Skip to content
Tagged articles

reward models

2 articles · Page 1 of 1
Meituan Technology Team
Meituan Technology Team
Nov 16, 2026 · Artificial Intelligence

EMNLP 2026 Highlights: 12 Long Papers from Meituan on Streaming Voice, RL, Agents & More

Meituan's technical team shares 12 EMNLP 2026 long papers covering streaming voice interaction, reinforcement learning with self-verification, instruction-following evaluation, agent skill internalization, on-policy distillation, Text-to-SQL over unknown schemas, unified memory frameworks, personalized reasoning, tool-use data synthesis, neuron consistency estimation, fast-slow reward models, and fine-grained gated delta networks.

EMNLP 2026Text-to-SQLagent training
0 likes · 28 min read
EMNLP 2026 Highlights: 12 Long Papers from Meituan on Streaming Voice, RL, Agents & More
Machine Heart
Machine Heart
Jun 25, 2026 · Artificial Intelligence

Do AI-Generated Images Invert Aesthetic Preferences? ICML 2026 Spotlight

The ICML 2026 spotlight paper argues that universal aesthetic alignment in image‑generation models narrows artistic expression, presents six interrelated concerns, and demonstrates through extensive prompts and benchmark tests that reward models and aligned generators stubbornly favor homogenized, overly positive imagery while failing to honor anti‑aesthetic or negative‑emotion requests.

AI-generated artICML 2026Image Generation
0 likes · 13 min read
Do AI-Generated Images Invert Aesthetic Preferences? ICML 2026 Spotlight