DEV Community

Programming

The magic behind computers. 💻 🪄

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Video Normals from Diffusion: Detail & Consistency for Open-World Footage

Video Normals from Diffusion: Detail & Consistency for Open-World Footage

Comments
14 min read
TextArena: LLM Games Test Reasoning, Negotiation, & Deception Skills

TextArena: LLM Games Test Reasoning, Negotiation, & Deception Skills

Comments
6 min read
Self-Training Boosts Code Generation: RewardRanker Outperforms GPT-3.5 & Rivals GPT-4

Self-Training Boosts Code Generation: RewardRanker Outperforms GPT-3.5 & Rivals GPT-4

Comments
5 min read
ReRAM Revolution: Stochastic Computing Breakthrough for Edge Devices

ReRAM Revolution: Stochastic Computing Breakthrough for Edge Devices

Comments
10 min read
Rust Concurrency: Common Async Pitfalls Explained

Rust Concurrency: Common Async Pitfalls Explained

8
Comments
4 min read
MedHal: New Dataset Flags Medical AI Lies - Can AI Detect False Health Info?

MedHal: New Dataset Flags Medical AI Lies - Can AI Detect False Health Info?

Comments
7 min read
LLMs Can "Bleed" Knowledge: How New Data Warps AI Understanding

LLMs Can "Bleed" Knowledge: How New Data Warps AI Understanding

Comments
9 min read
SIFT-50M: New Data Supercharges Speech LLMs, Improves Understanding

SIFT-50M: New Data Supercharges Speech LLMs, Improves Understanding

Comments
6 min read
VL-Rethinker: RL Drives Self-Reflection in Vision-Language Models for Smarter Reasoning

VL-Rethinker: RL Drives Self-Reflection in Vision-Language Models for Smarter Reasoning

Comments
9 min read
Single Transformer Beats Modular Vision-Language Models in New Study

Single Transformer Beats Modular Vision-Language Models in New Study

Comments
10 min read
VisuoThink: Visual-Text AI Beats Reasoning Limits with Multimodal Tree Search

VisuoThink: Visual-Text AI Beats Reasoning Limits with Multimodal Tree Search

Comments
13 min read
AI Team Cracks LLM Reasoning: New Model + "CEO" Agent Beats Benchmarks

AI Team Cracks LLM Reasoning: New Model + "CEO" Agent Beats Benchmarks

Comments
7 min read
InternVL3: Unified Multimodal AI Training Outperforms Open-Source Rivals

InternVL3: Unified Multimodal AI Training Outperforms Open-Source Rivals

Comments
7 min read
AI Automates MOOSE Simulations: Introducing the MooseAgent Framework

AI Automates MOOSE Simulations: Introducing the MooseAgent Framework

Comments
8 min read
FUSION: Deep Vision-Language Integration Outperforms with Fewer Tokens

FUSION: Deep Vision-Language Integration Outperforms with Fewer Tokens

Comments
10 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.