Profil bibliographique

Akhiad Bercovich

Informations fournies par OpenAlex. Research Africa ne déduit ni nationalité, ni poste, ni coordonnées personnelles.

8Publications signalées
1Citations signalées
0Affiliations récentes

Les domaines associés

Multimodal Machine Learning ApplicationsTopic ModelingExplainable Artificial Intelligence (XAI)Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot Learning

Les publications récentes

Accès ouvert 2026 preprint OpenAlex

Extending Puzzle for Mixture-of-Experts Reasoning Models with Application to GPT-OSS Acceleration

Akhiad Bercovich, Nir Ailon, Vladimir Anisimov, Tomer Asida et autres

Reasoning-focused LLMs improve answer quality by generating longer reasoning traces, but the additional tokens dramatically increase serving cost, motivating inference optimization. We extend and apply Puzzle, a post-training neural architecture search (NAS) framework, to gpt-oss-120B to produce gpt-oss-puzzle-88B, a deployment-optimized derivative. Our …

0 citations arXiv (Cornell University)
Accès ouvert 2026 preprint OpenAlex

Extending Puzzle for Mixture-of-Experts Reasoning Models with Application to GPT-OSS Acceleration

Akhiad Bercovich, Nir Ailon, Vladimir Anisimov, Tomer Asida et autres

Reasoning-focused LLMs improve answer quality by generating longer reasoning traces, but the additional tokens dramatically increase serving cost, motivating inference optimization. We extend and apply Puzzle, a post-training neural architecture search (NAS) framework, to gpt-oss-120B to produce gpt-oss-puzzle-88B, a deployment-optimized derivative. Our …

0 citations arXiv (Cornell University)
Accès ouvert 2026 preprint OpenAlex

Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery

Meng Xin, Sweta Priyadarshi, Jingyu Xin, Bilal Kartal et autres

This technical report presents quantization-aware distillation (QAD) and our best practices for recovering accuracy of NVFP4-quantized large language models (LLMs) and vision-language models (VLMs). QAD distills a full-precision teacher model into a quantized student model using a KL divergence loss. While applying …

0 citations arXiv (Cornell University)
Accès ouvert 2026 preprint OpenAlex

Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery

Meng Xin, Sweta Priyadarshi, Jingyu Xin, Bilal Kartal et autres

This technical report presents quantization-aware distillation (QAD) and our best practices for recovering accuracy of NVFP4-quantized large language models (LLMs) and vision-language models (VLMs). QAD distills a full-precision teacher model into a quantized student model using a KL divergence loss. While applying …

0 citations arXiv (Cornell University)
Accès ouvert 2025 preprint OpenAlex

NVIDIA Nemotron 3: Efficient and Open Intelligence

NVIDIA, :, Aaron Blakeman, Aaron Grattafiori et autres

We introduce the Nemotron 3 family of models - Nano, Super, and Ultra. These models deliver strong agentic, reasoning, and conversational capabilities. The Nemotron 3 family uses a Mixture-of-Experts hybrid Mamba-Transformer architecture to provide best-in-class throughput and context lengths of up to …

1 citation arXiv (Cornell University)
Accès ouvert 2025 preprint OpenAlex

NVIDIA Nemotron 3: Efficient and Open Intelligence

NVIDIA, :, Aaron Blakeman, Aaron Grattafiori et autres

We introduce the Nemotron 3 family of models - Nano, Super, and Ultra. These models deliver strong agentic, reasoning, and conversational capabilities. The Nemotron 3 family uses a Mixture-of-Experts hybrid Mamba-Transformer architecture to provide best-in-class throughput and context lengths of up to …

0 citations arXiv (Cornell University)
Accès ouvert 2025 preprint OpenAlex

Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA, :, Aaron Blakeman, Aaron Grattafiori et autres

We present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer language model. Nemotron 3 Nano was pretrained on 25 trillion text tokens, including more than 3 trillion new unique tokens over Nemotron 2, followed by supervised fine tuning and large-scale RL on …

0 citations arXiv (Cornell University)
Accès ouvert 2025 preprint OpenAlex

Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA, :, Aaron Blakeman, Aaron Grattafiori et autres

We present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer language model. Nemotron 3 Nano was pretrained on 25 trillion text tokens, including more than 3 trillion new unique tokens over Nemotron 2, followed by supervised fine tuning and large-scale RL on …

0 citations arXiv (Cornell University)
Notice OpenAlex

BNTIC News n’est pas le producteur de ces données. Les publications sont interrogées à la demande dans Crossref, OpenAIRE, DOAJ, Europe PMC, HAL, DataCite, AfricArXiv, ROR et la Banque mondiale, sans clé d’accès. OpenAlex reste optionnel. Aucun service payant n’est nécessaire et aucune donnée externe n’est enregistrée en base. Consulter les sources et leurs limites.