Modern game development faces significant challenges in creativity and cost due to predetermined content in traditional game engines. Recent breakthroughs in video generation models, capable of synthesizing realistic and interactive virtual environments, present an opportunity to revolutionize game creation. This position paper argues that next-generation game engines should be built on Interactive Generative Video (IGV). We term such engines Generative Game Engines (GGE), with IGV as the perceptual and world-generation core under designer control. We argue why IGV is uniquely suited for this role, identify what is missing, and examine progress across six functional modules to show how each supports our position, culminating in a five-level maturity roadmap (L0-L4). Drawing on discussions with researchers, game developers, and community participants, we present nine alternative views and ethical considerations to stimulate debate.
As online news consumption grows, personalized recommendation systems have become integral to digital journalism. However, these systems risk reinforcing filter bubbles and political polarization by failing to incorporate diverse perspectives. Stance detection -- identifying a text's position on a target -- can help mitigate this by enabling viewpoint-aware recommendations and data-driven analyses of media bias. Yet, existing stance detection research remains largely limited to short texts and high-resource languages. To address these gaps, we introduce \textsc{K-News-Stance}, the first Korean dataset for article-level stance detection, comprising 2,000 news articles with article-level and 19,650 segment-level stance annotations across 47 societal issues. We also propose \textsc{JoA-ICL}, a \textbf{Jo}urnalism-guided \textbf{A}gentic \textbf{I}n-\textbf{C}ontext \textbf{L}earning framework that employs a language model agent to predict the stances of key structural segments (e.g., leads, quotes), which are then aggregated to infer the overall article stance. Experiments show that \textsc{JoA-ICL} outperforms existing stance detection methods, highlighting the benefits of segment-level agency in capturing the overall position of long-form news articles. Two case studies further demonstrate its broader utility in promoting viewpoint diversity in news recommendations and uncovering patterns of media bias.
In this paper, we investigate the applicability of the CLIP-EBC framework, originally designed for crowd counting, to car object counting using the CARPK dataset. Experimental results show that our model achieves second-best performance compared to existing methods. In addition, we propose a K-means weighted clustering method to estimate object positions based on predicted density maps, indicating the framework's potential extension to localization tasks.
Large language models (LLMs) are often praised for exhibiting near-human performance on a wide range of tasks and valued for their ability to hold a general conversation. The rise of agentic AI systems is, however, ushering in a mass of applications in which language models perform a small number of specialized tasks repetitively and with little variation. Here we lay out the position that small language models (SLMs) are sufficiently powerful, inherently more suitable, and necessarily more economical for many invocations in agentic systems, and are therefore the future of agentic AI. Our argumentation is grounded in the current level of capabilities exhibited by SLMs, the common architectures of agentic systems, and the economy of LM deployment. We further argue that in situations where general-purpose conversational abilities are essential, heterogeneous agentic systems (i.e., agents invoking multiple different models) are the natural choice. We discuss the potential barriers for the adoption of SLMs in agentic systems and outline a general LLM-to-SLM agent conversion algorithm. Our position, formulated as a value statement, highlights the significance of the operational and economic impact even a partial shift from LLMs to SLMs is to have on the AI agent industry. We aim to stimulate the discussion on the effective use of AI resources and hope to advance the efforts to lower the costs of AI of the present day. Calling for both contributions to and critique of our position, we commit to publishing all such correspondence at https://research.nvidia.com/labs/lpr/slm-agents.
Radio-frequency simultaneous localization and mapping (RF-SLAM) methods jointly infer the position of mobile transmitters and receivers in wireless networks, together with a geometric map of the propagation environment. An inferred map of specular surfaces can be used to exploit non-line-of-sight components of the multipath channel to increase robustness, bypass obstructions, and improve overall communication and positioning performance. While performance bounds for user location are well established, the literature lacks performance bounds for map information. This paper derives the mapping error bound (MEB), i.e., the posterior Cram\'er-Rao lower bound on the position and orientation of specular surfaces, for RF-SLAM. In particular, we consider a very general scenario with single- and double-bounce reflections, as well as distributed anchors. We demonstrate numerically that a state-of-the-art RF-SLAM algorithm asymptotically converges to this MEB. The bounds assess not only the localization (position and orientation) but also the mapping performance of RF-SLAM algorithms in terms of global features.
