Advances in transformer-based language models have highlighted the benefits of language-specific pre-training on high-quality corpora. In this context, German NLP stands to gain from updated architectures and modern datasets tailored to the linguistic characteristics of the German language. GeistBERT seeks to improve German language processing by incrementally training on a diverse corpus and optimizing model performance across various NLP tasks. We pre-trained GeistBERT using fairseq, following the RoBERTa base configuration with Whole Word Masking (WWM), and initialized from GottBERT weights. The model was trained on a 1.3 TB German corpus with dynamic masking and a fixed sequence length of 512 tokens. For evaluation, we fine-tuned the model on standard downstream tasks, including NER (CoNLL 2003, GermEval 2014), text classification (GermEval 2018 coarse/fine, 10kGNAD), and NLI (German XNLI), using $F_1$ score and accuracy as evaluation metrics. GeistBERT achieved strong results across all tasks, leading among base models and setting a new state-of-the-art (SOTA) in GermEval 2018 fine text classification. It also outperformed several larger models, particularly in classification benchmarks. To support research in German NLP, we release GeistBERT under the MIT license.

In this paper, we introduce a multi-robot system that integrates mapping, localization, and task and motion planning (TAMP) enabled by 3D scene graphs to execute complex instructions expressed in natural language. Our system builds a shared 3D scene graph incorporating an open-set object-based map, which is leveraged for multi-robot 3D scene graph fusion. This representation supports real-time, view-invariant relocalization (via the object-based map) and planning (via the 3D scene graph), allowing a team of robots to reason about their surroundings and execute complex tasks. Additionally, we introduce a planning approach that translates operator intent into Planning Domain Definition Language (PDDL) goals using a Large Language Model (LLM) by leveraging context from the shared 3D scene graph and robot capabilities. We provide an experimental assessment of the performance of our system on real-world tasks in large-scale, outdoor environments. A supplementary video is available at https://youtu.be/8xbGGOLfLAY.

Large Language Models are versatile, general-purpose tools with a wide range of applications. Recently, the advent of "reasoning models" has led to substantial improvements in their abilities in advanced problem-solving domains such as mathematics and software engineering. In this work, we assessed the ability of reasoning models to perform chemistry tasks directly, without any assistance from external tools. We created a novel benchmark, called ChemIQ, consisting of 816 questions assessing core concepts in organic chemistry, focused on molecular comprehension and chemical reasoning. Unlike previous benchmarks, which primarily use multiple choice formats, our approach requires models to construct short-answer responses, more closely reflecting real-world applications. The reasoning models, OpenAI's o3-mini, Google's Gemini Pro 2.5, and DeepSeek R1, answered 50%-57% of questions correctly in the highest reasoning modes, with higher reasoning levels significantly increasing performance on all tasks. These models substantially outperformed the non-reasoning models which achieved only 3%-7% accuracy. We found that Large Language Models can now convert SMILES strings to IUPAC names, a task earlier models were unable to perform. Additionally, we show that the latest reasoning models can elucidate structures from 1D and 2D 1H and 13C NMR data, with Gemini Pro 2.5 correctly generating SMILES strings for around 90% of molecules containing up to 10 heavy atoms, and in one case solving a structure comprising 25 heavy atoms. For each task, we found evidence that the reasoning process mirrors that of a human chemist. Our results demonstrate that the latest reasoning models can, in some cases, perform advanced chemical reasoning.

We present the design process and findings of the pre-conference workshop at the Machine Learning for Healthcare Conference (2024) entitled Red Teaming Large Language Models for Healthcare, which took place on August 15, 2024. Conference participants, comprising a mix of computational and clinical expertise, attempted to discover vulnerabilities -- realistic clinical prompts for which a large language model (LLM) outputs a response that could cause clinical harm. Red-teaming with clinicians enables the identification of LLM vulnerabilities that may not be recognised by LLM developers lacking clinical expertise. We report the vulnerabilities found, categorise them, and present the results of a replication study assessing the vulnerabilities across all LLMs provided.

Fine-tuning Large Language Models (LLMs) on multi-turn reasoning datasets requires N (number of turns) separate forward passes per conversation due to reasoning token visibility constraints, as reasoning tokens for a turn are discarded in subsequent turns. We propose duplicating response tokens along with a custom attention mask to enable single-pass processing of entire conversations. We prove our method produces identical losses to the N-pass approach while reducing time complexity from $O\bigl(N^{3}\bigl)$ to $O\bigl(N^{2}\bigl)$ and maintaining the same memory complexity for a transformer based model. Our approach achieves significant training speedup while preserving accuracy. Our implementation is available online (https://github.com/devrev/One-Pass-to-Reason).

The rapid advancement of Large Language Models (LLMs) has significantly improved code generation, yet most models remain text-only, neglecting crucial visual aids like diagrams and flowcharts used in real-world software development. To bridge this gap, we introduce MM-Coder, a Multilingual Multimodal software developer. MM-Coder integrates visual design inputs-Unified Modeling Language (UML) diagrams and flowcharts (termed Visual Workflow)-with textual instructions to enhance code generation accuracy and architectural alignment. To enable this, we developed MMc-Instruct, a diverse multimodal instruction-tuning dataset including visual-workflow-based code generation, allowing MM-Coder to synthesize textual and graphical information like human developers, distinct from prior work on narrow tasks. Furthermore, we introduce MMEval, a new benchmark for evaluating multimodal code generation, addressing existing text-only limitations. Our evaluations using MMEval highlight significant remaining challenges for models in precise visual information capture, instruction following, and advanced programming knowledge. Our work aims to revolutionize industrial programming by enabling LLMs to interpret and implement complex specifications conveyed through both text and visual designs.

