Related papers: Apriel-1.5-15b-Thinker

Hybrid reasoning language models are commonly controlled through high-level Think/No-think instructions to regulate reasoning behavior, yet we found that such mode switching is largely driven by a small set of trigger tokens rather than the…

We demonstrate SAGE-32B, a 32 billion parameter language model that focuses on agentic reasoning and long range planning tasks. Unlike chat models that aim for general conversation fluency, SAGE-32B is designed to operate in an agentic…

While large language models (LLMs) have achieved remarkable performance in various tasks including mathematical reasoning, their development typically demands prohibitive computational resources. Recent advancements have reduced costs for…

Current critic-free RL methods for large reasoning models suffer from severe inefficiency when training on positive homogeneous prompts (where all rollouts are correct), resulting in waste of rollouts due to zero advantage estimates. We…

We present Bielik 11B v2, a state-of-the-art language model optimized for Polish text processing. Built on the Mistral 7B v0.2 architecture and scaled to 11B parameters using depth up-scaling, this model demonstrates exceptional performance…

We present GuardReasoner-Omni, a reasoning-based guardrail model designed to moderate text, image, video, and audio data. First, we construct a comprehensive training corpus comprising 181k samples spanning these four modalities. Our…

We introduce Xmodel-1.5, a 1-billion-parameter multilingual large language model pretrained on 2 trillion tokens, designed for balanced performance and scalability. Unlike most large models that use the BPE tokenizer, Xmodel-1.5 employs a…

Multimodal Large Language Models (MLLMs) have made remarkable progress in multimodal perception and reasoning by bridging vision and language. However, most existing MLLMs perform reasoning primarily with textual CoT, which limits their…

We propose a novel multimodal video benchmark - the Perception Test - to evaluate the perception and reasoning skills of pre-trained multimodal models (e.g. Flamingo, SeViLA, or GPT-4). Compared to existing benchmarks that focus on…

Reinforcement learning (RL) has emerged as a dominant paradigm for eliciting long-horizon reasoning in Large Language Models (LLMs). However, scaling Tool-Integrated Reasoning (TIR) via RL remains challenging due to interaction collapse: a…

We introduce Mistral 7B v0.1, a 7-billion-parameter language model engineered for superior performance and efficiency. Mistral 7B outperforms Llama 2 13B across all evaluated benchmarks, and Llama 1 34B in reasoning, mathematics, and code…

Designing aligned and robust rewards for open-ended generation remains a key barrier to RL post-training. Rubrics provide structured, interpretable supervision, but scaling rubric construction is difficult: expert rubrics are costly,…

The paradigm shift in large language models (LLMs) from instinctive responses to chain-of-thought (CoT) reasoning has fueled two prevailing assumptions: (1) reasoning capabilities only emerge in sufficiently large models, and (2) such…

Tool-integrated visual reasoning (TiVR) has demonstrated great potential in enhancing multimodal problem-solving. However, existing TiVR paradigms mainly focus on integrating various visual tools through reinforcement learning, while…

Inspired by the impressive reasoning capabilities demonstrated by reinforcement learning approaches like DeepSeek-R1, recent emerging research has begun exploring the use of reinforcement learning (RL) to enhance vision-language models…

Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs,…

Artificial Intelligence (AI) has achieved remarkable success in specialized tasks but struggles with efficient skill acquisition and generalization. The Abstraction and Reasoning Corpus (ARC) benchmark evaluates intelligence based on…

Unifying multimodal understanding and generation has shown impressive capabilities in cutting-edge proprietary systems. In this work, we introduce BAGEL, an open-source foundational model that natively supports multimodal understanding and…

We introduce Falcon2-11B, a foundation model trained on over five trillion tokens, and its multimodal counterpart, Falcon2-11B-vlm, which is a vision-to-text model. We report our findings during the training of the Falcon2-11B which follows…

The dominant paradigm for training large reasoning models starts with pre-training using next-token prediction loss on vast amounts of data. Reinforcement learning, while powerful in scaling reasoning, is introduced only as the very last…