Building upon our previous investigations of O1 replication (Part 1: Journey Learning [Qin et al., 2024] and Part 2: Distillation [Huang et al., 2024]), this work explores the potential of inference-time scaling in large language models (LLMs) for medical reasoning tasks, ranging from diagnostic decision-making to treatment planning. Through extensive experiments on medical benchmarks of varying complexity (MedQA, Medbullets, and JAMA Clinical Challenges), our investigation reveals several key insights: (1) Increasing inference time does lead to improved performance. With a modest training set of 500 samples, our model yields substantial performance improvements of 6%-11%. (2) Task complexity directly correlates with the required length of reasoning chains, confirming the necessity of extended thought processes for challenging problems. (3) The differential diagnoses generated by our model adhere to the principles of the hypothetico-deductive method, producing a list of potential conditions that may explain a patient's symptoms and systematically narrowing these possibilities by evaluating the evidence. These findings demonstrate the promising synergy between inference-time scaling and journey learning in advancing LLMs' real-world clinical reasoning capabilities.

Fine-tuning helps large language models (LLM) recover degraded information and enhance task performance. Although Low-Rank Adaptation (LoRA) is widely used and effective for fine-tuning, we have observed that its scaling factor can limit or even reduce performance as the rank size increases. To address this issue, we propose RoRA (Rank-adaptive Reliability Optimization), a simple yet effective method for optimizing LoRA's scaling factor. By replacing $\alpha/r$ with $\alpha/\sqrt{r}$, RoRA ensures improved performance as rank size increases. Moreover, RoRA enhances low-rank adaptation in fine-tuning uncompressed models and excels in the more challenging task of accuracy recovery when fine-tuning pruned models. Extensive experiments demonstrate the effectiveness of RoRA in fine-tuning both uncompressed and pruned models. RoRA surpasses the state-of-the-art (SOTA) in average accuracy and robustness on LLaMA-7B/13B, LLaMA2-7B, and LLaMA3-8B, specifically outperforming LoRA and DoRA by 6.5% and 2.9% on LLaMA-7B, respectively. In pruned model fine-tuning, RoRA shows significant advantages; for SHEARED-LLAMA-1.3, a LLaMA-7B with 81.4% pruning, RoRA achieves 5.7% higher average accuracy than LoRA and 3.9% higher than DoRA.

Approximately 200 million individuals around the world suffer from varying degrees of visual impairment, making it crucial to leverage AI technology to offer walking assistance for these people. With the recent progress of vision-language models (VLMs), employing VLMs to improve this field has emerged as a popular research topic. However, most existing methods are studied on self-built question-answering datasets, lacking a unified training and testing benchmark for walk guidance. Moreover, in blind walking task, it is necessary to perform real-time streaming video parsing and generate concise yet informative reminders, which poses a great challenge for VLMs that suffer from redundant responses and low inference efficiency. In this paper, we firstly release a diverse, extensive, and unbiased walking awareness dataset, containing 12k video-manual annotation pairs from Europe and Asia to provide a fair training and testing benchmark for blind walking task. Furthermore, a WalkVLM model is proposed, which employs chain of thought for hierarchical planning to generate concise but informative reminders and utilizes temporal-aware adaptive prediction to reduce the temporal redundancy of reminders. Finally, we have established a solid benchmark for blind walking task and verified the advantages of WalkVLM in stream video processing for this task compared to other VLMs. Our dataset and code will be released at anonymous link https://walkvlm2024.github.io.

The field of machine translation has achieved significant advancements, yet domain-specific terminology translation, particularly in AI, remains challenging. We introduce GIST, a large-scale multilingual AI terminology dataset containing 5K terms extracted from top AI conference papers spanning 2000 to 2023. The terms are translated into Arabic, Chinese, French, Japanese, and Russian using a hybrid framework that combines LLMs for extraction with human expertise for translation. The dataset's quality is benchmarked against existing resources, demonstrating superior translation accuracy through crowdsourced evaluation. GIST is integrated into translation workflows using post-translation refinement methods that require no retraining, where LLM prompting consistently improves BLEU and COMET scores. A web demonstration on the ACL Anthology platform highlights its practical application, showcasing improved accessibility for non-English speakers. This work aims to address critical gaps in AI terminology resources and fosters global inclusivity and collaboration in AI research.

While Large Language Models (LLMs) have demonstrated remarkable capabilities in scientific tasks, existing evaluation frameworks primarily assess their performance using rich contextual inputs, overlooking their ability to generate novel ideas from minimal information. We introduce LiveIdeaBench, a comprehensive benchmark that evaluates LLMs' scientific creativity and divergent thinking capabilities using single-keyword prompts. Drawing from Guilford's creativity theory, our framework employs a dynamic panel of state-of-the-art LLMs to assess generated ideas across four key dimensions: originality, feasibility, fluency, and flexibility. Through extensive experimentation with 20 leading models across 1,180 keywords spanning 18 scientific domains, we reveal that scientific creative ability shows distinct patterns from general intelligence metrics. Notably, our results demonstrate that models like QwQ-32B-preview achieve comparable creative performance to top-tier models like o1-preview, despite significant gaps in their general intelligence scores. These findings highlight the importance of specialized evaluation frameworks for scientific creativity and suggest that the development of creative capabilities in LLMs may follow different trajectories than traditional problem-solving abilities.