An organ shape atlas, which represents the shape and position of the organs and skeleton of a living body using a small number of parameters, is expected to have a wide range of clinical applications, including intraoperative guidance and radiotherapy. Because the shape and position of soft organs vary greatly among patients, it is difficult for linear models to reconstruct shapes that have large local variations. Because it is difficult for conventional nonlinear models to control and interpret the organ shapes obtained, deep learning has been attracting attention in three-dimensional shape representation. In this study, we propose an organ shape atlas based on a mesh variational autoencoder (MeshVAE) with hierarchical latent variables. To represent the complex shapes of biological organs and nonlinear shape differences between individuals, the proposed method maintains the performance of organ shape reconstruction by hierarchizing latent variables and enables shape representation using lower-dimensional latent variables. Additionally, templates that define vertex correspondence between different resolutions enable hierarchical representation in mesh data and control the global and local features of the organ shape. We trained the model using liver and stomach organ meshes obtained from 124 cases and confirmed that the model reconstructed the position and shape with an average distance between vertices of 1.5 mm and mean distance of 0.7 mm for the liver shape, and an average distance between vertices of 1.4 mm and mean distance of 0.8 mm for the stomach shape on test data from 19 of cases. The proposed method continuously represented interpolated shapes, and by changing latent variables at different hierarchical levels, the proposed method hierarchically separated shape features compared with PCA.
Artificial intelligence-generated content (AIGC) has shown remarkable performance in nuclear medicine imaging (NMI), offering cost-effective software solutions for tasks such as image enhancement, motion correction, and attenuation correction. However, these advancements come with the risk of hallucinations, generating realistic yet factually incorrect content. Hallucinations can misrepresent anatomical and functional information, compromising diagnostic accuracy and clinical trust. This paper presents a comprehensive perspective of hallucination-related challenges in AIGC for NMI, introducing the DREAM report, which covers recommendations for definition, representative examples, detection and evaluation metrics, underlying causes, and mitigation strategies. This position statement paper aims to initiate a common understanding for discussions and future research toward enhancing AIGC applications in NMI, thereby supporting their safe and effective deployment in clinical practice.
The development of large language models (LLMs) has entered in a experience-driven era, flagged by the emergence of environment feedback-driven learning via reinforcement learning and tool-using agents. This encourages the emergenece of model context protocol (MCP), which defines the standard on how should a LLM interact with external services, such as \api and data. However, as MCP becomes the de facto standard for LLM agent systems, it also introduces new safety risks. In particular, MCP introduces third-party services, which are not controlled by the LLM developers, into the agent systems. These third-party MCP services provider are potentially malicious and have the economic incentives to exploit vulnerabilities and sabotage user-agent interactions. In this position paper, we advocate the research community in LLM safety to pay close attention to the new safety risks issues introduced by MCP, and develop new techniques to build safe MCP-powered agent systems. To establish our position, we argue with three key parts. (1) We first construct \framework, a controlled framework to examine safety issues in MCP-powered agent systems. (2) We then conduct a series of pilot experiments to demonstrate the safety risks in MCP-powered agent systems is a real threat and its defense is not trivial. (3) Finally, we give our outlook by showing a roadmap to build safe MCP-powered agent systems. In particular, we would call for researchers to persue the following research directions: red teaming, MCP safe LLM development, MCP safety evaluation, MCP safety data accumulation, MCP service safeguard, and MCP safe ecosystem construction. We hope this position paper can raise the awareness of the research community in MCP safety and encourage more researchers to join this important research direction. Our code is available at https://github.com/littlelittlenine/SafeMCP.git.
Discrete diffusion models are a new class of text generators that offer advantages such as bidirectional context use, parallelizable generation, and flexible prompting compared to autoregressive models. However, a critical limitation of discrete diffusion models is their inability to perform flexible-length or flexible-position text infilling without access to ground-truth positional data. We introduce \textbf{DDOT} (\textbf{D}iscrete \textbf{D}iffusion with \textbf{O}ptimal \textbf{T}ransport Position Coupling), the first discrete diffusion model to overcome this challenge. DDOT jointly denoises token values and token positions, employing a novel sample-level Optimal Transport (OT) coupling. This coupling preserves relative token ordering while dynamically adjusting the positions and length of infilled segments, a capability previously missing in text diffusion. Our method is orthogonal to existing discrete text diffusion methods and is compatible with various pretrained text denoisers. Extensive experiments on text infilling benchmarks such as One-Billion-Word and Yelp demonstrate that DDOT outperforms naive diffusion baselines. Furthermore, DDOT achieves performance on par with state-of-the-art non-autoregressive models and enables significant improvements in training efficiency and flexibility.
