arXiv subjects

Kristian Kersting

Publications and source records attributed to Kristian Kersting.

At least 37 records · Page 2Linked to original sources

arXiv2026

KletterMix: Climbing Toward High-Quality German Pretraining Data - The Full Report

High-quality pretraining data is a central ingredient in modern language models, but German-language resources remain far less developed than their English counterparts: they are often smaller, less carefully curated, weakly documented, and rarely validated through controlled training experiments. We introduce KletterMix, a high-quality German corpus for language model pretraining and annealing, designed as a reusable dataset artifact for the natural language processing and modeling community. KletterMix is built by translating a state-of-the-art English pretraining corpus into German while preserving document boundaries, metadata, source structure, and topical diversity. This construction yields a German corpus with the scale and diversity of a modern pretraining dataset, while enabling direct comparison to its English source. We document the dataset through a broad set of corpus-level analyses, including translation quality, document length distributions, topic coverage, source composition, and geographic metadata. Using COMETKiwi, we show that the translated documents achieve strong quality across diverse domains, suggesting that careful translation can preserve much of the semantic and stylistic richness of the original corpus. Beyond dataset construction, we evaluate KletterMix as training data. Through controlled pretraining and annealing ablations against established German corpora, we show that models trained on KletterMix achieve measurable improvements on German-language downstream evaluations. These results demonstrate that carefully curated translated data can substantially strengthen the German pretraining data ecosystem.

cs.CL↗

arXiv2026

A Sovereign, Open-Source Foundation Model for German and English

We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English. Its hybrid design activates only 3B of 30B parameters per token and keeps the inference cache near-constant as context grows, giving it a decisive throughput advantage over dense models for long-context, high-concurrency deployment. Pretrained on roughly 27 trillion tokens with deliberately up-weighted German, Soofi S matches dense 14 to 27B models on aggregate English and German benchmarks while achieving the best code aggregates in both languages among 17 open base models, and outperforms every European sovereign baseline in our comparison, including ones far larger in active parameters. Among fully open models, Soofi S obtains the highest English and German evaluation scores, ahead of Olmo 3 32B and Apertus 70B. Soofi S was built end-to-end on the German Industrial AI Cloud, a sovereign HPC scale AI infrastructure operated by Deutsche Telekom in Munich. Soofi S will be released under highly permissive, open-access terms: weights, selected intermediate checkpoints, full per-source data accounting, hyperparameters, and training and evaluation code. Where source licenses permit, data-construction artifacts are released under permissive licenses; commercially licensed sources are documented with aggregate statistics and exact mixture accounting.

cs.CL↗

arXiv2026

Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction

A central challenge in building intelligent systems is enabling agents to jointly perceive complex inputs, form hypotheses about hidden patterns, and design informative experiments to test them. To study this problem, we propose ZendoWorld, a controlled interactive environment in which agents must infer a logical rule about visual game observations, acquire information by proposing new scenes, and refine their hypotheses based on feedback from the game environment. We evaluate several agents spanning pure VLM reasoning, Bayesian particle filtering, dynamic concept discovery, and neuro-symbolic methods. Our main findings are: (1) high accuracy in predicting labels for observed examples does not imply recovery of the underlying rule; (2) perception and induction are distinct bottlenecks for different agent classes; and (3) VLM-based agents propose near-uninformative experiments, failing to actively reduce hypothesis uncertainty. To compare these results, we collect human data on the task, which reveals a gap in inductive reasoning, particularly for more complex rules. Overall, ZENDOWORLD takes an important step toward evaluating intelligent agents and identifies concrete avenues for improvement, particularly in domains like scientific discovery.

