As large-scale AI models expand, training becomes costlier and sustaining progress grows harder. Classical scaling laws (e.g., Kaplan et al. (2020), Hoffmann et al. (2022)) predict training loss from a static compute budget yet neglect time and efficiency, prompting the question: how can we balance ballooning GPU fleets with rapidly improving hardware and algorithms? We introduce the relative-loss equation, a time- and efficiency-aware framework that extends classical AI scaling laws. Our model shows that, without ongoing efficiency gains, advanced performance could demand millennia of training or unrealistically large GPU fleets. However, near-exponential progress remains achievable if the "efficiency-doubling rate" parallels Moore's Law. By formalizing this race to efficiency, we offer a quantitative roadmap for balancing front-loaded GPU investments with incremental improvements across the AI stack. Empirical trends suggest that sustained efficiency gains can push AI scaling well into the coming decade, providing a new perspective on the diminishing returns inherent in classical scaling.

While recent advancements in foundation models have significantly impacted machine learning, rigorous tests on the performance of time series foundation models (TSFMs) remain largely underexplored. This paper presents an empirical study evaluating the zero-shot, long-horizon forecasting abilities of several leading TSFMs over two synthetic datasets constituting noisy periodic time series. We assess model efficacy across different noise levels, underlying frequencies, and sampling rates. As benchmarks for comparison, we choose two statistical techniques: a Fourier transform (FFT)-based approach and a linear autoregressive (AR) model. Our findings demonstrate that while for time series with bounded periods and higher sampling rates, TSFMs can match or outperform the statistical approaches, their forecasting abilities deteriorate with longer periods, higher noise levels, lower sampling rates and more complex shapes of the time series.

Video Large Language Models (Video LLMs) have recently exhibited remarkable capabilities in general video understanding. However, they mainly focus on holistic comprehension and struggle with capturing fine-grained spatial and temporal details. Besides, the lack of high-quality object-level video instruction data and a comprehensive benchmark further hinders their advancements. To tackle these challenges, we introduce the VideoRefer Suite to empower Video LLM for finer-level spatial-temporal video understanding, i.e., enabling perception and reasoning on any objects throughout the video. Specially, we thoroughly develop VideoRefer Suite across three essential aspects: dataset, model, and benchmark. Firstly, we introduce a multi-agent data engine to meticulously curate a large-scale, high-quality object-level video instruction dataset, termed VideoRefer-700K. Next, we present the VideoRefer model, which equips a versatile spatial-temporal object encoder to capture precise regional and sequential representations. Finally, we meticulously create a VideoRefer-Bench to comprehensively assess the spatial-temporal understanding capability of a Video LLM, evaluating it across various aspects. Extensive experiments and analyses demonstrate that our VideoRefer model not only achieves promising performance on video referring benchmarks but also facilitates general video understanding capabilities.

The integration of Large Language Models (LLMs) and Vision-Language Models (VLMs) opens new avenues for addressing complex challenges in multimodal content analysis, particularly in biased news detection. This study introduces VLBias, a framework that leverages state-of-the-art LLMs and VLMs to detect linguistic and visual biases in news content. We present a multimodal dataset comprising textual content and corresponding images from diverse news sources. We propose a hybrid annotation framework that combines LLM-based annotations with human review to ensure high-quality labeling while reducing costs and enhancing scalability. Our evaluation compares the performance of state-of-the-art SLMs and LLMs for both modalities (text and images) and the results reveal that while SLMs are computationally efficient, LLMs demonstrate superior accuracy in identifying subtle framing and text-visual inconsistencies. Furthermore, empirical analysis shows that incorporating visual cues alongside textual data improves bias detection accuracy by 3 to 5%. This study provides a comprehensive exploration of LLMs, SLMs, and VLMs as tools for detecting multimodal biases in news content and highlights their respective strengths, limitations, and potential for future applications

Modern Large Language Models (LLMs) are safety trained using Supervised Fine Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) to mitigate harmful, undesirable, or otherwise disallowed outputs [2]-[4]. Despite ongoing advances in these methods, today's models still exhibit safety shortcomings: they can be tricked into revealing harmful content, often refuse legitimate requests, and remain vulnerable to jailbreak attacks [5]-[8]. We argue that many of these failures arise from two limitations in modern safety training. First, LLMs must respond instantly to user requests using a fixed amount of compute, without deliberation even for complex safety scenarios. Second, LLMs must infer underlying safety standards indirectly from large sets of labeled examples, rather than directly learning the safety specifications that govern them. This reliance on implicit, pattern-based learning leads to poor data efficiency and makes it challenging for models to generalize when facing unfamiliar scenarios or adversarial attacks. We propose deliberative alignment, a training approach that teaches LLMs to explicitly reason through safety specifications before producing an answer. By applying this method to OpenAI's o-series models [1], we enable them to use chain-of-thought (CoT) reasoning to examine user prompts, identify relevant policy guidelines, and generate safer responses (e.g., Figure 1).

