the Zero Degree Calorimeter.”

“The paper is available on ArXiv.”

“PHOTON is a hierarchical autoregressive model.”

“”

“”

“The research applies Variational Autoregressive Networks (VANs) to the simulation of φ⁴ field theory systems.”

“The research focuses on the extraction of climate-related information.”

“”

“”

“The paper is available on ArXiv.”

“”

“The article's context indicates a new approach to training video diffusion models.”

“The paper investigates the lookahead capabilities of next-token prediction.”

“Draft with Diffusion, Verify with Autoregressive Models”

“”

“ReFusion is a Diffusion Large Language Model with Parallel Autoregressive Decoding.”

“The research is sourced from ArXiv.”

“STAR: STacked AutoRegressive Scheme for Unified Multimodal Learning”

“The paper focuses on mitigating drift in autoregressive video diffusion models.”

“The paper is sourced from ArXiv.”

“”

“The paper likely discusses a cache-guided autoregressive diffusion model.”

“”

“”

“”