cs.AI↗

arXiv2026

CausalSteward: An Agentic Divide-Conquer-Combine Copilot for Causal Discovery

Learning causal models from high-dimensional data is a significant challenge, particularly in real-world settings where violations of core assumptions lead to causal identifiability issues. Although massive amounts of prior knowledge are available, and contain valuable causal information, effectively integrating this knowledge into the causal discovery process remains an open problem. We introduce CausalSTeward (CAST), a novel human-in-the-loop framework for interactively assembling large causal models. CausalSteward is a multi-agent collaborative system that tackles high-dimensional causality through a divide-and-conquer approach where large clusters of variables are iteratively partitioned and then separately analyzed. Our framework fuses prior knowledge with a data-driven approach by using tailored tools such as retrieval augmented generation and conditional independence tests. Finally, we use this work to examine the capabilities and limitations of causal reasoning in multi-agent frameworks, and how the human-in-the-loop can contribute to accurate and trustworthy results.

cs.MA↗

arXiv2026

Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining

Pretraining transformers on long sequences (entire code repositories, collections of related documents) is bottlenecked by quadratic attention costs. We present Multipole Semantic Attention (MuSe), which accelerates 64k-context pretraining by 36% while matching baseline loss, requiring no architectural changes. MuSe clusters queries and keys separately in representation space. This yields query-specific summaries that substantially outperform spatial blocking at matched sparsity, while also enabling drop-in compatibility with existing pretrained models; we validate on Llama 3.1-8B and 3.2-1B without retraining. We pretrain language models up to 1B parameters at 64k context on code and scientific documents, confirming that MuSe preserves quality and long-context utilization during training.

cs.LG↗

arXiv2026

Context-specific Credibility-aware Multimodal Fusion with Conditional Probabilistic Circuits

Multimodal fusion requires integrating information from multiple sources that may conflict depending on context. Existing fusion approaches typically rely on static assumptions about source reliability, limiting their ability to resolve conflicts when a modality becomes unreliable due to situational factors such as sensor degradation or class-specific corruption. We introduce C$^2$MF, a context-specfic credibility-aware multimodal fusion framework that models per-instance source reliability using a Conditional Probabilistic Circuit (CPC). We formalize instance-level reliability through Context-Specific Information Credibility (CSIC), a KL-divergence-based measure computed exactly from the CPC. CSIC generalizes conventional static credibility estimates as a special case, enabling principled and adaptive reliability assessment. To evaluate robustness under cross-modal conflicts, we propose the Conflict benchmark, in which class-specific corruptions deliberately induce discrepancies between different modalities. Experimental results show that C$^2$MF improves predictive accuracy by up to 29% over static-reliability baselines in high-noise settings, while preserving the interpretability advantages of probabilistic circuit-based fusion.

cs.LG↗

arXiv2026

COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives

While interpretable models such as concept bottleneck models (CBMs) and program synthesis methods enable verification of model decisions, their evaluation is typically limited to simple tasks, leaving complex reasoning on real-world images largely unexplored. We introduce COCOLogic-V2, an object-centric dataset for visual inductive reasoning on real-world images covering a broad subset of first-order logic. By categorizing samples into positive variants, near-boundary (NB), and far-from-boundary (FB) negatives, COCOLogic-V2 enables fine-grained diagnosis of model accountability. Our evaluations show that models tend to separate positive and FB samples well but fail on NB samples, while perceptual noise and large rule-induced search spaces pose additional challenges in few-shot settings. Together, these results highlight that visual inductive reasoning remains an open challenge and COCOLogic-V2 provides a concrete foundation for advancing methods in this direction.

cs.LG↗

arXiv2026

Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings

While Prover-Verifier Games (PVGs) offer a promising path toward verifiability in nonlinear classification models, they have not yet been applied to complex inputs such as high-dimensional images. Conversely, expressive concept encodings effectively allow to translate such data into interpretable concepts but are often utilised in the context of low-capacity linear predictors. In this work, we push towards real-world verifiability by combining the strengths of both approaches. We introduce Neural Concept Verifier (NCV), a unified framework combining PVGs for formal verifiability with concept encodings to handle complex, high-dimensional inputs in an interpretable way. NCV achieves this by utilizing recent minimally supervised concept discovery models to extract structured concept encodings from raw inputs. A prover then selects a subset of these encodings, which a verifier, implemented as a nonlinear predictor, uses exclusively for decision-making. Our evaluations show that NCV outperforms classic concept-based models and pixel-based PVG classifier baselines on high-dimensional, logically complex datasets and helps mitigate shortcut behavior. Overall, we demonstrate NCV as a promising step toward concept-level, verifiable AI.

