Large language model (LLM) unlearning has become a critical topic in machine learning, aiming to eliminate the influence of specific training data or knowledge without retraining the model from scratch. A variety of techniques have been proposed, including Gradient Ascent, model editing, and re-steering hidden representations. While existing surveys often organize these methods by their technical characteristics, such classifications tend to overlook a more fundamental dimension: the underlying intention of unlearning--whether it seeks to truly remove internal knowledge or merely suppress its behavioral effects. In this SoK paper, we propose a new taxonomy based on this intention-oriented perspective. Building on this taxonomy, we make three key contributions. First, we revisit recent findings suggesting that many removal methods may functionally behave like suppression, and explore whether true removal is necessary or achievable. Second, we survey existing evaluation strategies, identify limitations in current metrics and benchmarks, and suggest directions for developing more reliable and intention-aligned evaluations. Third, we highlight practical challenges--such as scalability and support for sequential unlearning--that currently hinder the broader deployment of unlearning methods. In summary, this work offers a comprehensive framework for understanding and advancing unlearning in generative AI, aiming to support future research and guide policy decisions around data removal and privacy.

Integrating Low-Rank Adaptation (LoRA) into federated learning offers a promising solution for parameter-efficient fine-tuning of Large Language Models (LLMs) without sharing local data. However, several methods designed for federated LoRA present significant challenges in balancing communication efficiency, model accuracy, and computational cost, particularly among heterogeneous clients. These methods either rely on simplistic averaging of local adapters, which introduces aggregation noise, require transmitting large stacked local adapters, leading to poor communication efficiency, or necessitate reconstructing memory-dense global weight-update matrix and performing computationally expensive decomposition to design client-specific low-rank adapters. In this work, we propose FLoRIST, a federated fine-tuning framework that achieves mathematically accurate aggregation without incurring high communication or computational overhead. Instead of constructing the full global weight-update matrix at the server, FLoRIST employs an efficient decomposition pipeline by performing singular value decomposition on stacked local adapters separately. This approach operates within a compact intermediate space to represent the accumulated information from local LoRAs. We introduce tunable singular value thresholding for server-side optimal rank selection to construct a pair of global low-rank adapters shared by all clients. Extensive empirical evaluations across multiple datasets and LLMs demonstrate that FLoRIST consistently strikes the best balance between superior communication efficiency and competitive performance in both homogeneous and heterogeneous setups.

Large Language Models (LLMs) are increasingly capable but often require significant guidance or extensive interaction history to perform effectively in complex, interactive environments. Existing methods may struggle with adapting to new information or efficiently utilizing past experiences for multi-step reasoning without fine-tuning. We introduce a novel LLM agent framework that enhances planning capabilities through in-context learning, facilitated by atomic fact augmentation and a recursive lookahead search. Our agent learns to extract task-critical ``atomic facts'' from its interaction trajectories. These facts dynamically augment the prompts provided to LLM-based components responsible for action proposal, latent world model simulation, and state-value estimation. Planning is performed via a depth-limited lookahead search, where the LLM simulates potential trajectories and evaluates their outcomes, guided by the accumulated facts and interaction history. This approach allows the agent to improve its understanding and decision-making online, leveraging its experience to refine its behavior without weight updates. We provide a theoretical motivation linking performance to the quality of fact-based abstraction and LLM simulation accuracy. Empirically, our agent demonstrates improved performance and adaptability on challenging interactive tasks, achieving more optimal behavior as it accumulates experience, showcased in tasks such as TextFrozenLake and ALFWorld.

We present SensorLM, a family of sensor-language foundation models that enable wearable sensor data understanding with natural language. Despite its pervasive nature, aligning and interpreting sensor data with language remains challenging due to the lack of paired, richly annotated sensor-text descriptions in uncurated, real-world wearable data. We introduce a hierarchical caption generation pipeline designed to capture statistical, structural, and semantic information from sensor data. This approach enabled the curation of the largest sensor-language dataset to date, comprising over 59.7 million hours of data from more than 103,000 people. Furthermore, SensorLM extends prominent multimodal pretraining architectures (e.g., CLIP, CoCa) and recovers them as specific variants within a generic architecture. Extensive experiments on real-world tasks in human activity analysis and healthcare verify the superior performance of SensorLM over state-of-the-art in zero-shot recognition, few-shot learning, and cross-modal retrieval. SensorLM also demonstrates intriguing capabilities including scaling behaviors, label efficiency, sensor captioning, and zero-shot generalization to unseen tasks.

The widespread adoption of generative AI models has raised growing concerns about representational harm and potential discriminatory outcomes. Yet, despite growing literature on this topic, the mechanisms by which bias emerges - especially in unconditional generation - remain disentangled. We define the bias of an attribute as the difference between the probability of its presence in the observed distribution and its expected proportion in an ideal reference distribution. In our analysis, we train a set of unconditional image generative models and adopt a commonly used bias evaluation framework to study bias shift between training and generated distributions. Our experiments reveal that the detected attribute shifts are small. We find that the attribute shifts are sensitive to the attribute classifier used to label generated images in the evaluation framework, particularly when its decision boundaries fall in high-density regions. Our empirical analysis indicates that this classifier sensitivity is often observed in attributes values that lie on a spectrum, as opposed to exhibiting a binary nature. This highlights the need for more representative labeling practices, understanding the shortcomings through greater scrutiny of evaluation frameworks, and recognizing the socially complex nature of attributes when evaluating bias.

