论文检索

Reinforcement Learning · Online

Zhibo Hou, Zhiyu An, Wan Du

When there exists an unlearnable source of randomness (noisy-TV) in the environment, a naively intrinsic reward driven exploring agent gets stuck at that source of randomness and fails at exploration. Intrinsic reward based on uncertainty estimation or distribution similarity, while eventually escapes noisy-TVs as time unfolds, suffers from poor sample efficiency and high computational cost. Inspired by recent findings from neuroscience that humans monitor their improvements during exploration, we propose a novel method for intrinsically-motivated exploration, named Learning Progress Monitoring (LPM). During exploration, LPM rewards model improvements instead of prediction error or novelty, effectively rewards the agent for observing learnable transitions rather than the unlearnable transitions. We introduce a dual-network design that uses an error model to predict the expected prediction error of the dynamics model in its previous iteration, and use the difference between the model errors of the current iteration and previous iteration to guide exploration. We theoretically show that the intrinsic reward of LPM is zero-equivariant and a monotone indicator of Information Gain (IG), and that the error model is necessary to achieve monotonicity correspondence with IG. We empirically compared LPM against state-of-the-art baselines in noisy environments based on MNIST, 3D maze with 160x120 RGB inputs, and Atari. Results show that LPM's intrinsic reward converges faster, explores more states in the maze experiment, and achieves higher extrinsic reward in Atari. This conceptually simple approach marks a shift-of-paradigm of noise-robust exploration.

Applications · Physics

Nan Jiang, Ziyi Wang, Yexiang Xue

Symbolic regression seeks to uncover physical laws from experimental data by searching for closed-form expressions, which is an important task in AI-driven scientific discovery. Yet the exponential growth of the search space of expression renders the task computationally challenging. A promising yet underexplored direction for reducing the search space and accelerating training lies in *symbolic equivalence*: many expressions, although syntactically different, define the same function -- for example, $\log(x_1^2x_2^3)$, $\log(x_1^2)+\log(x_2^3)$, and $2\log(x_1)+3\log(x_2)$. Existing algorithms treat such variants as distinct outputs, leading to redundant exploration and slow learning. We introduce EGG-SR, a unified framework that integrates symbolic equivalence into a class of modern symbolic regression methods, including Monte Carlo Tree Search (MCTS), Deep Reinforcement Learning (DRL), and Large Language Models (LLMs). \method-SR compactly represents equivalent expressions through the proposed EGG module (via equality graphs), accelerating learning by: (1) pruning redundant subtree exploration in EGG-MCTS, (2) aggregating rewards across equivalent generated sequences in EGG-DRL, and (3) enriching feedback prompts in EGG-LLM. Theoretically, we show the benefit of embedding EGG into learning: it tightens the regret bound of MCTS and reduces the variance of the DRL gradient estimator. Empirically, EGG-SR consistently enhances a class of symbolic regression models across several benchmarks, discovering more accurate expressions within the same time limit. Project page is at: https://nan-jiang-group.github.io/egg-sr.

Deep Learning · Theory

Noam Razin, Yong Lin, Jiarui Yao, Sanjeev Arora

Reward models are key to language model post-training and inference pipelines. Conveniently, recent work showed that every language model defines an implicit reward model (IM-RM), without requiring any architectural changes. However, such IM-RMs tend to generalize worse, especially out-of-distribution, compared to explicit reward models (EX-RMs) that apply a dedicated linear head over the hidden representations of a language model. The existence of a generalization gap is puzzling, as EX-RMs and IM-RMs are nearly identical. They can be trained using the same data, loss function, and language model, and differ only in how the reward is computed. Toward a fundamental understanding of the implicit biases underlying different reward model types, we investigate the root cause of this gap. Our main finding, backed by theory and experiments, is that IM-RMs rely more heavily on superficial token-level cues. Consequently, they often generalize worse than EX-RMs under token-level distribution shifts, as well as in-distribution. Furthermore, we provide evidence against alternative hypotheses for the generalization gap. Most notably, we challenge the claim that IM-RMs struggle in tasks where generation is harder than verification because they can operate both as a verifier and a generator. Overall, our results highlight that seemingly minor design choices can substantially impact the generalization behavior of reward models.

