GDEPO: Group Dual-dynamic and Equal-right-advantage Policy Optimization with Enhanced Training Data Utilization for Sample-Constrained Reinforcement Learning

Automated Theorem Proving (ATP) represents a fundamental challenge in Artificial Intelligence (AI), requiring the construction of machine-verifiable proofs in formal languages such as Lean to evaluate AI reasoning capabilities. Reinforcement learning (RL), particularly the high-performance Group Relative Policy Optimization (GRPO) algorithm, has emerged as a mainstream approach for this task. However, in ATP scenarios, GRPO faces two critical issues: when composite rewards are used, its relative advantage estimation may conflict with the binary feedback from the formal verifier; meanwhile, its static sampling strategy may discard entire batches of data if no valid proof is found, resulting in zero contribution to model updates and significant data waste. To address these limitations, we propose Group Dual-dynamic and Equal-right-advantage Policy Optimization (GDEPO), a method incorporating three core mechanisms: 1) dynamic additional sampling, which resamples invalid batches until a valid proof is discovered; 2) equal-right advantage, decoupling the sign of the advantage function (based on correctness) from its magnitude (modulated by auxiliary rewards) to ensure stable and correct policy updates; and 3) dynamic additional iterations, applying extra gradient steps to initially failed but eventually successful samples to accelerate learning on challenging cases. Experiments conducted on three datasets of varying difficulty (MinF2F-test, MathOlympiadBench, PutnamBench) confirm the effectiveness of GDEPO, while ablation studies validate the necessity of its synergistic components. The proposed method enhances data utilization and optimization efficiency, offering a novel training paradigm for ATP.

Efficient Sequential Recommendation for Long Term User Interest Via Personalization

Recent years have witnessed success of sequential modeling, generative recommender, and large language model for recommendation. Though the scaling law has been validated for sequential models, it showed inefficiency in computational capacity when considering real-world applications like recommendation, due to the non-linear(quadratic) increasing nature of the transformer model. To improve the efficiency of the sequential model, we introduced a novel approach to sequential recommendation that leverages personalization techniques to enhance efficiency and performance. Our method compresses long user interaction histories into learnable tokens, which are then combined with recent interactions to generate recommendations. This approach significantly reduces computational costs while maintaining high recommendation accuracy. Our method could be applied to existing transformer based recommendation models, e.g., HSTU and HLLM. Extensive experiments on multiple sequential models demonstrate its versatility and effectiveness. Source code is available at \href{https://github.com/facebookresearch/PerSRec}{https://github.com/facebookresearch/PerSRec}.

NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation

We present NextFlow, a unified decoder-only autoregressive transformer trained on 6 trillion interleaved text-image discrete tokens. By leveraging a unified vision representation within a unified autoregressive architecture, NextFlow natively activates multimodal understanding and generation capabilities, unlocking abilities of image editing, interleaved content and video generation. Motivated by the distinct nature of modalities - where text is strictly sequential and images are inherently hierarchical - we retain next-token prediction for text but adopt next-scale prediction for visual generation. This departs from traditional raster-scan methods, enabling the generation of 1024x1024 images in just 5 seconds - orders of magnitude faster than comparable AR models. We address the instabilities of multi-scale generation through a robust training recipe. Furthermore, we introduce a prefix-tuning strategy for reinforcement learning. Experiments demonstrate that NextFlow achieves state-of-the-art performance among unified models and rivals specialized diffusion baselines in visual quality.

Hear the Heartbeat in Phases: Physiologically Grounded Phase-Aware ECG Biometrics

Electrocardiography (ECG) is adopted for identity authentication in wearable devices due to its individual-specific characteristics and inherent liveness. However, existing methods often treat heartbeats as homogeneous signals, overlooking the phase-specific characteristics within the cardiac cycle. To address this, we propose a Hierarchical Phase-Aware Fusion~(HPAF) framework that explicitly avoids cross-feature entanglement through a three-stage design. In the first stage, Intra-Phase Representation (IPR) independently extracts representations for each cardiac phase, ensuring that phase-specific morphological and variation cues are preserved without interference from other phases. In the second stage, Phase-Grouped Hierarchical Fusion (PGHF) aggregates physiologically related phases in a structured manner, enabling reliable integration of complementary phase information. In the final stage, Global Representation Fusion (GRF) further combines the grouped representations and adaptively balances their contributions to produce a unified and discriminative identity representation. Moreover, considering ECG signals are continuously acquired, multiple heartbeats can be collected for each individual. We propose a Heartbeat-Aware Multi-prototype (HAM) enrollment strategy, which constructs a multi-prototype gallery template set to reduce the impact of heartbeat-specific noise and variability. Extensive experiments on three public datasets demonstrate that HPAF achieves state-of-the-art results in the comparison with other methods under both closed and open-set settings.

Many Minds from One Model: Bayesian Transformers for Population Intelligence

Despite their scale and success, modern transformers are almost universally trained as single-minded systems: optimization produces one deterministic set of parameters, representing a single functional hypothesis about the data. Motivated by the idea that intelligence emerge from many minds, we propose Population Bayesian Transformers (B-Trans), which transform a standard Large Language Model into a Bayesian Transformer model to supports sampling diverse yet coherent model instances from a single set of pre-trained weights. B-Trans introduces a Bayesian-motivated posterior proxy by treating the bias-like offsets in normalization layers as stochastic variables with a Gaussian variational approximation, inducing a distribution over model behavior without the cost of training full Bayesian neural networks. Sampling from this proxy yields a set of model instances with diverse behaviors while maintaining general competence. To preserve coherence within each generation, we freeze the sampled noise at the sequence level, enforcing temporal consistency across tokens. B-Trans allows for population-level decision-making, where aggregating predictions across sampled individuals significantly enhances exploration. Experiments across zero-shot generation, Reinforcement Learning with Verifiable Rewards (RLVR), and RL without explicit labels demonstrate that B-Trans effectively leverage the wisdom of crowds, yielding superior semantic diversity while achieving better task performance compared to deterministic baselines.

