More
PulseAugur coverage of More — every cluster mentioning More across labs, papers, and developer communities, ranked by signal.
- 2026-06-08 research_milestone A new adaptive multi-objective reinforcement learning framework called MORE was introduced for e-commerce dialogue systems. source
- 2026-06-08 research_milestone A new adaptive multi-objective reinforcement learning framework called MORE was detailed in a research paper, showing significant improvements in e-commerce dialogue systems. source
3 day(s) with sentiment data
-
Mixture of Reused Experts (MoRE) architecture unveiled
Researchers have introduced Mixture of Reused Experts (MoRE), a novel hybrid architecture for AI models. This approach allows expert pools to be shared across adjacent layers within the model. While each layer maintains…
-
New AI training framework MORE optimizes reasoning and efficiency
Researchers have introduced MORE, a novel self-evolving training framework designed to optimize reasoning in AI agents. This framework adaptively selects both the type of reasoning (direct answering, chain-of-thought, o…
-
Metis-1.6 models achieve Pareto-optimal efficiency with novel architectures
A single researcher has developed Metis-1.6, a new suite of language models, Praxis and Logos, that prioritize efficient training methods and novel architectures over sheer parameter count. Despite not competing with fr…
-
MoRE method enables articulated 3D object generation from single images
Researchers have introduced MoRE, a novel method for generating articulated 3D objects from single images. This approach encodes joint attributes using axis classification and Plücker moment coefficients, allowing for t…
-
New MoRE framework enhances language-based trajectory prediction models
Researchers have developed MoRE, a novel framework designed to enhance language-based trajectory prediction models. MoRE integrates numerical forecasting priors into existing language models using reinforcement learning…
-
New MORE architecture integrates multi-task learning into ranking model backbones
Researchers have developed MORE (Multi-task cO-evolving Ranking modEl), a novel architecture that integrates multi-task learning directly within the ranking model's backbone. Unlike previous methods that applied multi-t…
-
New UG-UMRE framework enhances multimodal relation extraction
Researchers have developed a new framework called UG-UMRE to improve unified multimodal relation extraction (UMRE). This approach addresses issues of noise propagation from inherent uncertainty and the heterogeneity bet…
-
New MoRe method accelerates multi-objective learning convergence
Researchers have developed a new stochastic multi-objective learning method called MoRe, which improves convergence rates for optimizing multiple objectives simultaneously. The method addresses limitations in existing s…
-
New benchmark MORE evaluates multilingual document parsing across 149 languages
Researchers have introduced MORE, a new benchmark designed to evaluate multilingual document parsing capabilities across 149 languages. This benchmark addresses the current lack of evaluation for models on languages bey…
-
New AI framework MORE boosts e-commerce dialogue conversion
Researchers have developed a new adaptive multi-objective reinforcement learning framework called MORE, designed to optimize both reasoning accuracy and linguistic naturalness in e-commerce dialogue systems. This approa…
-
New methods learn domain-invariant representations for continual learning
Researchers have developed new methods for continual learning that focus on learning domain-invariant representations. This approach aims to prevent models from overfitting to specific domain cues, thereby improving gen…