Existing parameter-efficient fine-tuning (PEFT) methods primarily fall into two categories: addition-based and selective in-situ adaptation. The former, such as LoRA, introduce additional modules to adapt the model to downstream tasks, offering strong memory efficiency. However, their representational capacity is often limited, making them less suitable for fine-grained adaptation. In contrast, the latter directly fine-tunes a carefully chosen subset of the original model parameters, allowing for more precise and effective adaptation, but at the cost of significantly increased memory consumption. To reconcile this trade-off, we propose NeuroAda, a novel PEFT method that enables fine-grained model finetuning while maintaining high memory efficiency. Our approach first identifies important parameters (i.e., connections within the network) as in selective adaptation, and then introduces bypass connections for these selected parameters. During finetuning, only the bypass connections are updated, leaving the original model parameters frozen. Empirical results on 23+ tasks spanning both natural language generation and understanding demonstrate that NeuroAda achieves state-of-the-art performance with as little as $\leq \textbf{0.02}\%$ trainable parameters, while reducing CUDA memory usage by up to 60%. We release our code here: https://github.com/FightingFighting/NeuroAda.git.

Long-horizon agentic search requires iteratively exploring the web over long trajectories and synthesizing information across many sources, and is the foundation for enabling powerful applications like deep research systems. In this work, we show that popular agentic search frameworks struggle to scale to long trajectories primarily due to context limitations-they accumulate long, noisy content, hit context window and tool budgets, or stop early. Then, we introduce SLIM (Simple Lightweight Information Management), a simple framework that separates retrieval into distinct search and browse tools, and periodically summarizes the trajectory, keeping context concise while enabling longer, more focused searches. On long-horizon tasks, SLIM achieves comparable performance at substantially lower cost and with far fewer tool calls than strong open-source baselines across multiple base models. Specifically, with o3 as the base model, SLIM achieves 56% on BrowseComp and 31% on HLE, outperforming all open-source frameworks by 8 and 4 absolute points, respectively, while incurring 4-6x fewer tool calls. Finally, we release an automated fine-grained trajectory analysis pipeline and error taxonomy for characterizing long-horizon agentic search frameworks; SLIM exhibits fewer hallucinations than prior systems. We hope our analysis framework and simple tool design inform future long-horizon agents.

Evaluating the creative capabilities of large language models (LLMs) in complex tasks often requires human assessments that are difficult to scale. We introduce a novel, scalable methodology for evaluating LLM story generation by analyzing underlying social structures in narratives as signed character networks. To demonstrate its effectiveness, we conduct a large-scale comparative analysis using networks from over 1,200 stories, generated by four leading LLMs (GPT-4o, GPT-4o mini, Gemini 1.5 Pro, and Gemini 1.5 Flash) and a human-written corpus. Our findings, based on network properties like density, clustering, and signed edge weights, show that LLM-generated stories consistently exhibit a strong bias toward tightly-knit, positive relationships, which aligns with findings from prior research using human assessment. Our proposed approach provides a valuable tool for evaluating limitations and tendencies in the creative storytelling of current and future LLMs.

Course syllabi set the tone and expectations for courses, shaping the learning experience for both students and instructors. In computing courses, especially those addressing fairness and ethics in artificial intelligence (AI), machine learning (ML), and algorithmic design it is imperative that we understand how approaches to navigating barriers to fair outcomes are being addressed.These expectations should be inclusive, transparent, and grounded in promoting critical thinking. Syllabus analysis offers a way to evaluate the coverage, depth, practices, and expectations within a course. Manual syllabus evaluation, however, is time-consuming and prone to inconsistency. To address this, we developed a justice-oriented scoring rubric and asked a large language model (LLM) to review syllabi through a multi-perspective role simulation. Using this rubric, we evaluated 24 syllabi from four perspectives: instructor, departmental chair, institutional reviewer, and external evaluator. We also prompted the LLM to identify thematic trends across the courses. Findings show that multi-perspective evaluation aids us in noting nuanced, role-specific priorities, leveraging them to fill hidden gaps in curricula design of AI/ML and related computing courses focused on fairness and ethics. These insights offer concrete directions for improving the design and delivery of fairness, ethics, and justice content in such courses.

Reinforcement learning (RL) has recently become the core paradigm for aligning and strengthening large language models (LLMs). Yet, applying RL in off-policy settings--where stale data from past policies are used for training--improves sample efficiency, but remains challenging: policy entropy declines sharply, optimization often becomes unstable and may even collapse. Through theoretical and empirical analysis, we identify two key insights: (i) an imbalance in optimization, where negative-advantage samples dominate the policy gradient, suppressing useful behaviors and risking gradient explosions; and (ii) the derived Entropy-Clip Rule, which reveals that the fixed clipping mechanism in PPO-like objectives systematically blocks entropy-increasing updates, thereby driving the policy toward over-exploitation at the expense of exploration. Building on these insights, we propose BAlanced Policy Optimization with Adaptive Clipping (BAPO), a simple yet effective method that dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization. Across diverse off-policy scenarios--including sample replay and partial rollout--BAPO achieves fast, stable, and data-efficient training. On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B, while our 32B BAPO model not only achieves state-of-the-art results among models of the same scale but also outperforms leading proprietary systems like o3-mini and Gemini-2.5-Flash-Thinking.