Computer Vision · Image and Video Generation

Yuran Dong, Hang Dai, Mang Ye

Multimodal editing large models have demonstrated powerful editing capabilities across diverse tasks. However, a persistent and long-standing limitation is the decline in facial identity (ID) consistency during realistic portrait editing. Due to the human eye’s high sensitivity to facial features, such inconsistency significantly hinders the practical deployment of these models. Current facial ID preservation methods struggle to achieve consistent restoration of both facial identity and edited element IP due to Cross-source Distribution Bias and Cross-source Feature Contamination. To address these issues, we propose EditedID, an Alignment-Disentanglement-Entanglement framework for robust identity-specific facial restoration. By systematically analyzing diffusion trajectories, sampler behaviors, and attention properties, we introduce three key components: 1) Adaptive mixing strategy that aligns cross-source latent representations throughout the diffusion process. 2) Hybrid solver that disentangles source-specific identity attributes and details. 3) Attentional gating mechanism that selectively entangles visual elements. Extensive experiments show that EditedID achieves state-of-the-art performance in preserving original facial ID and edited element IP consistency. As a training-free and plug-and-play solution, it establishes a new benchmark for practical and reliable single/multi-person facial identity restoration in open-world settings, paving the way for the deployment of multimodal editing large models in real-person editing scenarios. The code is available at https://github.com/NDYBSNDY/EditedID.

Weilin Zhou

State-of-the-art models for code representation, such as GraphCodeBERT, embed the hierarchical structure of source code into Euclidean space. This approach can lead to significant representation distortion, especially when embedding deep or highly branched hierarchies,limiting the models' ability to capture deep program semantics. We argue that the natural geometry for code is hyperbolic, as its exponential volume growth perfectly matches the tree-like structure of a code's Abstract Syntax Tree (AST), enabling low-distortion hierarchical embeddings. We introduce {HypeCodeNet}, a geometric deep learning framework that operates natively in hyperbolic space. Formulated in the numerically stable Lorentz model, its manifold-aware components include a hyperbolic embedding layer, a tangent space message-passing mechanism, and a geodesic-based attention module. On code clone detection, code completion, and link prediction, HypeCodeNet significantly outperforms existing Euclidean models, especially on tasks requiring deep structural understanding. Our work suggests that hyperbolic geometry offers a geometrically sound foundation for code representation, establishing hyperbolic geometry as a key to unlocking the structured semantics of code.

Computer Vision · Image and Video Generation

Kaiyi Huang, Yukun Huang, Xintao WANG, Zinan Lin, Xuefei Ning, Pengfei Wan, Di ZHANG, Yu Wang, Xihui Liu

Existing AI-based film generation systems can generate high-quality videos, but struggle to design expressive camera language and establish cinematic rhythm. This deficiency leads to templated visuals and unengaging narratives. To address these limitations, we introduce FilMaster, an end-to-end automated film generation system that integrates real-world cinematic principles to generate professional-grade, editable films. Inspired by professional filmmaking, FilMaster is built on two key cinematic principles: (1) camera language design by learning cinematography from extensive real-world film references, and (2) cinematic rhythm by emulating professional post-production workflows. For camera language, our Multi-shot Synergized Camera Language Design module introduces a novel scene-level Retrieval-Augmented Generation (RAG) framework. Unlike shot-level RAG which retrieves references independently and often leads to visual incoherence, our approach treats an entire scene, comprising multiple shots with a shared spatio-temporal context and narrative objective, as a single, unified query. This holistic query retrieves a consistent set of semantically similar shots with cinematic techniques from a large corpus of 440,000 real film clips. These references then guide an LLM to synergistically plan coherent and expressive camera language for all shots within that scene. To achieve cinematic rhythm, our Audience-Aware Cinematic Rhythm Control module emulates professional post-production, featuring a Rough Cut assembly followed by a Fine Cut process that uses simulated audience feedback to optimize the integration of video and sound for cinematic rhythm. Extensive experiments show superior performance in camera language and cinematic rhythm, paving the way for generative AI in professional filmmaking.

