Skip to main content
Search

Technische Universität Berlin

8 related articles

Subscribe to updates
  1. Diffusion language models learn to count characters: no fine-tuning, summaries land within 3.1 characters of target

    For summarization settings such as headlines and previews that must fit an exact character count, Delta estimates the expected character length of the current output inside a masked diffusion language model's denoising loop and dynamically inserts or removes masked positions to steer generation toward the target. It needs no fine-tuning and applies to off-the-shelf LLaDA and Dream. Across the XSum, CNN/DailyMail and arXiv summarization benchmarks, character-length error falls by an order of magnitude relative to the baselines while summary quality stays competitive under automatic and human evaluation.

  2. arXiv

    SO3LR Tauri stretches one force field to 85 elements: a single set of weights runs proteins, nucleic acids, membranes and platinated DNA

    SO3LR Tauri extends the earlier SO3LR force field from eight elements and 4 million structures to 85 elements and roughly 148 million structures, and rewrites its short-range repulsion, electrostatics and dispersion modules. Keeping the fast SO3krates message-passing backbone, it reproduces nucleobase-pair and protein–ligand interactions and carbohydrate conformer ordering against coupled-cluster references, and yields water and organic-solvent densities, ion hydration and structures of several biomolecular classes in dynamics without system-specific fitting. The models ship in three sizes and scale to the million-atom range on a single GPU.

  3. Vehicles Leave After One-Shot Training: Exact Federated Editing Cuts Cumulative Time 36%–44% in Mobility Simulation

    One-shot federated learning finishes training in a single communication round, but the resulting model is frozen once devices join or leave, leaving full retraining as the fallback. F-SOSA draws a fixed-size uniform random client subset so outputs under neighboring device sets stay bounded in total variation, then rewrites curvature-aware fusion as a projection over client-additive sufficient statistics, enabling F-SOSA-U for withdrawing a contribution and F-SOSA-I for adding one. In a SUMO urban mobility simulation, both match retraining accuracy while cutting cumulative time and communication by 36%–44% and 22%–33%.

  4. arXiv

    Delegating quantum generative models to a remote server: the sampling protocol now estimates the corrupted-sample rate, not just accept or abort

    When the inference phase of a quantum generative model is delegated to a remote quantum server, the client can now verify the sampling result without revealing inputs, circuit, or outputs. Earlier verifiable blind sampling rested on computational assumptions, whereas this protocol builds on universal blind quantum computing and trap circuits, amortizing verification over rounds and returning an estimate of the corrupted-sample ratio beyond accept or abort. Numerical simulations run on a 4-qubit IQP Born machine for the Bars&Stripes benchmark, where trap detections correlate with wrong samples.

  5. arXiv

    MAPE-K dual-AI framework lets a quadruped robot turn natural-language intentions into executable code, robust on finite tasks while open-ended exhaustive search stays cognitively limited

    The work introduces a MAPE-K-inspired dual-AI architecture in which an LLM translates high-level natural-language intentions into executable Python code constrained to a robotic function library, while a VLM provides open-ended semantic grounding through a distillation process, with geometric and semantic thresholds triggering replanning; benchmarked on quadruped exploration tasks in Gazebo across three frontier models, finite tasks show high success rates while open-ended exhaustive tasks degrade, with failures concentrated in semantic grounding, completeness checking, and termination control rather than low-level action execution.

  6. bioRxiv

    The ModelSEED Biochemistry Database, 2026 update: grading multi-source thermodynamics

    This update expands the ModelSEED Biochemistry Database to roughly 46,000 compounds, 56,000 reactions and 37,000 metabolic structures, widens thermodynamic handling from two sources to four (group contribution, eQuilibrator 3.0, dGPredictor and experimental values) each kept with its own uncertainty, assigns gold, silver or bronze evidence grades to about 33,000 reactions, and releases reaction directions predicted by an ensemble of large language models alongside a new conflict-resolution pipeline that documents structural choices across sources.

  7. medRxiv

    The Multimodal Anonymizer: a fully local multi-agent AI system for medical data deidentification

    The study developed and evaluated the Multimodal Anonymizer, a modular, locally deployable multi-agent framework integrating multimodal large language models, task-specific neural networks, and rule-based transformations; on benchmarks spanning text, tables, PDFs, imaging, metadata, filenames, audio, handwriting, and 3D imaging, its best local configuration (orchestrator Qwen3-VL-235B-A22B-Thinking) achieved 98.80% per-patient deidentification sensitivity (95%-CI 97.20; 100) and 99.60% critical clinical preservation (95%-CI 98.80; 100), reached 100% sensitivity and critical preservation on 250 local Charité partograms, and outperformed established tools across most modalities.

  8. arXiv

    Routing Multiple Agents Below the Sum of Distances: A Parameterized Complexity Characterization of Transient Multiagent Pathfinding

    This work studies Transient Multiagent Pathfinding, in which agents must be routed without collisions and disappear upon reaching their destinations, and shows that the problem is fixed-parameter tractable in the combined parameter k+ζ, where k is the number of agents and ζ=L−λ is the gap between the sequential-routing upper bound L=1+Σdist(si,ti) and the target makespan λ, running in 2O(k²ζ)·nO(1) time, complemented by matching lower bounds (W[1]-hardness for k alone, W[1]-hardness for ζ alone when terminals need not be distinct, and no polynomial kernel for k+ζ) and by fixed-parameter tractability in ζ alone when all terminals are pairwise distinct, running in 2O(ζ³)·nO(1) time.

You’re all caught up