The recent widespread adoption of Large Language Models (LLMs) and machine learning in general has sparked research interest in exploring the possibilities of deploying these models on smaller devices such as laptops and mobile phones. This creates a need for frameworks and approaches that are capable of taking advantage of on-device hardware. The MLX framework was created to address this need. It is a framework optimized for machine learning (ML) computations on Apple silicon devices, facilitating easier research, experimentation, and prototyping. This paper presents a performance evaluation of MLX, focusing on inference latency of transformer models. We compare the performance of different transformer architecture implementations in MLX with their Pytorch counterparts. For this research we create a framework called MLX-transformers which includes different transformer implementations in MLX and downloads the model checkpoints in pytorch and converts it to the MLX format. By leveraging the advanced architecture and capabilities of Apple Silicon, MLX-Transformers enables seamless execution of transformer models directly sourced from Hugging Face, eliminating the need for checkpoint conversion often required when porting models between frameworks. Our study benchmarks different transformer models on two Apple Silicon macbook devices against an NVIDIA CUDA GPU. Specifically, we compare the inference latency performance of models with the same parameter sizes and checkpoints. We evaluate the performance of BERT, RoBERTa, and XLM-RoBERTa models, with the intention of extending future work to include models of different modalities, thus providing a more comprehensive assessment of MLX's capabilities. The results highlight MLX's potential in enabling efficient and more accessible on-device ML applications within Apple's ecosystem.

The COVID Fake News dataset is a collection of mostly COVID-19 pandemic-specific news headlines and brief claims. The data is representative of the combination of proven factual statements and much misleading or outright false information widespread on digital platforms during the pandemic. The data set was then preprocessed and split into training (8,160 samples) and testing (2,041 samples) categories in a balanced portion so that both real and fake labels could be checked robustly. The dataset used to check whether the pipeline can be applied to other domains rather than the pandemic area is the FakeNewsNet GossipCop. This dataset lies in the domain of entertainment and celebrity news and it is one of the prominent areas where gossip, rumors, fabricated stories are prevalent. Approximately 10,000 samples were used to train, and 2,500 samples were used to test. In the present dataset, the labels distinguish the news objects as Real or Fake by fact-checking them with regards to the original GossipCop platform. The two datasets were combined, standardized, and stratified to ensure the balanced classes in the samples during training and validation. Such prudent training has the benefit of enabling these models to improve in identifying subtle signs in language that may be contained in actual and made-up claims that can be used in enhancing the pipeline to perform better in practical misinformation detection applications.

Social media platforms such as Twitter (now X) provide rich data for analyzing public discourse, especially during crises such as the COVID-19 pandemic. However, the brevity, informality, and noise of social media short texts often hinder the effectiveness of traditional topic modeling, producing incoherent or redundant topics that are often difficult to interpret. To address these challenges, we have developed \emph{TM-Rephrase}, a model-agnostic framework that leverages large language models (LLMs) to rephrase raw tweets into more standardized and formal language prior to topic modeling. Using a dataset of 25,027 COVID-19-related Twitter posts, we investigate the effects of two rephrasing strategies, general- and colloquial-to-formal-rephrasing, on multiple topic modeling methods. Results demonstrate that \emph{TM-Rephrase} improves three metrics measuring topic modeling performance (i.e., topic coherence, topic uniqueness, and topic diversity) while reducing topic redundancy of most topic modeling algorithms, with the colloquial-to-formal strategy yielding the greatest performance gains and especially for the Latent Dirichlet Allocation (LDA) algorithm. This study contributes to a model-agnostic approach to enhancing topic modeling in public health related social media analysis, with broad implications for improved understanding of public discourse in health crisis as well as other important domains.

The prevalence of Large Language Models (LLMs) for generating multilingual text and source code has only increased the imperative for machine-generated content detectors to be accurate and efficient across domains. Current detectors, predominantly utilizing zero-shot methods, such as Fast DetectGPT or GPTZero, either incur high computational cost or lack sufficient accuracy, often with a trade-off between the two, leaving room for further improvement. To address these gaps, we propose the fine-tuning of encoder-only Small Language Models (SLMs), in particular, the pre-trained models of RoBERTA and CodeBERTa using specialized datasets on source code and other natural language to prove that for the task of binary classification, SLMs outperform LLMs by a huge margin whilst using a fraction of compute. Our encoders achieve AUROC $= 0.97$ to $0.99$ and macro-F1 $0.89$ to $0.94$ while reducing latency by $8$-$12\times$ and peak VRAM by $3$-$5\times$ at $512$-token inputs. Under cross-generator shifts and adversarial transformations (paraphrase, back-translation; code formatting/renaming), performance retains $\geq 92%$ of clean AUROC. We release training and evaluation scripts with seeds and configs; a reproducibility checklist is also included.

WORK Although the findings highlight the effectiveness of fine - tuned transformer models for Bengali - Sylheti translation, several limitations remain. The dataset size (5,002 parallel sentences) restricts the models' capacity to generalize across diverse syntactic structures, stylistic variations, and domain - specific expressions. In addition, orthographic inconsistencies in Sylheti introduce noise, leading to training instability, particularly in models like mBART - 50. Another limitation is the reliance on automatic evaluation metrics such as BLEU and chrF, which may not fully capture the linguistic richness or cultural nuance of Sylheti. Future research should therefore focus on expanding the datas et through community - driven contributions and data augmentation strategies. Incorporating orthographic normalization could improve consistency and reduce variability during training. Hybrid approaches that combine the strengths of pre - trained LLMs with fin e - tuned NMT models may also enhance translation robustness in low - resource settings. Finally, incorporating human evaluation will provide a more comprehensive assessment of translation adequacy, fluency, and cultural alignment.