General Machine Learning · Representation Learning

Junyi Lin, Dunyao Xue, Jun Yu, Hongteng Xu, Cheng Meng

We introduce SEINT, a novel Special Euclidean group-Invariant (SE(\emph{p})) metric for comparing probability distributions on $p$-dimensional measured Banach spaces. Existing SE(\emph{p})-invariant alignment methods often face high computational costs or lack metric guarantees. To overcome these limitations, we develop a polar transport discrepancy combined with distance convolution to extract SE(\emph{p})-invariant representations. These representations are then used to compute the alignment between two distributions via optimal transport. Theoretically, we prove that SEINT is a well-defined metric on the space of isometry classes of normed vector spaces. Beyond its inherent SE(\emph{p})-invariance, SEINT also supports cross-space distribution comparison. Computationally, SEINT aligns two samples of size $n$ with a complexity of just $\mathcal{O}(n\log n)$ to $\mathcal{O}(n^2)$. Extensive experiments validate its advantages: As a robust metric, it outperforms or matches existing SE(\emph{p})-invariant methods in classification and cross-space tasks under isometries. As a regularizer, it greatly enhances molecular generation performance across both pre-training and fine-tuning tasks, achieving state-of-the-art (SOTA) results on key benchmarks.

Computer Vision · Vision Models & Multimodal

Ziyue Wang, Sheng JIn, ZHONGRONG ZUO, Jiawei Wu, Han Qiu, Qi She, Hao Zhang, Jiang Xudong

Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models (MLLMs), yet existing video reasoning methods often rely on coarse sequence-level rewards or single-factor token selection. Such approaches neglect fine-grained links among visual inputs, temporal dynamics, and linguistic outputs, limiting both accuracy and interpretability. We propose Video-KTR, a modality-aware policy shaping framework that performs selective, token-level RL by combining three attribution signals: (1) visual-aware tokens identified via counterfactual masking to reveal perceptual dependence; (2) temporal-aware tokens detected through frame shuffling to expose causal and temporal sensitivity; and (3) high-entropy tokens signaling predictive uncertainty. By reinforcing only the union of key tokens, Video-KTR focuses learning on semantically informative, modality-sensitive content while filtering out low-value tokens. Across five challenging benchmarks, Video-KTR achieves state-of-the-art or highly competitive results—42.7% on Video-Holmes, surpassing GPT-4o—with consistent gains on both reasoning-centric and general video understanding tasks. Ablation studies verify the complementary roles of the attribution signals and the robustness of targeted token-level updates. Overall, Video-KTR improves accuracy and interpretability, offering a simple, drop-in extension to RL for complex video reasoning.

General Machine Learning · Probabilistic Methods

Zifan Wang, Alice Harting, Matthieu Barreau, Michael Zavlanos, Karl H. Johansson

Guidance of generative models is typically achieved by modifying the probability flow vector field through the addition of a guidance field. In this paper, we instead propose the Source-Guided Flow Matching (SGFM) framework, which modifies the source distribution directly while keeping the pre-trained vector field intact. This reduces the guidance problem to a well-defined problem of sampling from the source distribution. We theoretically show that SGFM recovers the desired target distribution exactly. Furthermore, we provide bounds on the Wasserstein error for the generated distribution when using an approximate sampler of the source distribution and an approximate vector field. The key benefit of our approach is that it allows the user to flexibly choose the sampling method depending on their specific problem. To illustrate this, we systematically compare different sampling methods and discuss conditions for asymptotically exact guidance. Moreover, our framework integrates well with optimal flow matching models since the straight transport map generated by the vector field is preserved. Experimental results on synthetic 2D benchmarks, physics-informed generative tasks, and imaging inverse problems demonstrate the effectiveness and flexibility of the proposed framework.

General Machine Learning · Probabilistic Methods

Bruno Viti, Elias Karabelas, Martin Holler

Most machine learning-based image segmentation models produce pixel-wise confidence scores that represent the model’s predicted probability for each class label at every pixel. While this information can be particularly valuable in high-stakes domains such as medical imaging, these scores are heuristic in nature and do not constitute rigorous quantitative uncertainty estimates. Conformal prediction (CP) provides a principled framework for transforming heuristic confidence scores into statistically valid uncertainty estimates. However, applying CP directly to image segmentation ignores the spatial correlations between pixels, a fundamental characteristic of image data. This can result in overly conservative and less interpretable uncertainty estimates. To address this, we propose CONSIGN (*Conformal Segmentation Informed by Spatial Groupings via Decomposition*), a CP-based method that incorporates spatial correlations to improve uncertainty quantification in image segmentation. Our method generates meaningful prediction sets that come with user-specified, high-probability error guarantees. It is compatible with any pre-trained segmentation model capable of generating multiple sample outputs. We evaluate CONSIGN against two CP baselines across three medical imaging datasets and two COCO dataset subsets, using three different pre-trained segmentation models. Results demonstrate that accounting for spatial structure significantly improves performance across multiple metrics and enhances the quality of uncertainty estimates.

