Trending Research
Language Model Crossover: Variation through Few-Shot Prompting
The promise of such language model crossover (which is simple to implement and can leverage many different open-source language models) is that it enables a simple mechanism to evolve semantically-rich text representations (with few domain-specific tweaks), and naturally benefits from current progress in language models.
Moving Object Segmentation: All You Need Is SAM (and Flow)
The objective of this paper is motion segmentation -- discovering and segmenting the moving objects in a video.
Asynchronous Methods for Deep Reinforcement Learning
uvipen/Super-mario-bros-A3C-pytorch
•
•
We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers.
Ranked #9 on
Atari Games
on Atari 2600 Star Gunner
STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
Answering real-world user queries, such as product search, often requires accurate retrieval of information from semi-structured knowledge bases or databases that involve blend of unstructured (e. g., textual descriptions of products) and structured (e. g., entity relations of products) information.
GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting
A key insight is to encode the 3D Gaussian attributes into a shared implicit feature representation, where it is merged with audio features to manipulate each Gaussian attribute.
PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
magic-research/PLLaVA
•
•
arXiv 2024
PLLaVA achieves new state-of-the-art performance on modern benchmark datasets for both video question-answer and captioning tasks.
Ranked #1 on
Zero-Shot Video Question Answer
on TGIF-QA
Dense Captioning
Video-based Generative Performance Benchmarking (Consistency)
+6
PromptBench: A Unified Library for Evaluation of Large Language Models
The evaluation of large language models (LLMs) is crucial to assess their performance and mitigate potential security risks.
TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding
However, key-value (KV) cache, which is stored to avoid re-computation, has emerged as a critical bottleneck by growing linearly in size with the sequence length.
UFO: A UI-Focused Agent for Windows OS Interaction
We introduce UFO, an innovative UI-Focused agent to fulfill user requests tailored to applications on Windows OS, harnessing the capabilities of GPT-Vision.
Proximal Policy Optimization Algorithms
uvipen/super-mario-bros-ppo-pytorch
•
•
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.
