English
Related papers

Related papers: Code World Models for Parameter Control in Evoluti…

200 papers

Current large language models (LLMs) primarily rely on linear sequence generation and massive parameter counts, yet they severely struggle with complex algorithmic reasoning. While recent reasoning architectures, such as the Hierarchical…

Artificial Intelligence · Computer Science 2026-03-25 Vasiliy A. Es'kin , Mikhail E. Smorkalov

Aligning large language models (LLMs) with human preferences through reinforcement learning (RLHF) can lead to reward hacking, where LLMs exploit failures in the reward model (RM) to achieve seemingly high rewards without meeting the…

Machine Learning · Computer Science 2024-01-23 Alexandre Ramé , Nino Vieillard , Léonard Hussenot , Robert Dadashi , Geoffrey Cideron , Olivier Bachem , Johan Ferret

In recent years, the size of pre-trained language models (PLMs) has grown by leaps and bounds. However, efficiency issues of these large-scale PLMs limit their utilization in real-world scenarios. We present a suite of cost-effective…

We consider the protein sequence engineering problem, which aims to find protein sequences with high fitness levels, starting from a given wild-type sequence. Directed evolution has been a dominating paradigm in this field which has an…

Machine Learning · Computer Science 2025-01-20 Yinkai Wang , Jiaxing He , Yuanqi Du , Xiaohui Chen , Jianan Canal Li , Li-Ping Liu , Xiaolin Xu , Soha Hassoun

This study reveals how frontier Large Language Models LLMs can "game the system" when faced with impossible situations, a critical security and alignment concern. Using a novel textual simulation approach, we presented three leading LLMs…

Artificial Intelligence · Computer Science 2025-05-14 Lars Malmqvist

Catching flying objects with a cushioning process is a skill commonly performed by humans, yet it remains a significant challenge for robots. In this paper, we present a framework that combines optimization and learning to achieve compliant…

Robotics · Computer Science 2025-09-19 Bingjie Chen , Keyu Fan , Qi Yang , Yi Cheng , Houde Liu , Kangkang Dong , Chongkun Xia , Liang Han , Bin Liang

High-Level Synthesis (HLS) design space exploration (DSE) seeks Pareto-optimal designs within expansive pragma configuration spaces. To accelerate HLS DSE, graph neural networks (GNNs) are commonly employed as surrogates for HLS tools to…

Hardware Architecture · Computer Science 2026-01-09 Lei Xu , Shanshan Wang , Chenglong Xiao

Alignment has quickly become a default ingredient in LLM development, with techniques such as reinforcement learning from human feedback making models act safely, follow instructions, and perform ever-better on complex tasks. While these…

Computation and Language · Computer Science 2025-09-16 Peter West , Christopher Potts

We introduce Lossless Context Management (LCM), a deterministic architecture for LLM memory that outperforms Claude Code on long-context tasks. When benchmarked using Opus 4.6, our LCM-augmented coding agent, Volt, achieves higher scores…

Artificial Intelligence · Computer Science 2026-05-07 Clint Ehrlich , Theodore Blackman

We consider minimizing a smooth function subject to a summation constraint over its variables. By exploiting a connection between the greedy 2-coordinate update for this problem and equality-constrained steepest descent in the 1-norm, we…

Optimization and Control · Mathematics 2023-07-04 Amrutha Varshini Ramesh , Aaron Mishkin , Mark Schmidt , Yihan Zhou , Jonathan Wilder Lavington , Jennifer She

Today's pursuit of a single Large Language Model (LMM) for all software engineering tasks is resource-intensive and overlooks the potential benefits of complementarity, where different models contribute unique strengths. However, the degree…

Software Engineering · Computer Science 2025-10-31 Fernando Vallecillos-Ruiz , Max Hort , Leon Moonen

In the Submodular Welfare Maximization (SWM) problem, the input consists of a set of $n$ items, each of which must be allocated to one of $m$ agents. Each agent $\ell$ has a valuation function $v_\ell$, where $v_\ell(S)$ denotes the welfare…

Data Structures and Algorithms · Computer Science 2017-12-18 Nitish Korula , Vahab Mirrokni , Morteza Zadimoghaddam

We show how combinatorial optimisation algorithms can be applied to the problem of identifying c-optimal experimental designs when there may be correlation between and within experimental units and evaluate the performance of relevant…

Computation · Statistics 2023-02-24 Samuel I Watson , Yi Pan

Reward models (RMs) are central to aligning large language models (LLMs) with human preferences, powering RLHF and advanced decoding strategies. While most prior work focuses on single-step generation, real-world applications increasingly…

Artificial Intelligence · Computer Science 2026-04-21 Xingyu Fan , Wei Shao , Jiacheng Liu , Linqi Song , Pheng Ann Heng

Large Language Models (LLMs) have shown superior capability to solve reasoning problems with programs. While being a promising direction, most of such frameworks are trained and evaluated in settings with a prior knowledge of task…

Computation and Language · Computer Science 2024-06-21 Yuan Yang , Siheng Xiong , Ali Payani , Ehsan Shareghi , Faramarz Fekri

The code written by developers usually suffers from efficiency problems and contain various performance bugs. These inefficiencies necessitate the research of automated refactoring methods for code optimization. Early research in code…

Software Engineering · Computer Science 2024-08-23 Shuzheng Gao , Cuiyun Gao , Wenchao Gu , Michael Lyu

Successful application of large language models (LLMs) to robotic planning and execution may pave the way to automate numerous real-world tasks. Promising recent research has been conducted showing that the knowledge contained in LLMs can…

Robotics · Computer Science 2024-07-23 Ateeq Sharfuddin , Travis Breaux

With the end of Moore's Law, optimizing code for performance has become paramount for meeting ever-increasing compute demands, particularly in hyperscale data centers where even small efficiency gains translate to significant resource and…

We introduce transductive program synthesis, a new formulation of the program synthesis task that explicitly leverages test inputs during synthesis. While prior approaches to program synthesis--whether based on natural language descriptions…

Artificial Intelligence · Computer Science 2025-10-22 Kang-il Lee , Jahyun Koo , Seunghyun Yoon , Minbeom Kim , Hyukhun Koh , Dongryeol Lee , Kyomin Jung

In the area of code generation research, the emphasis has transitioned from crafting individual functions to developing class-level method code that integrates contextual information. This shift has brought several benchmarks such as…

Software Engineering · Computer Science 2024-08-28 Zinan Wang