cs.LG↗

arXiv2026

All Eyes on the Workflow: Automated and Efficient Event Discovery from Video Streams

Disciplines such as business process management and process mining aid organizations by discovering insights about processes on the basis of recorded event data. However, an obstacle to process analysis is data multi-modality: for instance, data in video form are not directly interpretable as events. Existing approaches rely on a dictionary of activity label as input, cannot provide frame-by-frame labeling explanations, or rely on superseded computer vision techniques. In this work, we present SnapLog, an approach to extract event data from videos by converting frames to feature vectors using image embeddings and performing temporal segmentation through frame-wise similarity matrices. A generalized few-shot classification is then used to assign labels to the video segments, yielding labeled, timestamped sub-sequences of frames that are interpretable as events. Conventional process mining techniques can be used to analyze the resulting data. We show that our approach produces logs that accurately reflect the process in the videos.

cs.CV↗

arXiv2026

CycliST: A Video Language Model Benchmark for Reasoning on Cyclical State Transitions

We present CycliST, a novel benchmark dataset designed to evaluate Video Language Models (VLM) on their ability for textual reasoning over cyclical state transitions. CycliST captures fundamental aspects of real-world processes by generating synthetic, richly structured video sequences featuring periodic patterns in object motion and visual attributes. CycliST employs a tiered evaluation system that progressively increases difficulty through variations in the number of cyclic objects, scene clutter, and lighting conditions, challenging state-of-the-art models on their spatio-temporal cognition. We conduct extensive experiments with current state-of-the-art VLMs, both open-source and proprietary, and reveal their limitations in generalizing to cyclical dynamics such as linear and orbital motion, as well as time-dependent changes in visual attributes like color and scale. Our results demonstrate that present-day VLMs struggle to reliably detect and exploit cyclic patterns, lack a notion of temporal understanding, and are unable to extract quantitative insights from scenes, such as the number of objects in motion, highlighting a significant technical gap that needs to be addressed. More specifically, we find no single model consistently leads in performance: neither size nor architecture correlates strongly with outcomes, and no model succeeds equally well across all tasks. By providing a targeted challenge and a comprehensive evaluation framework, CycliST paves the way for visual reasoning models that surpass the state-of-the-art in understanding periodic patterns.

cs.CV↗

arXiv2026

Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation

Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.g., on the model's ability to follow specific formatting requirements. This especially penalizes base models that may know the correct answers but lack the ability -- typically introduced in post-training -- to structure them as instructed. To overcome this, we propose soft-prompt tuning, an efficient, fair, and architecture-agnostic model evaluation. By optimizing only 10 soft-prompt vectors (roughly 0.0006% parameters for a 7B model) over a short tuning period, we adapt models to specific benchmark formats, closing gaps in format-following and ensuring that underlying knowledge is accurately reflected in benchmark scores. This allows one to fairly compare different base models -- trained with various pre-training recipes -- on benchmarks without the need for full post-training. We evaluated soft-prompt tuning across 7 models and 7 datasets. The results show that (a) soft-prompt tuning saturates format-following within 80 steps (~640 samples) making it highly efficient, (b) soft-prompt tuning significantly outperforms zero- and few-shot prompting, surfacing base model knowledge that standard prompting misses, that (c) even post-trained models can benefit from soft-prompts to maximize format compliance, and that (d) soft-prompted base model performance predicts post-trained model rankings more reliably than zero- and few-shot baselines, offering a low-cost proxy for downstream model quality. Our contributions include (1) metrics which disentangle format-following and knowledge accuracy, (2) a fairer benchmarking protocol of LLM knowledge, and (3) a cost- and memory-effective recipe to identify optimal pre-training strategies early in LLM development.

