Evaluating and Improving LLM Self-Modeling
arXiv:2608.30980v1 Announce Type: cross Abstract: We study self-modeling: an LLM's ability to answer questions about its own behavior. We focus on verifiable behavioral questions, such as whether a pr
Knowledge catalogue
arXiv:2608.30980v1 Announce Type: cross Abstract: We study self-modeling: an LLM's ability to answer questions about its own behavior. We focus on verifiable behavioral questions, such as whether a pr
arXiv:2608.30884v1 Announce Type: cross Abstract: While gender and racial biases in language models have been widely studied, anti-LGBTQ biases remain underexplored, particularly beyond English. Exist
arXiv:2608.28678v1 Announce Type: new Abstract: Scalable Vector Graphics (SVGs) power much of the modern visual ecosystem, yet state-of-the-art generative models focus almost entirely on rasterized im
arXiv:2608.29309v1 Announce Type: cross Abstract: This work provides an overview of the different strategies that can be used to evaluate the performance of AI models and agents based on large languag
arXiv:2608.29543v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have established conversational text-to-SQL as a practical interface between users and databases, ofte
arXiv:2608.28776v1 Announce Type: new Abstract: Multilingual sentence embeddings are increasingly used to estimate semantic similarity across languages, yet their sensitivity to fine-grained translati
arXiv:2510.26861v4 Announce Type: replace-cross Abstract: Multimodal retrieval systems are expected to operate in a semantic space, agnostic to the language or cultural origin of the query. In practic
arXiv:2608.29738v1 Announce Type: new Abstract: Large language models (LLMs) can generate apparently highly persuasive text, but does sounding persuasive mean arguing well? We introduce extsc{Persuasi
arXiv:2608.28716v1 Announce Type: cross Abstract: Deep learning segmentation models are often evaluated using geometric metrics such as Dice, HD95, and ASD, yet it remains unclear to what extent impro
arXiv:2608.28833v1 Announce Type: new Abstract: While Large language models (LLMs) incorporate user personalization signals to improve usability and helpfulness, they increasingly shift from providing
arXiv:2608.28714v1 Announce Type: cross Abstract: Objective: Deep learning accelerates brain MRI four- to tenfold, but models can erase lesions or synthesize false tissue - failures pixel-averaged met
arXiv:2608.29431v1 Announce Type: new Abstract: Localized Representation Steering (LRS) is widely used to correct reasoning pathologies in large language models. However, standard benchmark evaluation
arXiv:2608.29376v1 Announce Type: new Abstract: Code generation increasingly relies on large transformer models, whose capability advances with scale. Yet such a scale is costly, creating demand for s
arXiv:2608.29835v1 Announce Type: new Abstract: Large language models (LLMs) often produce fluent but weakly grounded conclusions when reasoning over non-interactive, long-form narratives. A central f
arXiv:2608.30439v1 Announce Type: cross Abstract: Inference with transformer-based large language models (LLMs) is often limited by the memory-bound KV cache and quadratic attention cost. State-space
arXiv:2608.29576v1 Announce Type: new Abstract: Online learning-based control is a promising approach to control uncertain systems, where unknown components are identified during operation to improve
arXiv:2608.31066v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning improves multi-step problem solving, but long reasoning traces inflate inference cost. Token-level CoT compression redu
arXiv:2608.29927v1 Announce Type: new Abstract: We address the problem of 3D body pose estimation of multiple interacting people from their egocentric views with centralized coordination. Each individ
arXiv:2608.29092v1 Announce Type: new Abstract: Large vision-language models (LVLMs) frequently generate content unsupported by visual inputs. Preliminary experiments show that visual evidence is prim
arXiv:2608.31014v1 Announce Type: new Abstract: Computational mental health screening using multimodal speech and text has shown great promise. However, existing models often assume all clinical speec
arXiv:2606.13120v2 Announce Type: replace Abstract: Search Agents -- large language models augmented with search tools -- have intensified the need for future-proof evaluation benchmarks. Existing ben
arXiv:2608.29387v1 Announce Type: new Abstract: Large language models can generate interactive web interfaces, but reliable generative UI requires maintaining an executable artifact as user requests e
arXiv:2608.29978v1 Announce Type: new Abstract: Large language models are increasingly required to generate responses that satisfy multiple competing objectives. Since optimal trade-offs depend on bot
arXiv:2608.30429v1 Announce Type: new Abstract: LLM-based agent systems increasingly adopt skill-based architectures to reduce repetitive reasoning costs and improve stable, efficient task execution.
