NewsHive
CONTACT USANALYST PORTAL →
aiBACKGROUND

Self-Routing: Parameter-Free Expert Routing from Hidden States

BACKGROUND
9 SIGNALSFIRST DETECTED 2 April 2026
Narrative synthesis pending — 9 signals collected.
How the story developed
28 Sept
21 Sept
17 Sept
11 Sept
31 Aug
10 Aug
9 Jul
1 Jul
2 Apr
6.3
Other feeds and industry voices
14 Apr
SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding

arXiv:2604.10152v1 Announce Type: new Abstract: The Mixture-of-Experts (MoE) architecture has emerged as a promising approach to mitigate the rising computational costs of large

REPORT · HOW · ArXiv CS.AIOPEN STORY
13 May
GAR: Carbon-Aware Routing for LLM Inference via Constrained Optimization

arXiv:2605.11603v1 Announce Type: new Abstract: The growing deployment of large language models (LLMs) makes per-request routing essential for balancing response quality and

REPORT · HOW · ArXiv CS.AIOPEN STORY
27 Apr
Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation Models

arXiv:2604.21952v1 Announce Type: cross Abstract: This work presents a multi-layered methodology for efficiently accelerating multimodal foundation models (MFMs). It combines

REPORT · WHAT · ArXiv CS.AIOPEN STORY
20 May
Generative Recursive Reasoning

arXiv:2605.19376v1 Announce Type: new Abstract: How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising

REPORT · HOW · ArXiv CS.AIOPEN STORY
14 Apr
The Myth of Expert Specialization in MoEs: Why Routing Reflects Geometry, Not Necessarily Domain Expertise

arXiv:2604.09780v1 Announce Type: new Abstract: Mixture of Experts (MoEs) are now ubiquitous in large language models, yet the mechanisms behind their "expert specialization"

REPORT · WHAT · ArXiv CS.AIOPEN STORY
5 May
BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs

arXiv:2605.00422v1 Announce Type: cross Abstract: Large language models (LLMs) have driven major progress in NLP, yet their substantial memory and compute demands still hinder

REPORT · WHAT · ArXiv CS.AIOPEN STORY
20 Mar
SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding

arXiv:2603.18567v1 Announce Type: cross Abstract: Large language models incur high inference latency due to sequential autoregressive decoding. Speculative decoding alleviates

REPORT · HOW · ArXiv CS.AIOPEN STORY
13 May
Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers

arXiv:2605.11556v1 Announce Type: new Abstract: Solving complex long-horizon tasks requires strong planning and reasoning capabilities. Although datasets with explicit

REPORT · WHAT · ArXiv CS.AIOPEN STORY
Sources
ArXiv CS.AI×9

NewsHive monitors these sources continuously. All signal titles above link to the original reporting.

Intelligence by NewsHive. Need help navigating what this means for your business? Contact GeekyBee →