Related papers: PYTHALAB-MERA: Validation-Grounded Memory, Retriev…

Code optimization is a challenging task requiring a substantial level of expertise from developers. Nonetheless, this level of human capacity is not sufficient considering the rapid evolution of new hardware architectures and software…

Effective training-time guidance is central to multi-agent reinforcement learning (MARL), yet remains difficult in sparse-reward settings where weak supervision limits coordination and policy improvement, and existing methods often require…

For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging than one-shot generation. We study PPO-trained agents using MiniGrid as core evaluation…

Assessing the veracity of online content has become increasingly critical. Large language models (LLMs) have recently enabled substantial progress in automated veracity assessment, including automated fact-checking and claim verification…

Optimizing CUDA code across multiple generations of GPU architectures is challenging, as achieving peak performance requires an extensive exploration of an increasingly complex, hardware-specific optimization space. Traditional compilers…

The main issue with most evaluation schemes today is their "static" nature: the same problems are reused repeatedly, allowing for memorization, format exploitation, and eventual saturation. To measure genuine AI progress, we need evaluation…

Autonomous highway driving demands a critical balance between proactive, efficiency-seeking behavior and robust safety guarantees. This paper proposes Language Action-guided Reinforcement Learning (LA-RL) with Safety Guarantees, a novel…

Evaluating Large Language Model (LLM) applications differs from traditional software testing because outputs are stochastic, high-dimensional, and sensitive to prompt and model changes. We present an evaluation-driven workflow - Define,…

Reinforcement Learning from Verifiable Rewards (RLVR) has improved language models in domains such as mathematics and code, where correctness can be checked automatically. However, many important tasks are only partially verifiable: prompts…

Frozen encoder--decoder language models are stateless: the latent representation is discarded after every forward pass, so no information persists across sessions. This paper presents a \textbf{proof-of-concept pilot study} showing that…

Instruction-based Large Language Models (LLMs) have proven effective in numerous few-shot or zero-shot Natural Language Processing (NLP) tasks. However, creating human-annotated instruction data is time-consuming, expensive, and often…

Modern Large Language Model (LLM)-based programming agents often rely on test execution feedback to refine their generated code. These tests are synthetically generated by LLMs. However, LLMs may produce invalid or hallucinated test cases,…

We present an algorithm for local, regularized, policy improvement in reinforcement learning (RL) that allows us to formulate model-based and model-free variants in a single framework. Our algorithm can be interpreted as a natural extension…

Large Language Models (LLMs) have demonstrated remarkable capability in machine translation on high-resource language pairs, yet their performance on low-resource translation still lags behind. Existing post-training methods rely heavily on…

Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulting in what we term vision-language-action (VLA) models.…

Sequential fine-tuning of pretrained language encoders often overwrites previously acquired capabilities, but the forgetting behavior of parameter-efficient updates remains under-characterized. We present a controlled empirical study of…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a promising framework for improving reasoning abilities in Large Language Models (LLMs). However, policy optimized with binary verification prone to overlook…

Vision-Language-Action (VLA) models exhibit strong generalization in robotic manipulation, yet reinforcement learning (RL) fine-tuning often degrades robustness under spatial distribution shifts. For flow-matching VLA policies, this…

Training and fine-tuning large language models (LLMs) come with challenges related to memory and computational requirements due to the increasing size of the model weights and the optimizer states. Various techniques have been developed to…

Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial efforts in creating and annotating data. In this work, we…