In this paper, we consider a novel optimization design for multi-waveguide pinching-antenna systems, aiming to maximize the weighted sum rate (WSR) by jointly optimizing beamforming coefficients and antenna position. To handle the formulated non-convex problem, a gradient-based meta-learning joint optimization (GML-JO) algorithm is proposed. Specifically, the original problem is initially decomposed into two sub-problems of beamforming optimization and antenna position optimization through equivalent substitution. Then, the convex approximation methods are used to deal with the nonconvex constraints of sub-problems, and two sub-neural networks are constructed to calculate the sub-problems separately. Different from alternating optimization (AO), where two sub-problems are solved alternately and the solutions are influenced by the initial values, two sub-neural networks of proposed GML-JO with fixed channel coefficients are considered as local sub-tasks and the computation results are used to calculate the loss function of joint optimization. Finally, the parameters of sub-networks are updated using the average loss function over different sub-tasks and the solution that is robust to the initial value is obtained. Simulation results demonstrate that the proposed GML-JO algorithm achieves 5.6 bits/s/Hz WSR within 100 iterations, yielding a 32.7\% performance enhancement over conventional AO with substantially reduced computational complexity. Moreover, the proposed GML-JO algorithm is robust to different choices of initialization and yields better performance compared with the existing optimization methods.
Science progresses by iteratively advancing and correcting humanity's understanding of the world. In machine learning (ML) research, rapid advancements have led to an explosion of publications, but have also led to misleading, incorrect, flawed or perhaps even fraudulent studies being accepted and sometimes highlighted at ML conferences due to the fallibility of peer review. While such mistakes are understandable, ML conferences do not offer robust processes to help the field systematically correct when such errors are made.This position paper argues that ML conferences should establish a dedicated "Refutations and Critiques" (R & C) Track. This R & C Track would provide a high-profile, reputable platform to support vital research that critically challenges prior research, thereby fostering a dynamic self-correcting research ecosystem. We discuss key considerations including track design, review principles, potential pitfalls, and provide an illustrative example submission concerning a recent ICLR 2025 Oral. We conclude that ML conferences should create official, reputable mechanisms to help ML research self-correct.
Speaker tracking methods often rely on spatial observations to assign coherent track identities over time. This raises limits in scenarios with intermittent and moving speakers, i.e., speakers that may change position when they are inactive, thus leading to discontinuous spatial trajectories. This paper proposes to investigate the use of speaker embeddings, in a simple solution to this issue. We propose to perform identity reassignment post-tracking, using speaker embeddings. We leverage trajectory-related information provided by an initial tracking step and multichannel audio signal. Beamforming is used to enhance the signal towards the speakers' positions in order to compute speaker embeddings. These are then used to assign new track identities based on an enrollment pool. We evaluate the performance of the proposed speaker embedding-based identity reassignment method on a dataset where speakers change position during inactivity periods. Results show that it consistently improves the identity assignment performance of neural and standard tracking systems. In particular, we study the impact of beamforming and input duration for embedding extraction.
This note presents a non-associative algebraic framework for the representation and computation of information items in high-dimensional space. This framework is consistent with the principles of spatial computing and with the empirical findings in cognitive science about memory. Computations are performed through a process of multiplication-like binding and non-associative interference-like bundling. Models that rely on associative bundling typically lose order information, which necessitates the use of auxiliary order structures, such as position markers, to represent sequential information that is important for cognitive tasks. In contrast, the non-associative bundling proposed allows the construction of sparse representations of arbitrarily long sequences that maintain their temporal structure across arbitrary lengths. In this operation, noise is a constituent element of the representation of order information, rather than a means of obscuring it. The non-associative nature of the proposed framework results in the representation of a single sequence by two distinct states. The L-state, generated through left-associative bundling, continuously updates and emphasises a recency effect, while the R-state, formed through right-associative bundling, encodes finite sequences or chunks, capturing a primacy effect. The construction of these states may be associated with activity in the prefrontal cortex in relation to short-term memory and hippocampal encoding in long-term memory, respectively. The accuracy of retrieval is contingent upon a decision-making process that is based on the mutual information between the memory states and the cue. The model is able to replicate the Serial Position Curve, which reflects the empirical recency and primacy effects observed in cognitive experiments.