Computer Vision · Vision Models & Multimodal

Haozhe Qi, Shaokai Ye, Alexander Mathis, Mackenzie Mathis

Understanding human behavior requires measuring behavioral actions. Due to its complexity, behavior is best mapped onto a rich, semantic structure such as language. Emerging multimodal large language models (MLLMs) are promising candidates, but their fine-grained action understanding ability has not been fully examined. In this work, we reformulate EPIC-KITCHENS-100, one of the largest and most challenging egocentric action recognition datasets, into a MLLM benchmark (EPIC-KITCHENS-100-MQA). We demonstrate that when we sample difficult answers based on specialist models as distractors, leading MLLMs struggle to recognize the correct actions. How can we increase the performance of MLLMs? We curated a supervised finetuning dataset that includes `hard' action recognition, temporal detection, captioning, and free-form question answering to improve models' diverse action understanding capabilities. We introduce a new model called LLaVAction that adds an action token to boost models' attention on visual tokens and a two-stage pipeline to obtain structured actions. LLaVAction greatly improves the MLLMs' ability of action understanding, achieving strong improvements on both MLLM benchmarks (21 points in accuracy over GPT-4o on EPIC-KITCHENS-100-MQA) and established action recognition benchmarks, suggesting that our methods prepare MLLMs to be a promising path forward for complex action tasks. Code, data, the benchmark, and models are available at https://github.com/AdaptiveMotorControlLab/LLaVAction.

Jenny Zhang, Shengran Hu, Cong Lu, Robert Lange, Jeff Clune

Most of today's AI systems are constrained by human-designed, fixed architectures and cannot autonomously and continuously improve themselves. The scientific method, on the other hand, is a cumulative and open-ended system, where each innovation builds upon previous artifacts, enabling future discoveries. There is growing hope that the current manual process of advancing AI could itself be automated. If done safely, such automation would accelerate AI development and allow us to reap its benefits much sooner. This prospect raises the question of how AI systems can endlessly improve themselves while getting better at solving relevant problems. Meta-learning can automate the discovery of novel algorithms, but is limited by first-order improvements and the human design of a suitable search space. The Gödel machine proposed a theoretical alternative: a self-improving AI that repeatedly modifies itself in a provably beneficial manner. Unfortunately, proving that most changes are net beneficial is impossible in practice. We introduce the Darwin Gödel Machine (DGM), a novel self-improving system that iteratively modifies its own code (thereby also improving its ability to modify its own codebase) and empirically validates each change using coding benchmarks. Inspired by Darwinian evolution and open-endedness research, the DGM grows an archive of generated coding agents. It samples agents from this archive, which self-modify to create new, interesting versions of themselves. This open-ended exploration forms a growing tree of diverse, high-quality agents and allows the parallel exploration of many different paths through the search space. Empirically, the DGM automatically improves its coding capabilities (e.g., better code editing tools, long-context window management, peer-review mechanisms), increasing performance on SWE-bench from 20.0% to 50.0%, and on Polyglot from 14.2% to 30.7%. Furthermore, the DGM significantly outperforms baselines without self-improvement or open-ended exploration. All experiments were done with safety precautions (e.g., sandboxing, human oversight). Overall, the DGM represents a significant step toward self-improving AI, capable of gathering its own stepping stones along a path that unfolds into endless innovation.

Theory · Reinforcement Learning and Planning

Bowen Hu, Yixin Tao

We study a principal-agent problem in a Markov Decision Process where the principal provides subsidies to influence the agent's policy, which in turn determines the accrued rewards. Our focus is on designing a robust subsidy scheme that maximizes the principal’s cumulative expected return, even when the agent displays bounded rationality and may deviate from the optimal action policy after receiving subsidies. As a baseline, we first analyze the case of a perfectly rational agent and show that the principal’s optimal subsidy coincides with the policy that maximizes social welfare, the sum of the utilities of both the principal and the agent. We then introduce a bounded-rationality model: the globally $\epsilon$-incentive-compatible agent, who accepts any policy whose expected cumulative utility lies within $\epsilon$ of the personal optimum. In this setting, we prove that the optimal robust subsidy scheme problem simplifies to a one-dimensional concave optimization, revealing that optimal subsidies concentrate along social-welfare-maximizing trajectories. We also bound the associated loss in social welfare. Finally, we investigate a finer-grained, state-wise $\epsilon$-incentive-compatible model. In this setting, we show that under two natural definitions of state-wise incentive-compatibility, the problem becomes intractable: one definition results in a non-Markovian agent action policy, while the other renders the search for an optimal subsidy scheme NP-hard.

