Neural intel Pod

The provided research explores optimizing communication and sensing for autonomous vehicles using millimeter wave technology and orthogonal frequency-division multiplexing. Facing dynamic environments and the impact of wireless conditions on mmWave, the authors propose an adaptive system. This system employs reinforcement learning, considering queue state and channel state information. The goal is to achieve reliable communication and accurate velocity estimation of surrounding objects. To improve performance, they introduce adaptive OFDM and a reward function that utilizes the age of updates. Simulation results using A2C and PPO algorithms demonstrate the superiority of their approach over existing designs.

Recent progress in video generation still struggles with issues like motion instability and prompt alignment. To address this, the study explores incorporating human preferences into advanced flow-based video generation models. The authors introduce a large, new dataset of human-annotated video preferences across visual quality, motion quality, and text alignment. They also develop a multi-dimensional reward model to quantify these preferences and propose three alignment algorithms for flow-based models, demonstrating that a modified Direct Preference Optimization method yields the most effective results in aligning video generation with human expectations.

This research paper introduces AnimeGamer, a novel method for creating infinite anime life simulation games. Unlike previous work limited to static images or finite gameplay, AnimeGamer uses a multimodal large language model to process user instructions and predict subsequent game states. These states include dynamic animation shots and updated character attributes, aiming for a more immersive and consistent gaming experience. The paper details the model's architecture, training process, and evaluation, demonstrating its superior performance in generating coherent and interactive anime game worlds compared to baseline methods.

The provided research introduces NoProp, a novel method for training neural networks that deviates from traditional backpropagation by eliminating both forward and backward passes. Instead, it draws inspiration from diffusion models, where each layer learns independently to denoise a noisy version of the target. This approach trains networks without hierarchical representation learning in the conventional sense, achieving competitive or superior accuracy and efficiency compared to existing backpropagation-free techniques on image classification tasks. The work explores discrete-time and continuous-time variations of NoProp, including connections to flow matching, and examines its performance and memory usage relative to backpropagation and other alternative optimization methods.

The provided paper introduces ACPBench Hard, a new benchmark designed to evaluate the reasoning capabilities of large language models for automated planning. This benchmark extends the original ACPBench by featuring open-ended, generative versions of planning-related questions across various tasks, mirroring the challenges faced by symbolic planners. The authors tested several large language and reasoning models, including state-of-the-art options, on ACPBench Hard and found that their performance was generally subpar, indicating a significant gap in their ability to reliably reason about planning. The research highlights the difficulty current models face with core planning reasoning tasks and suggests future directions for improving their performance.

From Amazon's blog

Dynamic 4D Modeling from Casual Video

The provided research paper introduces KDTalker, a novel method for generating realistic audio-driven talking portraits by combining implicit 3D keypoints with a spatiotemporal diffusion model. This framework addresses limitations in existing techniques by achieving high lip synchronization accuracy and diverse head poses while maintaining computational efficiency. KDTalker leverages unsupervised learning of adaptable facial keypoints and a custom attention mechanism to ensure temporally consistent and expressive animations from a single image and audio. Experimental results demonstrate KDTalker's superior performance compared to state-of-the-art methods in terms of visual quality, motion diversity, and synchronization. The paper also includes ablation studies that validate the contributions of different components of the proposed framework.

AI2 has announced OLMo 2, a new family of fully open 7B and 13B language models demonstrating performance on par with or exceeding similarly sized open models, even rivaling open-weight models like Llama 3.1. This release includes not only model weights but also data, code, and evaluation frameworks, emphasizing truly open science. Key advancements in OLMo 2 involve improved training stability, staged training techniques, state-of-the-art post-training recipes from Tülu 3, and a comprehensive evaluation system (OLMES). The Instruct versions of OLMo 2 also show strong competitiveness with leading open-weight instruct models, highlighting the effectiveness of their post-training methodology.

Stable 3D Shape Correspondence via Registration