cs.CL↗

arXiv2026

Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes

Interactive agents trained only against task return can achieve high scores while failing to represent the mechanisms that make their actions succeed. This makes brittle behavior difficult to diagnose and limits adaptation when environment dynamics change. Existing LLM reflection and policy-code repair can revise behavior from failed trajectories, but questions and world-understanding tests are usually used only after training. We introduce an Explicit Symbolic Behavioral Model (ESBM), a trainable behavioral model that couples task performance with evidence-grounded question answering and executable mechanism prediction. An ESBM represents behavior through typed predicates, weighted rules, bounded options and mechanism memory; the mechanism layer predicts symbolic events, object changes, rewards and terminal consequences under action interventions. After each rollout, adaptive questions and active world-model probes convert score failures, QA errors and transition-prediction errors into constraints for local ESBM edits. Candidate models are selected by a multi-criterion rule that jointly evaluates task score, answerability and active world-model consistency. Under the tested Atari-style protocols, ESBM learns high-scoring policies while producing explicit answers and executable mechanism predictions, indicating that adaptive questions can serve as both training pressure and reusable benchmarks for mechanistic policy learning in this setting.

cs.LG↗

arXiv2026

Finding DoRI: Discovery of Retained Images in Diffusion Models

Text-to-image diffusion models (DMs) have achieved remarkable success in image generation. However, concerns about data privacy and intellectual property remain due to their potential to inadvertently memorize and replicate training data. Recent mitigation efforts have focused on identifying and pruning weights responsible for triggering verbatim training data replication, based on the assumption that memorization can be localized. We challenge this assumption and demonstrate that, even after such pruning, small perturbations to the text embeddings of previously mitigated prompts can re-trigger data replication, revealing the fragility of such methods. Our further analysis then provides multiple indications that memorization is indeed \textit{not} inherently local: (1) replication triggers for memorized images are distributed throughout text embedding space; (2) embeddings yielding the same replicated image produce divergent model activations; and (3) different pruning methods identify inconsistent sets of memorization-related weights for the same image. Finally, we show that bypassing the locality assumption enables more robust mitigation through adversarial fine-tuning. These findings provide new insights into the fundamental nature of memorization in text-to-image DMs and inform the future development of more reliable mitigation methods against DM memorization.

cs.CV↗

arXiv2026

No Safe Dose: How Training Data Drives Unsafe Image Generation

Text-to-image models trained on large-scale data often inevitably ingest unsafe content. While some people observe input-output amplifications, it remains unclear whether and how training data composition directly drives model output safety or by other factors. We shed light on this question by isolating this variable: we train the same text-to-image model on datasets that differ \emph{only} in their fraction of unsafe images (0\% to 9.6\%), across several dataset scales (100K to 8M). Then we generate images with the resulting models, and evaluate them with four independent safety classifiers. Output unsafety rises monotonically from 16.6\% at 0\% contamination to 25.5\% at 5\%. A factorial design reveals that the \emph{proportion}, not the absolute count, of unsafe training images is the operative variable. The 16.6\% irreducible baseline at zero contamination implicates the other components, e.g. frozen text encoder, as a residual safety risk -- confirmed by a text encoder ablation showing that SafeCLIP reduces this floor to 9.6\%, while the dose-response effect persists across all three encoders tested. Critically, no quality degradation in terms of FID, CLIPscore and ImageReward accompanies safety filtering. These results establish that data curation and text encoder safety are complementary and independently effective interventions. At the same time, the remaining level of unsafety poses questions for future research about emerging capabilities and compositionality.

