BitTokens represent numbers as single tokens via IEEE 754 binary format, allowing small language models to learn basic arithmetic algorithms nearly perfectly.
arXiv.org
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
verdicts
UNVERDICTED 8representative citing papers
Active-GRPO reaches 0.1773 average SRxSim on TOMG-Bench MOLOPT by adaptively switching between imitation and self-reinforcement while upgrading references, outperforming GRPO and RePO.
LLM-ACES is a closed-loop method that combines LLM-proposed operator priors with disagreement-driven adaptive data acquisition to discover governing ODEs, reporting lowest median NMSE and 46-52% symbolic accuracy on 122 systems.
LLM-AutoSciLab proposes an LLM-driven closed-loop system for hypothesis generation and adaptive experiment selection that reports higher accuracy and 2-5x better sample efficiency than baselines on new chemistry and gene-network discovery benchmarks.
MOSAIC generates executable scientific code without I/O test cases by combining student-teacher distillation with a consolidated context window to reduce hallucinations across subproblems.
MOSAIC is a training-free multi-agent LLM framework with rationale, coding, reflection, and debugging agents plus a consolidated context window that outperforms prior methods on scientific coding benchmarks.
AI model evaluations for biological capabilities should prioritize high-consequence risks like pandemics, informed by life sciences dual-use experience, and occur prior to deployment to enable biosafety measures.
Apertus, a 70B open multilingual foundation model, was pre-trained on the Alps supercomputer, with details on adapting HPC infrastructure into a resilient ML platform.
citing papers explorer
-
Efficient numeracy in language models through single-token number embeddings
BitTokens represent numbers as single tokens via IEEE 754 binary format, allowing small language models to learn basic arithmetic algorithms nearly perfectly.
-
Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization
Active-GRPO reaches 0.1773 average SRxSim on TOMG-Bench MOLOPT by adaptively switching between imitation and self-reinforcement while upgrading references, outperforming GRPO and RePO.
-
LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Search
LLM-ACES is a closed-loop method that combines LLM-proposed operator priors with disagreement-driven adaptive data acquisition to discover governing ODEs, reporting lowest median NMSE and 46-52% symbolic accuracy on 122 systems.
-
LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs
LLM-AutoSciLab proposes an LLM-driven closed-loop system for hypothesis generation and adaptive experiment selection that reports higher accuracy and 2-5x better sample efficiency than baselines on new chemistry and gene-network discovery benchmarks.
-
No Test Cases, No Problem: Distillation-Driven Code Generation for Scientific Workflows
MOSAIC generates executable scientific code without I/O test cases by combining student-teacher distillation with a consolidated context window to reduce hallucinations across subproblems.
-
MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding
MOSAIC is a training-free multi-agent LLM framework with rationale, coding, reflection, and debugging agents plus a consolidated context window that outperforms prior methods on scientific coding benchmarks.
-
Prioritizing High-Consequence Biological Capabilities in Evaluations of Artificial Intelligence Models
AI model evaluations for biological capabilities should prioritize high-consequence risks like pandemics, informed by life sciences dual-use experience, and occur prior to deployment to enable biosafety measures.
-
An Engineering Journey Training Large Language Models at Scale on Alps: The Apertus Experience
Apertus, a 70B open multilingual foundation model, was pre-trained on the Alps supercomputer, with details on adapting HPC infrastructure into a resilient ML platform.