Understanding the mechanisms behind Large Language Models (LLMs) is crucial for designing improved models and strategies. While recent studies have yielded valuable insights into the mechanisms of textual LLMs, the mechanisms of Multimodal Large Language Models (MLLMs) remain underexplored. In this paper, we apply mechanistic interpretability methods to analyze the visual question answering (VQA) mechanisms in Llava. We compare the mechanisms between VQA and textual QA (TQA) in color answering tasks and find that: a) VQA exhibits a mechanism similar to the in-context learning mechanism observed in TQA; b) the visual features exhibit significant interpretability when projecting the visual embeddings into the embedding space; and c) Llava enhances the existing capabilities of the corresponding textual LLM Vicuna during visual instruction tuning. Based on these findings, we develop an interpretability tool to help users and researchers identify important visual locations for final predictions, aiding in the understanding of visual hallucination. Our method demonstrates faster and more effective results compared to existing interpretability approaches. Large Language Models (LLMs) (Brown, 2020; Ouyang et al., 2022; Touvron et al., 2023) have achieved remarkable results in numerous downstream tasks (Xiao et al., 2023; Tan et al., 2023; Deng et al., 2023). However, the underlying mechanisms are not yet well understood. This lack of clarity poses a significant challenge for researchers attempting to address issues such as hallucination (Yao et al., 2023), toxicity (Gehman et al., 2020), and bias (Kotek et al., 2023) in LLMs. Therefore, understanding the mechanisms of LLMs has become an increasingly important area of research.

Nowadays transformer-based Large Language Models (LLM) for code generation tasks usually apply sampling and filtering pipelines. Due to the sparse reward problem in code generation tasks caused by one-token incorrectness, transformer-based models will sample redundant programs till they find a correct one, leading to low efficiency. To overcome the challenge, we incorporate Experience Replay (ER) in the fine-tuning phase, where codes and programs produced are stored and will be replayed to give the LLM agent a chance to learn from past experiences. Based on the spirit of ER, we introduce a novel approach called BTP pipeline which consists of three phases: beam search sampling, testing phase, and prioritized experience replay phase. The approach makes use of failed programs collected by code models and replays programs with high Possibility and Pass-rate Prioritized value (P2Value) from the replay buffer to improve efficiency. P2Value comprehensively considers the possibility of transformers' output and pass rate and can make use of the redundant resources caused by the problem that most programs collected by LLMs fail to pass any tests. We empirically apply our approach in several LLMs, demonstrating that it enhances their performance in code generation tasks and surpasses existing baselines.

It was an interesting year for robots at CES 2025. While we had hoped the AI boom would bring a new wave of useful robots to the show, it seems that many robotics companies are still figuring out exactly how to best use AI. What we found instead was a mix of adorable robot companions, strange concepts and one, slightly terrifying humanoid. We visited a lot of robots at CES and, for better or worse, some really left an impression on us. These are the ones that stood out the most.

Citing internal Meta communications, the filing claims that the social network company's chief executive backed the use of the LibGen dataset, a vast online archive of books, despite warnings within the company's AI executive team that it is a dataset "we know to be pirated". The internal message says that using a database containing pirated material could weaken the Facebook and Instagram owner's negotiations with regulators, according to the filing. "Media coverage suggesting we have used a dataset we know to be pirated, such as LibGen, may undermine our negotiating position with regulators." The authors sued Meta in 2023, arguing that the social media company misused their books to train Llama, the large language model that powers its chatbots. The Library Genesis, or LibGen, dataset is a "shadow library" that originated in Russia and claims to contain millions of novels, nonfiction books and science magazine articles.

Among many skills that the agents need to possess, building and maintaining a semantic map of the environment is most crucial in long-horizon tasks. A semantic map captures information about the environment in a structured way, allowing the agent to reference it for advanced reasoning throughout the task. While existing surveys in embodied AI focus on general advancements or specific tasks like navigation and manipulation, this paper provides a comprehensive review of semantic map-building approaches in embodied AI, specifically for indoor navigation. We categorize these approaches based on their structural representation (spatial grids, topological graphs, dense point-clouds or hybrid maps) and the type of information they encode (implicit features or explicit environmental data). We also explore the strengths and limitations of the map building techniques, highlight current challenges, and propose future research directions. We identify that the field is moving towards developing open-vocabulary, queryable, task-agnostic map representations, while high memory demands and computational inefficiency still remaining to be open challenges. This survey aims to guide current and future researchers in advancing semantic mapping techniques for embodied AI systems.