Podcast Episodes
Back to Search
Video Generation Improvement via Human Preference Alignment
Recent progress in video generation still struggles with issues like motion instability and prompt alignment. To address this, the study explores inc…
1Â year, 6Â months ago
AnimeGamer: Infinite Anime Life Simulation via MLLM
This research paper introduces AnimeGamer, a novel method for creating infinite anime life simulation games. Unlike previous work limited to static i…
1Â year, 6Â months ago
NoProp: Learning Neural Networks Without Backpropagation
The provided research introduces NoProp, a novel method for training neural networks that deviates from traditional backpropagation by eliminating bo…
1Â year, 6Â months ago
ACPBench Hard: Generative Planning Reasoning Tasks
The provided paper introduces ACPBench Hard, a new benchmark designed to evaluate the reasoning capabilities of large language models for automated p…
1Â year, 6Â months ago
Efficient Training of Large Language Models
From Amazon's blog
1Â year, 6Â months ago
Uni4D Dynamic 4D Modeling from Casual Video
Dynamic 4D Modeling from Casual Video
1Â year, 6Â months ago
KDTalker: Audio-Driven Talking Portraits via Implicit Keypoint Diffusion
The provided research paper introduces KDTalker, a novel method for generating realistic audio-driven talking portraits by combining implicit 3D keyp…
1Â year, 6Â months ago
OLMo 2: Fully Open Language Model Advancements
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 op…
1Â year, 6Â months ago
Stable-SCore Stable 3D Shape Correspondence via Registration
Stable 3D Shape Correspondence via Registration
1Â year, 6Â months ago
ProjectEval: Benchmarking Project-Level Code Generation by LLM Agents
The provided text introduces ProjectEval, a new benchmark for automatically evaluating the project-level code generation capabilities of programming …
1Â year, 6Â months ago