Reinforcement Learning · Planning

Shenghua Wan, Le Gan, De-Chuan Zhan

Pre-training world models on large, action-free video datasets offers a promising path toward generalist agents, but a fundamental flaw undermines this paradigm. Prevailing methods train models to predict a single, deterministic future, an objective that is ill-posed for inherently stochastic environments where actions are unknown. We contend that a world model should instead learn a structured, probabilistic representation of the future where predictive uncertainty correctly scales with the temporal horizon. To achieve this, we introduce a pre-training framework, **H**orizon-c**A**librated **U**ncertainty **W**orld **M**odel (HAUWM), built on a probabilistic ensemble that predicts frames at randomly sampled future horizons. The core of our method is a Horizon-Calibrated Uncertainty (HCU) loss, which explicitly shapes the latent space by encouraging predictive variance to grow as the model projects further into the future. This approach yields a latent dynamics model that is not only predictive but also equipped with a reliable measure of temporal confidence. When fine-tuned for downstream control, our pre-trained model significantly outperforms state-of-the-art methods across a diverse suite of benchmarks, including MetaWorld, the DeepMind Control Suite, and RoboDesk. These results highlight the critical role of structured uncertainty in robust decision-making.

General Machine Learning · Representation Learning

Junlin Han, Shengbang Tong, David Fan, Yufan Ren, Koustuv Sinha, Philip Torr, Filippos Kokkinos

Large Language Models (LLMs), despite being trained on text alone, surprisingly develop rich visual priors. These priors allow latent visual capabilities to be unlocked for vision tasks with a relatively small amount of multimodal data, and to perform symbolic visual generation tasks without ever having seen an image. Through systematic analysis, we reveal that visual priors—the implicit, emergent knowledge about the visual world acquired during language pre-training—are composed of separable perception and reasoning priors with unique scaling trends and origins. We show that an LLM's latent visual reasoning ability is predominantly developed by pre-training on reasoning-centric data (\eg, code, math, academia) and scales progressively. This reasoning prior acquired from language pre-training is transferable and universally applicable to visual reasoning. In contrast, the perception prior emerges more diffusely from broad corpora, and perception ability is more sensitive to the vision encoder and visual instruction tuning data. In parallel, text describing the visual world proves crucial, though its performance impact saturates rapidly. Leveraging these insights, we propose a data-centric recipe for pre-training vision-aware LLMs and verify it in 1T token scale pre-training. Our findings are grounded in over 100 controlled experiments consuming 500,000 GPU-hours, spanning the full MLLM construction pipeline—from LLM pre-training to visual alignment and supervised multimodal fine-tuning—across five model scales, a wide range of data categories and mixtures, and multiple adaptation setups. Along with our main findings, we also propose and investigate several hypotheses, and introduce a Multi-Level Existence Bench (MLE-Bench) to facilitate future research. Together, this work provides a new way of deliberately cultivating visual priors from language pre-training, paving the way for the next generation of multimodal LLMs. We recommend a visit to our project page (https://junlinhan.github.io/projects/lsbs/) for an interactive reading.

Reinforcement Learning · Everything Else

Zequan Wu, Mengye Ren

The Forward-Forward (FF) Algorithm is a recently proposed learning procedure for neural networks that employs two forward passes instead of the traditional forward and backward passes used in backpropagation. However, FF remains largely confined to supervised settings, leaving a gap at domains where learning signals can be yielded more naturally such as RL. In this work, inspired by FF's goodness function using layer activity statistics, we introduce Action-conditioned Root mean squared Q-Functions (ARQ), a novel value estimation method that applies a goodness function and action conditioning for local RL using temporal difference learning. Despite its simplicity and biological grounding, our approach achieves superior performance compared to state-of-the-art local backprop-free RL methods in the MinAtar and the DeepMind Control Suite benchmarks, while also outperforming algorithms trained with backpropagation on most tasks.