GVSynergy-Det: Synergistic Gaussian-Voxel Representations for Multi-View 3D Object Detection

Image-based 3D object detection aims to identify and localize objects in 3D space using only RGB images, eliminating the need for expensive depth sensors required by point cloud-based methods. Existing image-based approaches face two critical challenges: methods achieving high accuracy typically require dense 3D supervision, while those operating without such supervision struggle to extract accurate geometry from images alone. In this paper, we present GVSynergy-Det, a novel framework that enhances 3D detection through synergistic Gaussian-Voxel representation learning. Our key insight is that continuous Gaussian and discrete voxel representations capture complementary geometric information: Gaussians excel at modeling fine-grained surface details while voxels provide structured spatial context. We introduce a dual-representation architecture that: 1) adapts generalizable Gaussian Splatting to extract complementary geometric features for detection tasks, and 2) develops a cross-representation enhancement mechanism that enriches voxel features with geometric details from Gaussian fields. Unlike previous methods that either rely on time-consuming per-scene optimization or utilize Gaussian representations solely for depth regularization, our synergistic strategy directly leverages features from both representations through learnable integration, enabling more accurate object localization. Extensive experiments demonstrate that GVSynergy-Det achieves state-of-the-art results on challenging indoor benchmarks, significantly outperforming existing methods on both ScanNetV2 and ARKitScenes datasets, all without requiring any depth or dense 3D geometry supervision (e.g., point clouds or TSDF).

ReasonCD: A Multimodal Reasoning Large Model for Implicit Change-of-Interest Semantic Mining

Remote sensing image change detection is one of the fundamental tasks in remote sensing intelligent interpretation. Its core objective is to identify changes within change regions of interest (CRoI). Current multimodal large models encode rich human semantic knowledge, which is utilized for guidance in tasks such as remote sensing change detection. However, existing methods that use semantic guidance for detecting users' CRoI overly rely on explicit textual descriptions of CRoI, leading to the problem of near-complete performance failure when presented with implicit CRoI textual descriptions. This paper proposes a multimodal reasoning change detection model named ReasonCD, capable of mining users' implicit task intent. The model leverages the powerful reasoning capabilities of pre-trained large language models to mine users' implicit task intents and subsequently obtains different change detection results based on these intents. Experiments on public datasets demonstrate that the model achieves excellent change detection performance, with an F1 score of 92.1\% on the BCDD dataset. Furthermore, to validate its superior reasoning functionality, this paper annotates a subset of reasoning data based on the SECOND dataset. Experimental results show that the model not only excels at basic reasoning-based change detection tasks but can also explain the reasoning process to aid human decision-making.

VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference

This paper presents VLCache, a cache reuse framework that exploits both Key-Value (KV) cache and encoder cache from prior multimodal inputs to eliminate costly recomputation when the same multimodal inputs recur. Unlike previous heuristic approaches, we formally identify the cumulative reuse error effect and demonstrate how to minimize the non-prefix cache reuse error effectively. We further analyze the varying importance of model layers and propose a dynamic, layer-aware recomputation strategy to balance accuracy and efficiency. Experimental results show that VLCache achieves an accuracy on par with full recomputation, while requiring only 2-5% of the tokens to compute, yielding 1.2x-16x TTFT speedups. We develop an experimental implementation of the proposed VLCache pipeline based on SGLang, enabling significantly faster inference in practical deployments.

Null-LoRA: Low-Rank Adaptation on Null Space

Parameter-efficient fine-tuning methods have gained considerable popularity for adapting large-scale models to downstream tasks, particularly LoRA and its variants. Existing methods perform low-rank adaptation over the full parameter space. However, fine-tuning within a subspace can achieve comparable effectiveness. Inspired by the observation that pre-trained models possess non-trivial null spaces, we propose Null-space based Low-Rank Adaptation (Null-LoRA). Null-LoRA effectively reduces redundancy and enhances effective rank by freezing portions of the low-rank matrices. To further improve parameter efficiency, Null-LoRA constrains the entire incremental update within the null space, maximizing the utilization of incremental updates to adapt to new task paradigms. Null-LoRA surpasses the state of the art with fewer parameters in extensive experiments across image-text retrieval and visual question answering tasks.

Progressive Conditioned Scale-Shift Recalibration of Self-Attention for Online Test-time Adaptation

Online test-time adaptation aims to dynamically adjust a network model in real-time based on sequential input samples during the inference stage. In this work, we find that, when applying a transformer network model to a new target domain, the Query, Key, and Value features of its self-attention module often change significantly from those in the source domain, leading to substantial performance degradation of the transformer model. To address this important issue, we propose to develop a new approach to progressively recalibrate the self-attention at each layer using a local linear transform parameterized by conditioned scale and shift factors. We consider the online model adaptation from the source domain to the target domain as a progressive domain shift separation process. At each transformer network layer, we learn a Domain Separation Network to extract the domain shift feature, which is used to predict the scale and shift parameters for self-attention recalibration using a Factor Generator Network. These two lightweight networks are adapted online during inference. Experimental results on benchmark datasets demonstrate that the proposed progressive conditioned scale-shift recalibration (PCSR) method is able to significantly improve the online test-time domain adaptation performance by a large margin of up to 3.9\% in classification accuracy on the ImageNet-C dataset.