Large Language Models (LLMs) have demonstrated strong capabilities in general-purpose code generation. However, generating the code which is deeply hardware-specific, architecture-aware, and performance-critical, especially for massively parallel GPUs, remains a complex challenge. In this work, we explore the use of LLMs for the automated generation and optimization of CUDA programs, with the goal of producing high-performance GPU kernels that fully exploit the underlying hardware. To address this challenge, we propose a novel framework called \textbf{Feature Search and Reinforcement (FSR)}. FSR jointly optimizes compilation and functional correctness, as well as the runtime performance, which are validated through extensive and diverse test cases, and measured by actual kernel execution latency on the target GPU, respectively. This approach enables LLMs not only to generate syntactically and semantically correct CUDA code but also to iteratively refine it for efficiency, tailored to the characteristics of the GPU architecture. We evaluate FSR on representative CUDA kernels, covering AI workloads and computational intensive algorithms. Our results show that LLMs augmented with FSR consistently guarantee correctness rates. Meanwhile, the automatically generated kernels can outperform general human-written code by a factor of up to 179$\times$ in execution speeds. These findings highlight the potential of combining LLMs with performance reinforcement to automate GPU programming for hardware-specific, architecture-sensitive, and performance-critical applications.

Antibody-facilitated immune responses are central to the body's defense against pathogens, viruses, and other foreign invaders. The ability of antibodies to specifically bind and neutralize antigens is vital for maintaining immunity. Over the past few decades, bioengineering advancements have significantly accelerated therapeutic antibody development. These antibody-derived drugs have shown remarkable efficacy, particularly in treating cancer, SARS-CoV-2, autoimmune disorders, and infectious diseases. Traditionally, experimental methods for affinity measurement have been time-consuming and expensive. With the advent of artificial intelligence, in silico medicine has been revolutionized; recent developments in machine learning, particularly the use of large language models (LLMs) for representing antibodies, have opened up new avenues for AI-based design and improved affinity prediction. Herein, we present an advanced antibody-antigen binding affinity prediction model (LlamaAffinity), leveraging an open-source Llama 3 backbone and antibody sequence data sourced from the Observed Antibody Space (OAS) database. The proposed approach shows significant improvement over existing state-of-the-art (SOTA) methods (AntiFormer, AntiBERTa, AntiBERTy) across multiple evaluation metrics. Specifically, the model achieved an accuracy of 0.9640, an F1-score of 0.9643, a precision of 0.9702, a recall of 0.9586, and an AUC-ROC of 0.9936. Moreover, this strategy unveiled higher computational efficiency, with a five-fold average cumulative training time of only 0.46 hours, significantly lower than in previous studies.

We introduce **SWE-Flow**, a novel data synthesis framework grounded in Test-Driven Development (TDD). Unlike existing software engineering data that rely on human-submitted issues, **SWE-Flow** automatically infers incremental development steps directly from unit tests, which inherently encapsulate high-level requirements. The core of **SWE-Flow** is the construction of a Runtime Dependency Graph (RDG), which precisely captures function interactions, enabling the generation of a structured, step-by-step *development schedule*. At each step, **SWE-Flow** produces a partial codebase, the corresponding unit tests, and the necessary code modifications, resulting in fully verifiable TDD tasks. With this approach, we generated 16,061 training instances and 2,020 test instances from real-world GitHub projects, creating the **SWE-Flow-Eval** benchmark. Our experiments show that fine-tuning open model on this dataset significantly improves performance in TDD-based coding. To facilitate further research, we release all code, datasets, models, and Docker images at [Github](https://github.com/Hambaobao/SWE-Flow).

Communication among humans relies on conversational grounding, allowing interlocutors to reach mutual understanding even when they do not have perfect knowledge and must resolve discrepancies in each other's beliefs. This paper investigates how large language models (LLMs) manage common ground in cases where they (don't) possess knowledge, focusing on facts in the political domain where the risk of misinformation and grounding failure is high. We examine the ability of LLMs to answer direct knowledge questions and loaded questions that presuppose misinformation. We evaluate whether loaded questions lead LLMs to engage in active grounding and correct false user beliefs, in connection to their level of knowledge and their political bias. Our findings highlight significant challenges in LLMs' ability to engage in grounding and reject false user beliefs, raising concerns about their role in mitigating misinformation in political discourse.

Scientific fact-checking has mostly focused on text and tables, overlooking scientific charts, which are key for presenting quantitative evidence and statistical reasoning. We introduce ClimateViz, the first large-scale benchmark for scientific fact-checking using expert-curated scientific charts. ClimateViz contains 49,862 claims linked to 2,896 visualizations, each labeled as support, refute, or not enough information. To improve interpretability, each example includes structured knowledge graph explanations covering trends, comparisons, and causal relations. We evaluate state-of-the-art multimodal language models, including both proprietary and open-source systems, in zero-shot and few-shot settings. Results show that current models struggle with chart-based reasoning: even the best systems, such as Gemini 2.5 and InternVL 2.5, reach only 76.2 to 77.8 percent accuracy in label-only settings, far below human performance (89.3 and 92.7 percent). Explanation-augmented outputs improve performance in some models. We released our dataset and code alongside the paper.