LongLive: Real-time Interactive Long Video Generation

We present LongLive, a frame-level autoregressive (AR) framework for real-time and interactive long video generation. Long video generation presents challenges in both efficiency and quality. Diffusion and Diffusion-Forcing models can produce high-quality videos but suffer from low efficiency due to bidirectional attention. Causal attention AR models support KV caching for faster inference, but often degrade in quality on long videos due to memory challenges during long-video training. In addition, beyond static prompt-based generation, interactive capabilities, such as streaming prompt inputs, are critical for dynamic content creation, enabling users to guide narratives in real time. This interactive requirement significantly increases complexity, especially in ensuring visual consistency and semantic coherence during prompt transitions. To address these challenges, LongLive adopts a causal, frame-level AR design that integrates a KV-recache mechanism that refreshes cached states with new prompts for smooth, adherent switches; streaming long tuning to enable long video training and to align training and inference (train-long-test-long); and short window attention paired with a frame-level attention sink, shorten as frame sink, preserving long-range consistency while enabling faster generation. With these key designs, LongLive fine-tunes a 1.3B-parameter short-clip model to minute-long generation in just 32 GPU-days. At inference, LongLive sustains 20.7 FPS on a single NVIDIA H100, achieves strong performance on VBench in both short and long videos. LongLive supports up to 240-second videos on a single H100 GPU. LongLive further supports INT8-quantized inference with only marginal quality loss.

MINT-RVAE: Multi-Cues Intention Prediction of Human-Robot Interaction using Human Pose and Emotion Information from RGB-only Camera Data

Efficiently detecting human intent to interact with ubiquitous robots is crucial for effective human-robot interaction (HRI) and collaboration. Over the past decade, deep learning has gained traction in this field, with most existing approaches relying on multimodal inputs, such as RGB combined with depth (RGB-D), to classify time-sequence windows of sensory data as interactive or non-interactive. In contrast, we propose a novel RGB-only pipeline for predicting human interaction intent with frame-level precision, enabling faster robot responses and improved service quality. A key challenge in intent prediction is the class imbalance inherent in real-world HRI datasets, which can hinder the model's training and generalization. To address this, we introduce MINT-RVAE, a synthetic sequence generation method, along with new loss functions and training strategies that enhance generalization on out-of-sample data. Our approach achieves state-of-the-art performance (AUROC: 0.95) outperforming prior works (AUROC: 0.90-0.912), while requiring only RGB input and supporting precise frame onset prediction. Finally, to support future research, we openly release our new dataset with frame-level labeling of human interaction intent.

Dynamic Experts Search: Enhancing Reasoning in Mixture-of-Experts LLMs at Test Time

Test-Time Scaling (TTS) enhances the reasoning ability of large language models (LLMs) by allocating additional computation during inference. However, existing approaches primarily rely on output-level sampling while overlooking the role of model architecture. In mainstream Mixture-of-Experts (MoE) LLMs, we observe that varying the number of activated experts yields complementary solution sets with stable accuracy, revealing a new and underexplored source of diversity. Motivated by this observation, we propose Dynamic Experts Search (DES), a TTS strategy that elevates expert activation into a controllable dimension of the search space. DES integrates two key components: (1) Dynamic MoE, which enables direct control of expert counts during inference to generate diverse reasoning trajectories without additional cost; and (2) Expert Configuration Inheritance, which preserves consistent expert counts within a reasoning path while varying them across runs, thereby balancing stability and diversity throughout the search. Extensive experiments across MoE architectures, verifiers and reasoning benchmarks (i.e., math, code and knowledge) demonstrate that DES reliably outperforms TTS baselines, enhancing accuracy and stability without additional cost. These results highlight DES as a practical and scalable form of architecture-aware TTS, illustrating how structural flexibility in modern LLMs can advance reasoning.

Nearly Tight Regret Bounds for Profit Maximization in Bilateral Trade

Bilateral trade models the task of intermediating between two strategic agents, a seller and a buyer, willing to trade a good for which they hold private valuations. We study this problem from the perspective of a broker, in a regret minimization framework. At each time step, a new seller and buyer arrive, and the broker has to propose a mechanism that is incentive-compatible and individually rational, with the goal of maximizing profit. We propose a learning algorithm that guarantees a nearly tight $\tilde{O}(\sqrt{T})$ regret in the stochastic setting when seller and buyer valuations are drawn i.i.d. from a fixed and possibly correlated unknown distribution. We further show that it is impossible to achieve sublinear regret in the non-stationary scenario where valuations are generated upfront by an adversary. Our ambitious benchmark for these results is the best incentive-compatible and individually rational mechanism. This separates us from previous works on efficiency maximization in bilateral trade, where the benchmark is a single number: the best fixed price in hindsight. A particular challenge we face is that uniform convergence for all mechanisms' profits is impossible. We overcome this difficulty via a careful chaining analysis that proves convergence for a provably near-optimal mechanism at (essentially) optimal rate. We further showcase the broader applicability of our techniques by providing nearly optimal results for the joint ads problem.

Metrics for Parametric Families of Networks

We introduce a general framework for analyzing data modeled as parameterized families of networks. Building on a Gromov-Wasserstein variant of optimal transport, we define a family of parameterized Gromov-Wasserstein distances for comparing such parametric data, including time-varying metric spaces induced by collective motion, temporally evolving weighted social networks, and random graph models. We establish foundational properties of these distances, showing that they subsume several existing metrics in the literature, and derive theoretical approximation guarantees. In particular, we develop computationally tractable lower bounds and relate them to graph statistics commonly used in random graph theory. Furthermore, we prove that our distances can be consistently approximated in random graph and random metric space settings via empirical estimates from generative models. Finally, we demonstrate the practical utility of our framework through a series of numerical experiments.

