Trending Research
Smaller But Better: Unifying Layout Generation with Smaller Large Language Models
We propose LGGPT, an LLM-based model tailored for unified layout generation.
R-KV: Redundancy-aware KV Cache Compression for Training-Free Reasoning Models Acceleration
To address this, we propose Redundancy-aware KV Cache Compression for Reasoning models (R-KV), a novel method specifically targeting redundant tokens in reasoning models.
ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks
Our results show that agents powered by state-of-the-art models resolve only 13. 8% of SRE scenarios, 25. 2% of CISO scenarios, and 0% of FinOps scenarios.
ManimML: Communicating Machine Learning Architectures with Animation
A user can take a preexisting neural network architecture and easily write a specification for an animation in ManimML, which will then automatically compose animations for different components of the system into a final animation of the entire neural network.
TradingAgents: Multi-Agents LLM Financial Trading Framework
Significant progress has been made in automated problem-solving using societies of agents powered by large language models (LLMs).
Mirage: A Multi-Level Superoptimizer for Tensor Programs
We introduce Mirage, the first multi-level superoptimizer for tensor programs.
Continuous Thought Machines
SakanaAI/continuous-thought-machines
•
•
The CTM has two core innovations: (1) neuron-level temporal processing, where each neuron uses unique weight parameters to process a history of incoming signals; and (2) neural synchronization employed as a latent representation.
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting
Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables.
AlphaEvolve: A Learning Framework to Discover Novel Alphas in Quantitative Investment
In this paper, we introduce a new class of alphas to model scalar, vector, and matrix features which possess the strengths of these two existing classes.
Skill Expansion and Composition in Parameter Space
ltlhuuu/PSEC
•
•
In this paper, we propose Parametric Skill Expansion and Composition (PSEC), a new framework designed to iteratively evolve the agents' capabilities and efficiently address new challenges by maintaining a manageable skill library.
