All stories
AI News

The Daily Signal: 2026-06-23

Today's top AI stories — curated, deduplicated, and distilled.

AI NEWS The Daily Signal: 2026-06-23 STORIES 5 SOURCES 5 DATE 2026-06-23 #daily-digest #curated #AI #technology nizam.wiki

The Daily Signal: 2026-06-23

Here’s what actually happened in AI today. No fluff, no hype — just signal.

📰 Top Stories

1. CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation

Humanoid loco-manipulation is often simplified into a stop-and-go process: walking to an object, stopping to manipulate it, and then resuming locomotion. It also commonly relies on low degree-of-freedom (DoF) end effectors that behave like an open-close grasp primitive. We introduce CoorDex, a learning pipeline that converts high-dimensional body and dexterous hand control into coordinated latent

View source →

2. Semantic Browsing: Controllable Diversity for Image Generation

Modern text-to-image models excel in visual fidelity and prompt adherence. However, this strict adherence comes at the cost of diversity: generated samples tend to collapse into a single visual interpretation. Existing methods to improve diversity produce outputs driven by incidental variations rather than meaningful design choices. This motivates a new variant of the diversity task where structur

View source →

3. AIR: Adaptive Interleaved Reasoning with Code in MLLMs

Following the paradigm shift initiated by OpenAI o3, interleaved reasoning with code to enhance multimodal large language models (MLLMs) has become a pivotal research frontier. The existing literature focuses primarily on tool-use within vision-perception tasks. However, such approaches typically rely on predefined heuristics for visual manipulation and are inherently incapable of addressing numer

View source →

4. Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?

AdamW is the de facto optimizer for training large language models (LLMs), yet the theory behind it still lives mostly in finite-variance regimes. This is increasingly unsatisfying, as empirical evidence indicates that stochastic gradient noise in LLM pretraining is typically heavy-tailed. Recent work shows that sign-based optimizers such as Lion and Muon achieve sharp heavy-tailed rates, and that

View source →

5. Randomized YaRN Improves Length Generalization for Long-Context Reasoning

Large language models (LLMs) are typically pretrained on short sequences and then extended to work on longer sequences with additional training. However, such LLMs still struggle to further generalize to very long sequences. We propose Randomized YaRN, a training method that improves length generalization by combining YaRN-based positional extrapolation with randomized positional encoding and a le

View source →

📄 Papers of the Day

CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation

Authors: Sikai Li, Shuning Li, Zhenyu Wei
Published: 2026-06-22

Humanoid loco-manipulation is often simplified into a stop-and-go process: walking to an object, stopping to manipulate it, and then resuming locomotion. It also commonly relies on low degree-of-freedom (DoF) end effectors that behave like an open-close grasp primitive. We introduce CoorDex, a learning pipeline that converts high-dimensional body and dexterous hand control into coordinated latent

Read the full paper →

Semantic Browsing: Controllable Diversity for Image Generation

Authors: Sara Dorfman, Maya Vishnevsky, Omer Dahary
Published: 2026-06-22

Modern text-to-image models excel in visual fidelity and prompt adherence. However, this strict adherence comes at the cost of diversity: generated samples tend to collapse into a single visual interpretation. Existing methods to improve diversity produce outputs driven by incidental variations rather than meaningful design choices. This motivates a new variant of the diversity task where structur

Read the full paper →

AIR: Adaptive Interleaved Reasoning with Code in MLLMs

Authors: Cong Han, Xiaohan Lan, Haibo Qiu
Published: 2026-06-22

Following the paradigm shift initiated by OpenAI o3, interleaved reasoning with code to enhance multimodal large language models (MLLMs) has become a pivotal research frontier. The existing literature focuses primarily on tool-use within vision-perception tasks. However, such approaches typically rely on predefined heuristics for visual manipulation and are inherently incapable of addressing numer

Read the full paper →


Sources: 5 articles + 5 papers from 2 sources. This digest is auto-generated by Nizam.Wiki.