AI Agents rely on Large Language Models (LLMs) and Multimodal-LLMs (MLLMs) to perform interpretation and inference in text and image tasks without post-training, where LLMs and MLLMs play the most critical role and determine the initial ability and limitations of AI Agents. Usually, AI Agents utilize sophisticated prompt engineering and external reasoning framework to obtain a promising interaction with LLMs, e.g., Chain-of-Thought, Iteration of Thought and Image-of-Thought. However, they are still constrained by the inherent limitations of LLM in understanding natural language, and the iterative reasoning process will generate a large amount of inference cost. To this end, we propose a novel AI Agent Reasoning Framework with Introspection of Thought (INoT) by designing a new LLM-Read code in prompt. It enables LLM to execute programmatic dialogue reasoning processes following the code in prompt. Therefore, self-denial and reflection occur within LLM instead of outside LLM, which can reduce token cost effectively. Through our experiments on six benchmarks for three different tasks, the effectiveness of INoT is verified, with an average improvement of 7.95\% in performance, exceeding the baselines. Furthermore, the token cost of INoT is lower on average than the best performing method at baseline by 58.3\%. In addition, we demonstrate the versatility of INoT in image interpretation and inference through verification experiments.

We introduce our Leanabell-Prover-V2, a 7B large language models (LLMs) that can produce formal theorem proofs in Lean 4, with verifier-integrated Long Chain-of-Thoughts (CoT). Following our previous work Leanabell-Prover-V1, we continual to choose to posttrain existing strong prover models for further performance improvement. In our V2 version, we mainly upgrade the Reinforcement Learning (RL) with feedback provided by the Lean 4 verifier. Crucially, verifier feedback, such as indicating success or detailing specific errors, allows the LLM to become ``self-aware'' of the correctness of its own reasoning process and learn to reflexively correct errors. Leanabell-Prover-V2 directly optimizes LLM reasoning trajectories with multi-turn verifier interactions, together with feedback token masking for stable RL training and a simple reward strategy. Experiments show that Leanabell-Prover-V2 improves performance by 3.2% (pass@128) with Kimina-Prover-Preview-Distill-7B and 2.0% (pass@128) with DeepSeek-Prover-V2-7B on the MiniF2F test set. The source codes, curated data and models are available at: https://github.com/Leanabell-LM/Leanabell-Prover-V2.

This paper introduces the Ambient Intelligence Rehabilitation Support (AIRS) framework, an advanced artificial intelligence-based solution tailored for home rehabilitation environments. AIRS integrates cutting-edge technologies, including Real-Time 3D Reconstruction (RT-3DR), intelligent navigation, and large Vision-Language Models (VLMs), to create a comprehensive system for machine-guided physical rehabilitation. The general AIRS framework is demonstrated in rehabilitation scenarios following total knee replacement (TKR), utilizing a database of 263 video recordings for evaluation. A smartphone is employed within AIRS to perform RT-3DR of living spaces and has a body-matched avatar to provide visual feedback about the excercise. This avatar is necessary in (a) optimizing exercise configurations, including camera placement, patient positioning, and initial poses, and (b) addressing privacy concerns and promoting compliance with the AI Act. The system guides users through the recording process to ensure the collection of properly recorded videos. AIRS employs two feedback mechanisms: (i) visual 3D feedback, enabling direct comparisons between prerecorded clinical exercises and patient home recordings and (ii) VLM-generated feedback, providing detailed explanations and corrections for exercise errors. The framework also supports people with visual and hearing impairments. It also features a modular design that can be adapted to broader rehabilitation contexts. AIRS software components are available for further use and customization.

Image captioning is an important problem in developing various AI systems, and these tasks require large volumes of annotated images to train the models. Since all existing labelled datasets are already used for training the large Vision Language Models (VLMs), it becomes challenging to improve the performance of the same. Considering this, it is essential to consider the unsupervised image captioning performance, which remains relatively under-explored. To that end, we propose LoGIC (Lewis Communication Game for Image Captioning), a Multi-agent Reinforcement Learning game. The proposed method consists of two agents, a 'speaker' and a 'listener', with the objective of learning a strategy for communicating in natural language. We train agents in the cooperative common-reward setting using the GRPO algorithm and show that improvement in image captioning performance emerges as a consequence of the agents learning to play the game. We show that using pre-trained VLMs as the 'speaker' and Large Language Model (LLM) for language understanding in the 'listener', we achieved a $46$ BLEU score after fine-tuning using LoGIC without additional labels, a $2$ units advantage in absolute metrics compared to the $44$ BLEU score of the vanilla VLM. Additionally, we replace the VLM from the 'speaker' with lightweight components: (i) a ViT for image perception and (ii) a GPT2 language generation, and train them from scratch using LoGIC, obtaining a $31$ BLEU score in the unsupervised setting, a $10$ points advantage over existing unsupervised image-captioning methods.