cs.CV↗

arXiv2026

ORCA: An End-to-End Interactive Copilot for Optimized Root Cause Analysis

Causal analysis is a crucial task in many domains, including manufacturing, social science, and medicine. However, despite recent progress, the conceptual and methodological complexity of causal methods makes them largely inaccessible to domain experts. This gap prevents experts from leveraging these advances and hinders researchers who lack access to real-world data for validation. To bridge this divide, we introduce ORCA, a copilot for end-to-end causal analysis. ORCA orchestrates agents to understand the user's goals and guide them through the most appropriate causal analysis workflow, from fully automatic to highly user-guided execution. It features causal discovery, causal effect estimation, explainability and Root-Cause-Analysis (RCA). ORCA evaluates and compares performance, generates key metrics and diagrams, and generates insights through structured reports. We highlight its effectiveness across several real-world use-cases.

cs.AI↗

arXiv2026

Imitation learning for clinical decision support in pediatric ECMO

Pediatric critical care is a dynamic, high-stakes process involving constant monitoring and adjustments in life-saving treatments. Modeling these interventions is crucial for effective decision support. To address the challenges of high complexity and data scarcity in pediatric Extracorporeal Membrane Oxygenation (ECMO), we frame clinical decision-making as learning to act from trajectories, i.e., imitation learning that learns action models from observational data, with a key feature that actions are not directly observed. We consider TabPFN, a recent transformer-based approach for tabular data, and traditional baselines including XGBoost and Multi-Layer Perceptrons(MLPs) on real-world pediatric ECMO data to learn the action models. We find that the TabPFN-based approach consistently outperforms these classical baselines, supporting its use as a strong clinician-behavior baseline for pediatric ECMO decision support.

cs.LG↗

arXiv2026

STORM: Segment, Track, and Object Re-Localization from a Single Image

Accurate 6D pose estimation and tracking are core capabilities for physical AI systems, yet real-world deployment remains brittle and labor-intensive. Many pipelines rely on CAD models, manual masking, or per-object adaptation, and still fail under occlusion or fast motion without a principled way to recognize failure. We propose STORM, a unified framework for reference-conditioned 6D tracking that can operate from a single reference image, with minimal manual input and improved robustness. STORM combines: (i) Hierarchical Spatial Fusion Attention (HSFA), a task-driven reference-query fusion architecture that supports both single-reference and multi-reference conditioning and can optionally use vision-language semantic conditioning to resolve instance ambiguities; and (ii) a BCE-trained tracking verifier whose continuous compatibility logit is used as an energy-like score to detect drift and trigger automatic re-initialization. Experiments on LM-O and YCB-Video show that STORM improves annotation-free pose tracking accuracy over strong baselines and recovers reliably from severe occlusions and rapid viewpoint changes with minimal overhead.

cs.CV↗

arXiv2026

SLR: Automated Synthesis for Scalable Logical Reasoning

We introduce SLR, an end-to-end framework for systematic evaluation and training of Large Language Models (LLMs) via Scalable Logical Reasoning. Given a user's task specification, SLR automatically synthesizes (i) an instruction prompt for an inductive reasoning task, (ii) a validation program, executable on model outputs to provide verifiable rewards, and (iii) the latent ground-truth rule. This process is fully automated, scalable, requires no human annotations, and offers precise control over task difficulty. Using SLR, we create SLR-Bench, a benchmark comprising 19k prompts organized into 20 curriculum levels that progressively increase in relational, arithmetic, and recursive complexity. Large-scale evaluation reveals that contemporary LLMs readily produce syntactically valid rules, yet often fail at correct logical inference. Recent reasoning LLMs demonstrate improved performance but incur very high test-time computation, with costs exceeding $300 for just 1,000 prompts. Finally, curriculum learning via SLR doubles Llama-3-8B accuracy on SLR-Bench, achieving parity with Gemini-Flash-Thinking at a fraction of computational cost. Moreover, these reasoning capabilities generalize to a wide range of established benchmarks, underscoring the effectiveness of SLR for downstream reasoning.

cs.AI↗