Trending Research
ReasonGraph: Visualisation of Reasoning Paths
Large Language Models (LLMs) reasoning processes are challenging to analyze due to their complexity and the lack of organized visualization tools.
TikZero: Zero-Shot Text-Guided Graphics Program Synthesis
Meanwhile, large amounts of unaligned graphics programs and captioned raster images are more readily available.
FinRobot: AI Agent for Equity Research and Valuation with Large Language Models
The system is structured around three specialized agents: the Data-CoT Agent, which aggregates diverse data sources for robust financial integration; the Concept-CoT Agent, which mimics an analysts reasoning to generate actionable insights; and the Thesis-CoT Agent, which synthesizes these insights into a coherent investment thesis and report.
Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control
nvidia-cosmos/cosmos-transfer1
•
•
We introduce Cosmos-Transfer, a conditional world generation model that can generate world simulations based on multiple spatial control inputs of various modalities such as segmentation, depth, and edge.
Falcon: A Remote Sensing Vision-Language Foundation Model
This paper introduces a holistic vision-language foundation model tailored for remote sensing, named Falcon.
Seeing the Future, Perceiving the Future: A Unified Driving World Model for Future Generation and Perception
Extensive experiments on the nuScenes dataset demonstrate that UniFuture outperforms specialized models on future generation and perception tasks, highlighting the advantages of a unified, structurally-aware world model.
Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey
By extending the advantage of chain-of-thought (CoT) reasoning in human-like step-by-step processes to multimodal contexts, multimodal CoT (MCoT) reasoning has recently garnered significant research attention, especially in the integration with multimodal large language models (MLLMs).
HybridFlow: A Flexible and Efficient RLHF Framework
volcengine/verl
•
•
Traditional RL can be modeled as a dataflow, where each node represents computation of a neural network (NN) and each edge denotes data dependencies between the NNs.
Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering
nvlabs/svraster
•
•
We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on adaptive sparse voxels without neural networks or 3D Gaussians.
Zep: A Temporal Knowledge Graph Architecture for Agent Memory
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark.