Since self-attention layers in Transformers are permutation invariant by design, positional encodings must be explicitly incorporated to enable spatial understanding. However, fixed-size lookup tables used in traditional learnable position embeddings (PEs) limit extrapolation capabilities beyond pre-trained sequence lengths. Expert-designed methods such as ALiBi and RoPE, mitigate this limitation but demand extensive modifications for adapting to new modalities, underscoring fundamental challenges in adaptability and scalability. In this work, we present SeqPE, a unified and fully learnable position encoding framework that represents each $n$-dimensional position index as a symbolic sequence and employs a lightweight sequential position encoder to learn their embeddings in an end-to-end manner. To regularize SeqPE's embedding space, we introduce two complementary objectives: a contrastive objective that aligns embedding distances with a predefined position-distance function, and a knowledge distillation loss that anchors out-of-distribution position embeddings to in-distribution teacher representations, further enhancing extrapolation performance. Experiments across language modeling, long-context question answering, and 2D image classification demonstrate that SeqPE not only surpasses strong baselines in perplexity, exact match (EM), and accuracy--particularly under context length extrapolation--but also enables seamless generalization to multi-dimensional inputs without requiring manual architectural redesign. We release our code, data, and checkpoints at https://github.com/ghrua/seqpe.
This paper presents the problem of tracking intermittent and moving sources, i.e, sources that may change position when they are inactive. This issue is seldom explored, and most current tracking methods rely on spatial observations for track identity management. They are either based on a previous localization step, or designed to perform joint localization and tracking by predicting ordered position estimates. This raises concerns about whether such methods can maintain reliable track identity assignment performance when dealing with discontinuous spatial tracks, which may be caused by a change of direction during silence. We introduce LibriJump, a novel dataset of acoustic scenes in the First Order Ambisonics format focusing on speaker tracking. The dataset contains speakers with changing positions during inactivity periods, thus simulating discontinuous tracks. To measure the identity assignment performance, we propose to use tracking association metrics adapted from the computer vision community. We provide experiments showing the complementarity of association metrics with previously used tracking metrics, given continuous and discontinuous spatial tracks.
While certified robustness is widely promoted as a solution to adversarial examples in Artificial Intelligence systems, significant challenges remain before these techniques can be meaningfully deployed in real-world applications. We identify critical gaps in current research, including the paradox of detection without distinction, the lack of clear criteria for practitioners to evaluate certification schemes, and the potential security risks arising from users' expectations surrounding ``guaranteed" robustness claims. This position paper is a call to arms for the certification research community, proposing concrete steps to address these fundamental challenges and advance the field toward practical applicability.
A simultaneously transmitting and reflecting surface (STARS) assisted near-field (NF) integrated sensing and communication (ISAC) framework is proposed, where the radio sensors are installed on the STARS to directly conduct the distance-domain sensing by exploiting the characteristic spherical wavefront. A new squared position error bound (SPEB) expression is derived to reveal the dependence on beamforming (BF) design and sensor deployment. To balance the trade-off between the SPEB and the sensor deployment cost, a cost function minimization problem, a cost function minimization problem is formulated to jointly optimize the sensor deployment, the active and passive BF, subject to communication and power consumption constraints. For the sensor deployment optimization, a joint sensor deployment algorithm is proposed by invoking the successive convex approximation. Under a specific relationship between the sensor numbers and BF design, we derive the optimal sensor interval in a closed-form expression. For the joint BF optimization, a penalty-based method is invoked. Simulation results validated that the derived SPEB expression is close to the exact SPEB, which reveals the Fisher information Matrix of position estimation in NF can be approximated as a diagonal matrix. Furthermore, the proposed algorithms achieve the best SPEB performance than the benchmark schemes accompanying the lowest deployment cost.
The main purpose of this paper is to generalize some recent results obtained by Chilarescu and Manuel Gomez. Essentially, we are trying to study the effect of elasticity of substitution on the parameters of economic growth, based on its two possible values - lower and higher than one. We show that a higher elasticity of substitution increases per capita income, the relative share of physical capital, the common growth rate and the share of human capital allocated to the production sector, and this property is not affected by the position of the elasticity of substitution - below or above one.
Consider a one-to-one two-sided matching market with workers on one side and single-position firms on the other, and suppose that the largest individually rational matching contains $n$ pairs. We show that the number of workers employed and positions filled in every stable matching is bounded from below by $\lceil\frac{n}{2}\rceil$ and we characterise the class of preferences that attain the bound.
Large Language Models (LLMs) are rapidly advancing across diverse domains, yet their application in theoretical physics research is not yet mature. This position paper argues that LLM agents can potentially help accelerate theoretical, computational, and applied physics when properly integrated with domain knowledge and toolbox. We analyze current LLM capabilities for physics -- from mathematical reasoning to code generation -- identifying critical gaps in physical intuition, constraint satisfaction, and reliable reasoning. We envision future physics-specialized LLMs that could handle multimodal data, propose testable hypotheses, and design experiments. Realizing this vision requires addressing fundamental challenges: ensuring physical consistency, and developing robust verification methods. We call for collaborative efforts between physics and AI communities to help advance scientific discovery in physics.