February 2026

TurboSparse-LLM Performance: Outperforming Mixtral and Gemma with Extreme Sparsity

⋅

Table of Links Abstract and 1. Introduction Related Work and Background Analysis 3.1 Limitations about Existing ReLUficatio 3.2 dReLU Are Neurons in Expert still Sparsely Activated? dReLU Sparsification Experiments Results 6.1 Downstream Tasks Performance 6.2 Sparsity of Sparsified Models Practical Inference Speedup Evaluation 7.1 Experiments Setting 7.2 Pure CPU Inference and 7.3 Hybrid GPU-CPU Inference 7.4 Deploy LLMs on mobile phones Conclusion and References A. Appendix / supplemental material B. Limitation C. Broader Impact 6 Experiments Results 6.1 […]

Ver mais

Liked Liked
The Air Force's new ICBM is nearly ready to fly, but there’s nowhere to put it

The Air Force’s new ICBM is nearly ready to fly, but there’s nowhere to put it

⋅

DENVER—The US Air Force’s new Sentinel intercontinental ballistic missile is on track for its first test flight next year, military officials reaffirmed this week. But no one is ready to say when hundreds of new missile silos, dug from the windswept Great Plains, will be finished, how much they cost, or, for that matter, how many nuclear warheads each Sentinel missile could actually carry. The LGM-35A Sentinel will replace the Air Force’s Minuteman III fleet, in service since […]

Ver mais

Liked Liked

dReLU Sparsification: Recovering LLM Performance with 150B Token Pretraining

⋅

Table of Links Abstract and 1. Introduction Related Work and Background Analysis 3.1 Limitations about Existing ReLUficatio 3.2 dReLU Are Neurons in Expert still Sparsely Activated? dReLU Sparsification Experiments Results 6.1 Downstream Tasks Performance 6.2 Sparsity of Sparsified Models Practical Inference Speedup Evaluation 7.1 Experiments Setting 7.2 Pure CPU Inference and 7.3 Hybrid GPU-CPU Inference 7.4 Deploy LLMs on mobile phones Conclusion and References A. Appendix / supplemental material B. Limitation C. Broader Impact 5 dReLU Sparsification In […]

Ver mais

Liked Liked

Sparse Activation in MoE Models: Extending ReLUfication to Mixture-of-Experts

⋅

Table of Links Abstract and 1. Introduction Related Work and Background Analysis 3.1 Limitations about Existing ReLUficatio 3.2 dReLU Are Neurons in Expert still Sparsely Activated? dReLU Sparsification Experiments Results 6.1 Downstream Tasks Performance 6.2 Sparsity of Sparsified Models Practical Inference Speedup Evaluation 7.1 Experiments Setting 7.2 Pure CPU Inference and 7.3 Hybrid GPU-CPU Inference 7.4 Deploy LLMs on mobile phones Conclusion and References A. Appendix / supplemental material B. Limitation C. Broader Impact 4 Are Neurons in […]

Ver mais

Liked Liked

Microsoft Research Introduces CORPGEN To Manage Multi Horizon Tasks For Autonomous AI Agents Using Hierarchical Planning and Memory

⋅

Microsoft researchers have introduced CORPGEN, an architecture-agnostic framework designed to manage the complexities of realistic organizational work through autonomous digital employees. While existing benchmarks evaluate AI agents on isolated, single tasks, real-world corporate environments require managing dozens of concurrent, interleaved tasks with complex dependencies. The research team identifies this distinct problem class as Multi-Horizon Task Environments (MHTEs). The Performance Gap in MHTEs Empirical testing reveals that baseline computer using agents (CUAs) experience significant performance degradation when moved from […]

Ver mais

Liked Liked

Microsoft Research Introduces CORPGEN To Manage Multi Horizon Tasks For Autonomous AI Agents Using Hierarchical Planning and Memory

⋅

Microsoft researchers have introduced CORPGEN, an architecture-agnostic framework designed to manage the complexities of realistic organizational work through autonomous digital employees. While existing benchmarks evaluate AI agents on isolated, single tasks, real-world corporate environments require managing dozens of concurrent, interleaved tasks with complex dependencies. The research team identifies this distinct problem class as Multi-Horizon Task Environments (MHTEs). The Performance Gap in MHTEs Empirical testing reveals that baseline computer using agents (CUAs) experience significant performance degradation when moved from […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2025