InfiR2: A Comprehensive FP8 Training Recipe for Reasoning-Enhanced Language Models

The immense computational cost of training Large Language Models (LLMs) presents a major barrier to innovation. While FP8 training offers a promising solution with significant theoretical efficiency gains, its widespread adoption has been hindered by the lack of a comprehensive, open-source training recipe. To bridge this gap, we introduce an end-to-end FP8 training recipe that seamlessly integrates continual pre-training and supervised fine-tuning. Our methodology employs a fine-grained, hybrid-granularity quantization strategy to maintain numerical fidelity while maximizing computational efficiency. Through extensive experiments, including the continue pre-training of models on a 160B-token corpus, we demonstrate that our recipe is not only remarkably stable but also essentially lossless, achieving performance on par with the BF16 baseline across a suite of reasoning benchmarks. Crucially, this is achieved with substantial efficiency improvements, including up to a 22% reduction in training time, a 14% decrease in peak memory usage, and a 19% increase in throughput. Our results establish FP8 as a practical and robust alternative to BF16, and we will release the accompanying code to further democratize large-scale model training.

Uncertainty-Aware Multi-Robot Task Allocation With Strongly Coupled Inter-Robot Rewards

This paper proposes a task allocation algorithm for teams of heterogeneous robots in environments with uncertain task requirements. We model these requirements as probability distributions over capabilities and use this model to allocate tasks such that robots with complementary skills naturally position near uncertain tasks, proactively mitigating task failures without wasting resources. We introduce a market-based approach that optimizes the joint team objective while explicitly capturing coupled rewards between robots, offering a polynomial-time solution in decentralized settings with strict communication assumptions. Comparative experiments against benchmark algorithms demonstrate the effectiveness of our approach and highlight the challenges of incorporating coupled rewards in a decentralized formulation.

Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator

Physics-informed graph neural networks (PIGNNs) have emerged as fast AC power-flow solvers that can replace classic Newton--Raphson (NR) solvers, especially when thousands of scenarios must be evaluated. However, current PIGNNs still need accuracy improvements at parity speed; in particular, the physics loss is inoperative at inference, which can deter operational adoption. We address this with PIGNN-Attn-LS, combining an edge-aware attention mechanism that explicitly encodes line physics via per-edge biases, capturing the grid's anisotropy, with a backtracking line-search-based globalized correction operator that restores an operative decrease criterion at inference. Training and testing use a realistic High-/Medium-Voltage scenario generator, with NR used only to construct reference states. On held-out HV cases consisting of 4--32-bus grids, PIGNN-Attn-LS achieves a test RMSE of 0.00033 p.u. in voltage and 0.08$^\circ$ in angle, outperforming the PIGNN-MLP baseline by 99.5\% and 87.1\%, respectively. With streaming micro-batches, it delivers 2--5$\times$ faster batched inference than NR on 4--1024-bus grids.

UnderwaterVLA: Dual-brain Vision-Language-Action architecture for Autonomous Underwater Navigation

This paper presents UnderwaterVLA, a novel framework for autonomous underwater navigation that integrates multimodal foundation models with embodied intelligence systems. Underwater operations remain difficult due to hydrodynamic disturbances, limited communication bandwidth, and degraded sensing in turbid waters. To address these challenges, we introduce three innovations. First, a dual-brain architecture decouples high-level mission reasoning from low-level reactive control, enabling robust operation under communication and computational constraints. Second, we apply Vision-Language-Action(VLA) models to underwater robotics for the first time, incorporating structured chain-of-thought reasoning for interpretable decision-making. Third, a hydrodynamics-informed Model Predictive Control(MPC) scheme compensates for fluid effects in real time without costly task-specific training. Experimental results in field tests show that UnderwaterVLA reduces navigation errors in degraded visual conditions while maintaining higher task completion by 19% to 27% over baseline. By minimizing reliance on underwater-specific training data and improving adaptability across environments, UnderwaterVLA provides a scalable and cost-effective path toward the next generation of intelligent AUVs.

Learning from Delayed Feedback in Games via Extra Prediction

This study raises and addresses the problem of time-delayed feedback in learning in games. Because learning in games assumes that multiple agents independently learn their strategies, a discrepancy in optimization often emerges among the agents. To overcome this discrepancy, the prediction of the future reward is incorporated into algorithms, typically known as Optimistic Follow-the-Regularized-Leader (OFTRL). However, the time delay in observing the past rewards hinders the prediction. Indeed, this study firstly proves that even a single-step delay worsens the performance of OFTRL from the aspects of regret and convergence. This study proposes the weighted OFTRL (WOFTRL), where the prediction vector of the next reward in OFTRL is weighted $n$ times. We further capture an intuition that the optimistic weight cancels out this time delay. We prove that when the optimistic weight exceeds the time delay, our WOFTRL recovers the good performances that the regret is constant ($O(1)$-regret) in general-sum normal-form games, and the strategies converge to the Nash equilibrium as a subsequence (best-iterate convergence) in poly-matrix zero-sum games. The theoretical results are supported and strengthened by our experiments.