Tootfinder

Reward Models Enable Scalable Code Verification by Trading Accuracy for Throughput
Gabriel Orlanski, Nicholas Roberts, Aws Albarghouthi, Frederic Sala
https://arxiv.org/abs/2506.10056

Reward Models Enable Scalable Code Verification by Trading Accuracy for Throughput
The standard paradigm for solving coding tasks via large language models (LLMs) is to generate-then-rank programs, where the latter step uses a verifier in the ranking process. The growing consensus is that a comprehensive verifier (e.g., a full test suite) should be prioritized over an outcome reward model (ORM) whenever possible, with little consideration given to the trade-offs involved. We aim to challenge this assumption by systematically exploring the tradeoff between speed and accuracy. …

Verification of the Release-Acquire Semantics
Parosh Abdulla, Elli Anastasiadi, Mohamed Faouzi Atig, Samuel Grahn
https://arxiv.org/abs/2506.08238 https://…

Verification of the Release-Acquire Semantics
The Release-Acquire (RA) semantics and its variants are some of the most fundamental models of concurrent semantics for architectures, programming languages, and distributed systems. Several steps have been taken in the direction of testing such semantics, where one is interested in whether a single program execution is consistent with a memory model. The more general verification problem, i.e., checking whether all allowed program runs are consistent with a memory model, has still not been stu…

Nominal Equational Rewriting and Narrowing
Mauricio Ayala-Rinc\'on (University of Bras\'ilia, Brazil), Maribel Fern\'andez (King's College London, UK), Daniele Nantes-Sobrinho (University of Bras\'ilia, Brazil,Imperial College London, UK), Daniella Santaguida (University of Bras\'ilia, Brazil)
https://arx…

Nominal Equational Rewriting and Narrowing
Narrowing is a well-known technique that adds to term rewriting mechanisms the required power to search for solutions to equational problems. Rewriting and narrowing are well-studied in first-order term languages, but several problems remain to be investigated when dealing with languages with binders using nominal techniques. Applications in programming languages and theorem proving require reasoning modulo alpha-equivalence considering structural congruences generated by equational axioms, suc…

MLorc: Momentum Low-rank Compression for Large Language Model Adaptation
Wei Shen, Yaxiang Zhang, Minhui Huang, Mengfan Xu, Jiawei Zhang, Cong Shen
https://arxiv.org/abs/2506.01897

MLorc: Momentum Low-rank Compression for Large Language Model Adaptation
With increasing size of large language models (LLMs), full-parameter fine-tuning imposes substantial memory demands. To alleviate this, we propose a novel memory-efficient training paradigm called Momentum Low-rank compression (MLorc). By directly compressing and reconstructing momentum rather than gradients, MLorc avoids imposing a fixed-rank constraint on weight update matrices and better preserves the training dynamics of full-parameter fine-tuning, in contrast to existing low-rank approache…

This https://arxiv.org/abs/2406.06095 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMS_…

An extension of C++ with memory-centric specifications for HPC to reduce memory footprints and streamline MPI development
The C++ programming language and its cousins lean towards a memory-inefficient storage of structs: The compiler inserts helper bits such that individual instance variables fit to byte or cache boundaries, while it is not able to exploit knowledge about the range of integers, enums or bitsets. Furthermore, the language provides neither support for data exchange via MPI nor for arbitrary floating-point precisions. We propose C++ attributes through which developers can guide the compiler what memo…

Movie Facts and Fibs (MF$^2$): A Benchmark for Long Movie Understanding
Emmanouil Zaranis, Ant\'onio Farinhas, Saul Santos, Beatriz Canaverde, Miguel Moura Ramos, Aditya K Surikuchi, Andr\'e Viveiros, Baohao Liao, Elena Bueno-Benito, Nithin Sivakumaran, Pavlo Vasylenko, Shoubin Yu, Sonal Sannigrahi, Wafaa Mohammed, Ben Peters, Danae S\'anchez Villegas, Elias Stengel-Eskin, Giuseppe Attanasio, Jaehong Yoon, Stella Frank, Alessandro Suglia, Chrysoula Zerva, Desmond Elliott, M…

Movie Facts and Fibs (MF$^2$): A Benchmark for Long Movie Understanding
Despite recent progress in vision-language models (VLMs), holistic understanding of long-form video content remains a significant challenge, partly due to limitations in current benchmarks. Many focus on peripheral, ``needle-in-a-haystack'' details, encouraging context-insensitive retrieval over deep comprehension. Others rely on large-scale, semi-automatically generated questions (often produced by language models themselves) that are easier for models to answer but fail to reflect genuine und…

VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code
Raghu Vamshi Hemadri, Jitendra Bhandari, Johann Knechtel, Badri P Gopalan, Ramesh Narayanaswamy, Ramesh Karri, Siddharth Garg
https://arxiv.org/abs/2506.07239

VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code
Modern chip design is complex, and there is a crucial need for early-stage prediction of key design-quality metrics like timing and routing congestion directly from Verilog code (a commonly used programming language for hardware design). It is especially important yet complex to predict individual lines of code that cause timing violations or downstream routing congestion. Prior works have tried approaches like converting Verilog into an intermediate graph representation and using LLM embedding…

Fairness Dynamics During Training
Krishna Patel, Nivedha Sivakumar, Barry-John Theobald, Luca Zappella, Nicholas Apostoloff
https://arxiv.org/abs/2506.01709

Fairness Dynamics During Training
We investigate fairness dynamics during Large Language Model (LLM) training to enable the diagnoses of biases and mitigations through training interventions like early stopping; we find that biases can emerge suddenly and do not always follow common performance metrics. We introduce two new metrics to evaluate fairness dynamics holistically during model pre-training: Average Rank and Jensen-Shannon Divergence by Parts. These metrics provide insights into the Pythia models' progression of biases…

A Large Language Model for Chemistry and Retrosynthesis Predictions
Yueqing Zhang, Wentao Liu, Yan Zhang, Danyang Xiong, Jihang Zhai, Hao Hao, YuCheng Gu, HaiBo Yang, Shuanhu Gao, Lianrui Hu, Aimin Zhou, Xiao He
https://arxiv.org/abs/2507.01444

A Large Language Model for Chemistry and Retrosynthesis Predictions
Large language models (LLM) have achieved impressive progress across a broad range of general-purpose tasks, but their effectiveness in chemistry remains limited due to scarce domain-specific datasets and the demand for precise symbolic and structural reasoning. Here we introduce ECNU-ChemGPT(name after East China Normal University), a chemistry-specialized LLM engineered for deep chemical knowledge understanding and accurate retrosynthetic route planning. Our approach is distinguished by four …

Memory-Efficient Split Federated Learning for LLM Fine-Tuning on Heterogeneous Mobile Devices
Xiaopei Chen, Liang Li, Fei Ji, Wen Wu
https://arxiv.org/abs/2506.02940

Memory-Efficient Split Federated Learning for LLM Fine-Tuning on Heterogeneous Mobile Devices
In this paper, we propose an edge-assisted split federated learning framework to facilitate large language model (LLM) fine-tuning on heterogeneous mobile devices while alleviating memory pressures on both mobile devices and the edge server. Specifically, mobile devices perform low-rank adaptation (LoRA) fine-tuning on only a subset of lower layers of the pre-trained LLM, tailored to their individual capacities. On the server, a full LLM is maintained, and the corresponding LoRA modules are sel…