How a simple prompting trick called Verbalized Sampling overcomes the "Typicality Bias" that makes LLMs predictable.
The Root Cause: Research identifies "Typicality Bias"—a cognitive psychological tendency...
Introducing a new era of open-source multimodal models featuring native tool use, massive context windows, and real-world agentic capabilities.
A Dual-Model Release: The GLM-4.6V series launches...
Bridging the gap between precision and flexibility with a novel "Chain-of-Frames" approach.
The Precision Paradox: Current video editing AI faces a critical trade-off between expert models...
Moving beyond handcrafted graphics to real-time, text-guided world building.
Bridging the AR Gap: EgoEdit addresses the unique challenges of first-person (egocentric) footage—such as rapid motion and...
Bytedance’s new model redefines video creation with unprecedented spatio-temporal precision.
Beyond Simple Editing: Vidi2 can ingest hours of raw footage and a simple prompt to autonomously...
Revolutionizing video generation by solving the "first-frame" problem and harmonizing motion with identity.
Paradigm Shift: SteadyDancer moves away from the flawed Reference-to-Video (R2V) model to an...
Bridging Words and Visions to Create Smarter, More Adaptive Agents in a Complex World
Unified Prediction Framework: Dynalang redefines AI agents by using language not...
How AutoDeco Eliminates Manual Tweaks and Ushers in Truly End-to-End AI Creativity
Challenging the Status Quo: Current large language models (LLMs) aren't truly "end-to-end" due...
Unraveling the Hidden Dangers of Low-Quality Training Data in the Age of AI
The Brain Rot Hypothesis: Researchers propose and test a theory that exposing...
Unlocking Superior Image Quality and Alignment in Flow-Matching Models
Overcoming GRPO's Core Flaws: Traditional Group Relative Policy Optimization (GRPO) excels in flow-matching-based text-to-image (T2I) generation...
Unlocking Spatio-Temporal Intelligence for Smarter Video Understanding
Bridging the Evidence Gap: Open-o3 Video introduces explicit spatio-temporal grounding, highlighting timestamps, objects, and bounding boxes to make...
Exploring How Advanced AI Might Mirror Human Gambling Flaws in High-Stakes Financial Worlds
Cognitive Echoes of Addiction: Large language models (LLMs) replicate human gambling distortions...