Optimization · Everything Else

Ruobing Wang, Xin Li, Mingzhong Wang

We propose MILPnet, a multi-scale hybrid attention framework that models Mixed Integer Linear Programming (MILP) problems as geometric sequences rather than graphs. This approach directly addresses the challenge of Foldable MILP instances, a class of problems that graph-based models, specifically Graph Neural Networks (GNNs), fail to distinguish due to expressiveness limits imposed by the Weisfeiler-Lehman test. By representing MILPs through sequences of constraint and objective features, MILPnet captures both local and global geometric structure using a theoretically grounded multi-scale attention mechanism. We theoretically prove that MILPnet can approximate feasibility, optimal objective value, and optimal solution mappings over a measurable topological space with arbitrarily small error. Empirically, MILPnet outperforms graph-based methods in feasibility prediction accuracy and convergence speed on Foldable MILPs, while using significantly fewer parameters. It also generalizes effectively among problem scales and demonstrates strong performance on real-world MILP benchmarks when integrated into an end-to-end solver pipeline. Our code is available.

Deep Learning · Everything Else

Xiaoyang Yi, Li Peng, Yuru Bao, Jian Zhang

Federated learning (FL), as a privacy-preserving distributed machine learning paradigm, enables clients to collaboratively train a global model without sharing local data. However, in real-world scenarios, domain shift caused by different source clients leads to structural discrepancies in the feature space, resulting in performance degradation of the global model. Although existing prototype-based FL methods offer improvements in cross-domain feature alignment, they still struggle to adapt to dynamic semantic structures and fail to continuously respond to the changing semantic separability and variance structure during training. To address this, we propose FedPTE, an FL framework with prototype topology evolution. Specifically, FedPTE treats prototype clusters as variable topological units, employing Bayesian Gaussian Mixture Models and marginal likelihood ratios on the server to perform probabilistic inference, which enables adaptive structural adjustments. Meanwhile, FedPTE introduces a stability constraint mechanism to balance the adaptability of topological evolution and training stability. By conducting prototype topology-aware contrastive learning on clients, it enhances the discriminability and cross-domain consistency of features. Experimental results demonstrate that FedPTE achieves superior performance across multiple cross-domain datasets, showcasing its strong expressiveness and generalization capability in heterogeneous domains.

Computer Vision · Image and Video Generation

Ji Xie, trevor darrell, Luke Zettlemoyer, Xudong Wang

Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture. However, conventional training relies on image–text pairs (or sequences) whose captions are typically sparse and miss fine-grained visual details, even when they use hundreds of words to describe a simple image. We introduce **Reconstruction Alignment (RecA)**, a resource-efficient post-training method that leverages visual understanding encoder embeddings as dense “text prompts,” providing rich supervision without captions. Concretely, RecA conditions a UMM on its own visual understanding embeddings and optimizes it to reconstruct the input image with a self-supervised reconstruction loss, thereby realigning understanding and generation. Despite its simplicity, RecA is broadly applicable: across autoregressive, masked-autoregressive, and diffusion-based UMMs, it consistently improves generation and editing fidelity. With only 27 GPU-hours, post-training with RecA substantially improves image generation performance on GenEval (0.73 → 0.90) and DPGBench (80.93 → 88.15), while also boosting editing benchmarks (ImgEdit 3.38 → 3.75, GEdit 6.94 → 7.27). Notably, RecA surpasses much larger open-source models and applies broadly across diverse UMM architectures, establishing it as an efficient and general post-training alignment strategy for UMMs.

Computer Vision · Image and Video Generation

Xinya Ji, Sebastian Weiss, Manuel Kansy, Jacek Naruniec, Xun Cao, Barbara Solenthaler, Derek Bradley

Despite recent progress in 3D Gaussian-based head avatar modeling, efficiently generating high fidelity avatars remains a challenge. Current methods typically rely on extensive multi-view capture setups or monocular videos with per-identity optimization during inference, limiting their scalability and ease of use on unseen subjects. To overcome these efficiency drawbacks, we propose FastGHA, a feed-forward method to generate high-quality Gaussian head avatars from only a few input images while supporting real-time animation. Our approach directly learns a per-pixel Gaussian representation from the input images, and aggregates multi-view information using a transformer-based encoder that fuses image features from both DINOv3 and Stable Diffusion VAE. For real-time animation, we extend the explicit Gaussian representations with per-Gaussian features and introduce a lightweight MLP-based dynamic network to predict 3D Gaussian deformations from expression codes. Furthermore, to enhance geometric smoothness of the 3D head, we employ point maps from a pre-trained large reconstruction model as geometry supervision. Experiments show that our approach significantly outperforms existing methods in both rendering quality and inference efficiency, while supporting real-time dynamic avatar animation.