arXiv:2608.30254v1 Announce Type: new Abstract: We resolve the threshold part of Question 4 of the COLT 2025 open problem 'Data Selection for Regression Tasks' of Hanneke, Moran, Shlimovich and Yehuda
arXiv:2310.02779v3 Announce Type: replace Abstract: Generative flow networks (GFlowNets) are sequential sampling models trained to match a given distribution. GFlowNets have been successfully applied
arXiv:2608.28591v1 Announce Type: new Abstract: Recent advancements in AI are helping scientists achieve breakthroughs in fields such as mathematics, medicine, and materials sciences. New evaluation d
arXiv:2608.28820v1 Announce Type: new Abstract: Computational pathology (CompPath) is transforming medicine by leveraging artificial intelligence (AI) algorithms to support diagnosis, prognosis, and t
arXiv:2608.29110v1 Announce Type: new Abstract: The United States has allocated approximately $65 billion through the Infrastructure Investment and Jobs Act for broadband expansion, yet evidence-based
arXiv:2608.29027v1 Announce Type: new Abstract: Shrimp disease classification has become an urgent issue due to its significant impact on the import-export output of producing countries, particularly
arXiv:2608.29401v1 Announce Type: cross Abstract: As several mathematical conjectures have recently been settled using large language models (LLMs), the mathematical community has formulated norms and
arXiv:2608.30869v1 Announce Type: cross Abstract: Let rgeq3 be fixed, and let mathbf{G}_n be the set of all simple graphs with vertex set [n]={1,ldots,n}. We consider an exponential random graph model
arXiv:2608.29348v1 Announce Type: new Abstract: Background: Patient details and acquisition metadata are important for clinical decisions, image quality control, and automated research pipelines, but
arXiv:2506.11635v2 Announce Type: replace-cross Abstract: Credit card fraud mitigation plays a significant role in modern society. While fraud detection systems are essential, they often struggle to k
arXiv:2608.31033v1 Announce Type: new Abstract: Lightstage facial capture produces production-quality digital humans, but it is resource and labor-intensive. Multi-camera setups, hours of computation,
arXiv:2608.29028v1 Announce Type: new Abstract: Multi-agent LLM systems often coordinate by compressing an upstream interaction into a handoff artifact that downstream agents treat as shared state. We
arXiv:2608.30690v1 Announce Type: new Abstract: Visual SLAM is commonly evaluated on clean trajectories, although deployment failures are often caused by adverse weather, illumination, blur, and senso
arXiv:2608.30223v1 Announce Type: cross Abstract: We propose a new design of fair classifiers for multi-class classification problems in the presence of vector-valued sensitive attributes. In that sce
arXiv:2608.28777v1 Announce Type: new Abstract: Although recent deepfake detectors achieve high overall accuracy, their errors remain unevenly distributed across demographic subgroups, with real faces
arXiv:2608.30996v1 Announce Type: new Abstract: Retrieval-augmented generation systems can precompute and store key-value caches of retrieved documents to avoid re-encoding context at every query. Qua
arXiv:2608.30192v1 Announce Type: new Abstract: Traditional finance relies on experts to hand-craft factors through a principled process grounded in economic rationale. Recent LLM-based multi-agent sy
arXiv:2608.29167v1 Announce Type: new Abstract: Robustness of segmentation models is commonly assessed through input-domain perturbations, while dependence on frequency content within learned feature
arXiv:2506.15626v3 Announce Type: replace-cross Abstract: extbf{Objective:} Brain-predicted age difference (BrainAGE) is a neuroimaging biomarker reflecting brain health. However, training robust Brai
arXiv:2608.30458v1 Announce Type: new Abstract: Accurate bladder tumor segmentation and assessment of mus- cle invasion from T2-weighted MRI are important for treatment plan- ning, but developing robu
arXiv:2601.10015v2 Announce Type: replace Abstract: Personalized Federated Learning (PFL) excels at tailoring client-specific models, which is particularly critical for decentralized and heterogeneous
arXiv:2608.29391v1 Announce Type: cross Abstract: Floating things invite touch. We present Feelium, a blimp-based telepresence platform that enables visual embodiment and touch interaction through its
arXiv:2608.28814v1 Announce Type: cross Abstract: Converting scientific figures into executable code has gained increasing attention, yet existing methods primarily focus on reproducing the reference
arXiv:2608.29384v1 Announce Type: new Abstract: The growing availability of dense commercial Synthetic Aperture Radar (SAR) time series enables temporal Interferometric SAR (InSAR) analysis, but fixed
arXiv:2608.30653v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in multi-image scenarios requiring complex reasoning across visual contexts. Howeve
arXiv:2608.30908v1 Announce Type: new Abstract: Fine-tuning Low-bit models aims to adapt a quantized model while keeping the final deployed checkpoint in the same low-bit form. This setting is practic
arXiv:2608.29980v1 Announce Type: new Abstract: Unsupervised action segmentation is a challenging task. It involves finding action categories and boundaries in videos without labels. Existing Optimal
arXiv:2608.29336v1 Announce Type: new Abstract: FISICA is a body-assessment and recommendation service running in production. One standing session with two photographs returns foot-loading measures, p
arXiv:2608.28687v1 Announce Type: new Abstract: Generative models have significantly improved the performance ceiling of image lossy compression at low bitrates by exploiting learned priors. However,
arXiv:2608.29029v1 Announce Type: cross Abstract: Joint-Embedding Predictive Architectures (JEPAs) have shown strong potential for learning compact predictive representations, and LeWorldModel (LeWM)
arXiv:2608.30450v1 Announce Type: new Abstract: Video virtual try-on aims to transfer a target garment onto a moving person across video frames. Current methods rely on human parsing masks or pose key
arXiv:2510.03204v2 Announce Type: replace Abstract: Web agents powered by large language models (LLMs) must process lengthy web page observations to complete user goals; these pages often exceed tens
arXiv:2608.29372v1 Announce Type: new Abstract: Retrospective backtests provide a limited test of adaptive trading agents: they cannot rule out historical contamination, expose sensitivity to a single
arXiv:2608.30046v1 Announce Type: cross Abstract: Noisy labels remain a critical challenge for training deep neural networks, since memorizing incorrect labels degrades generalization. Once noisy samp
arXiv:2608.29311v1 Announce Type: new Abstract: Classic Formal Concept Analysis (FCA) primarily focuses on the positive relationships between objects and attributes and does not have mechanisms for ha
arXiv:2608.29615v1 Announce Type: cross Abstract: Across industries, machine-learning systems support applications ranging from prediction and anomaly detection to forecasting, optimization, and sched