Toxicity detection is crucial for maintaining the peace of the society. While existing methods perform well on normal toxic contents or those generated by specific perturbation methods, they are vulnerable to evolving perturbation patterns. However, in real-world scenarios, malicious users tend to create new perturbation patterns for fooling the detectors. For example, some users may circumvent the detector of large language models (LLMs) by adding `I am a scientist' at the beginning of the prompt. In this paper, we introduce a novel problem, i.e., continual learning jailbreak perturbation patterns, into the toxicity detection field. To tackle this problem, we first construct a new dataset generated by 9 types of perturbation patterns, 7 of them are summarized from prior work and 2 of them are developed by us. We then systematically validate the vulnerability of current methods on this new perturbation pattern-aware dataset via both the zero-shot and fine tuned cross-pattern detection. Upon this, we present the domain incremental learning paradigm and the corresponding benchmark to ensure the detector's robustness to dynamically emerging types of perturbed toxic text. Our code and dataset are provided in the appendix and will be publicly available at GitHub, by which we wish to offer new research opportunities for the security-relevant communities.

We highlight two significant issues leading to the passivity of current merchant non-player characters (NPCs): pricing and communication. While immersive interactions have been a focus, negotiations between merchant NPCs and players on item prices have not received sufficient attention. First, we define passive pricing as the limited ability of merchants to modify predefined item prices. Second, passive communication means that merchants can only interact with players in a scripted manner. To tackle these issues and create an active merchant NPC, we propose a merchant framework based on large language models (LLMs), called MART, which consists of an appraiser module and a negotiator module. We conducted two experiments to guide game developers in selecting appropriate implementations by comparing different training methods and LLM sizes. Our findings indicate that finetuning methods, such as supervised finetuning (SFT) and knowledge distillation (KD), are effective in using smaller LLMs to implement active merchant NPCs. Additionally, we found three irregular cases arising from the responses of LLMs. We expect our findings to guide developers in using LLMs for developing active merchant NPCs.

Cooperation is vital to our survival and progress. Evolutionary game theory offers a lens to understand the structures and incentives that enable cooperation to be a successful strategy. As artificial intelligence agents become integral to human systems, the dynamics of cooperation take on unprecedented significance. The convergence of human-agent teaming, contract theory, and decentralized frameworks like Web3, grounded in transparency, accountability, and trust, offers a foundation for fostering cooperation by establishing enforceable rules and incentives for humans and AI agents. We conceptualize Incentivized Symbiosis as a social contract between humans and AI, inspired by Web3 principles and encoded in blockchain technology, to define and enforce rules, incentives, and consequences for both parties. By exploring this paradigm, we aim to catalyze new research at the intersection of systems thinking in AI, Web3, and society, fostering innovative pathways for cooperative human-agent coevolution.

We introduce Simultaneous Weighted Preference Optimization (SWEPO), a novel extension of Direct Preference Optimization (DPO) designed to accommodate multiple dynamically chosen positive and negative responses for each query. SWEPO employs a weighted group contrastive loss, assigning weights to responses based on their deviation from the mean reward score. This approach effectively prioritizes responses that are significantly better or worse than the average, enhancing optimization. Our theoretical analysis demonstrates that simultaneously considering multiple preferences reduces alignment bias, resulting in more robust alignment. Additionally, we provide insights into the training dynamics of our loss function and a related function, InfoNCA. Empirical validation on the UltraFeedback dataset establishes SWEPO as state-of-the-art, with superior performance in downstream evaluations using the AlpacaEval dataset.

As of December 2024, the ARC-AGI benchmark is five years old and remains unbeaten. We believe it is currently the most important unsolved AI benchmark in the world because it seeks to measure generalization on novel tasks -- the essence of intelligence -- as opposed to skill at tasks that can be prepared for in advance. This year, we launched ARC Prize, a global competition to inspire new ideas and drive open progress towards AGI by reaching a target benchmark score of 85\%. As a result, the state-of-the-art score on the ARC-AGI private evaluation set increased from 33\% to 55.5\%, propelled by several frontier AGI reasoning techniques including deep learning-guided program synthesis and test-time training. In this paper, we survey top approaches, review new open-source implementations, discuss the limitations of the ARC-AGI-1 dataset, and share key insights gained from the competition.