AAblation Study1 We conduct ablation studies to evaluate three key design choices in PosterAgent: (1) the binary-tree2 layout strategy for layout planning; (2) the inclusion of a commenter module as a visual critic; and3 (3) the use of in-context examples to enhance the visual perception capabilities of the commenter.4 We define the following variants:5 Direct: replacing the binary-tree layout with direct layout generation by an LLM;6 Tree: using the binary-tree layout strategy but removing the commenter module;7 Tree + Commenter: including the commenter module but without in-context examples;8 Tree + Commenter + IC: the full system, with both the commenter and in-context examples.9 All ablation variants are implemented using PosterAgent-4o, keeping all other components un-10 changed to isolate the effect of each factor. We visualize and compare results across five randomly11 selected papers from Paper2Poster, as shown in Figures 1 to 5.12 When prompting the LLM to directly generate poster layouts (Direct), the results are often structurally13 compromised (e.g., Figures 1a-3a), or resemble blog-style layouts that lack visual hierarchy and14 appeal (Figures 4a,5a). Fine-grained layout components, such as text boxes and figures, are especially15 challenging to synthesize in this setting: for instance, Figures1a-4a exhibit missing text boxes that16 leave noticeable blank areas, and Figure 4a fails to preserve the correct aspect ratio of figures.17

Academic poster generation is a crucial yet challenging task in scientific communication, requiring the compression of long-context interleaved documents into a single, visually coherent page. To address this challenge, we introduce the first benchmark and metric suite for poster generation, which pairs recent conference papers with author-designed posters and evaluates outputs on (i) Visual Quality--semantic alignment with human posters, (ii) Textual Coherence--language fluency, (iii) Holistic Assessment--six fine-grained aesthetic and informational criteria scored by a VLM-as-judge, and notably (iv) PaperQuiz--the poster's ability to convey core paper content as measured by VLMs answering generated quizzes. Building on this benchmark, we propose PosterAgent, a top-down, visualin-the-loop multi-agent pipeline: the (a) Parser distills the paper into a structured asset library; the (b) Planner aligns text-visual pairs into a binary-tree layout that preserves reading order and spatial balance; and the (c) Painter-Commenter loop refines each panel by executing rendering code and using VLM feedback to eliminate overflow and ensure alignment. In our comprehensive evaluation, we find that GPT-4o outputs--though visually appealing at first glance--often exhibit noisy text and poor PaperQuiz scores, and we find that reader engagement is the primary aesthetic bottleneck, as human-designed posters rely largely on visual semantics to convey meaning. Our fully open-source variants (e.g., based on the Qwen-2.5 series) outperform existing 4o-driven multi-agent systems across nearly all metrics, while using 87%fewer tokens. It transforms a 22-page paper into a finalized yet editable '.pptx' poster -- all for just $0.005. These findings chart clear directions for the next generation of fully automated poster-generation models.

Model fusion combines multiple Large Language Models (LLMs) with different strengths into a more powerful, integrated model through lightweight training methods.

Discrete diffusion models enable parallel token sampling for faster inference than autoregressive approaches. However, prior diffusion models use a decoder-only architecture, which requires sampling algorithms that invoke the full network at every denoising step and incur high computational cost. Our key insight is that discrete diffusion models perform two types of computation: 1) representing clean tokens and 2) denoising corrupted tokens, which enables us to use separate modules for each task. We propose an encoder-decoder architecture to accelerate discrete diffusion inference, which relies on an encoder to represent clean tokens and a lightweight decoder to iteratively refine a noised sequence. We also show that this architecture enables faster training of block diffusion models, which partition sequences into blocks for better quality and are commonly used in diffusion language model inference. We introduce a framework for Efficient Encoder-Decoder Diffusion (E2D2), consisting of an architecture with specialized training and sampling algorithms, and we show that E2D2 achieves superior trade-offs between generation quality and inference throughput on summarization, translation, and mathematical reasoning tasks. We provide the code1, model weights, and blog post on the project page: https://m-arriola.com/e2d2.

In multimodal representation learning, synergistic interactions between modalities not only provide complementary information but also create unique outcomes through specific interaction patterns that no single modality could achieve alone. Existing methods may struggle to effectively capture the full spectrum of synergistic information, leading to suboptimal performance in tasks where such interactions are critical. This is particularly problematic because synergistic information constitutes the fundamental value proposition of multimodal representation. To address this challenge, we introduce InfMasking, a contrastive synergistic information extraction method designed to enhance synergistic information through an Infinite Masking strategy. InfMasking stochastically occludes most features from each modality during fusion, preserving only partial information to create representations with varied synergistic patterns.

Modern code generation has made significant strides in functional correctness and execution efficiency. However, these systems often overlook a critical dimension in real-world software development: maintainability. To handle dynamic requirements with minimal rework, we propose MaintainCoder as a pioneering solution. It integrates the Waterfall model, design patterns, and multi-agent collaboration to systematically enhance cohesion, reduce coupling, achieving clear responsibility boundaries and better maintainability. We also introduce MaintainBench, a benchmark comprising requirement changes and novel dynamic metrics on maintenance efforts. Experiments demonstrate that existing code generation methods struggle to meet maintainability standards when requirements evolve. In contrast, MaintainCoder improves dynamic maintainability metrics by more than 60% with even higher correctness of initial codes. Furthermore, while static metrics fail to accurately reflect maintainability and even contradict each other, our proposed dynamic metrics exhibit high consistency. Our work not only provides the foundation for maintainable code generation, but also highlights the need for more realistic and comprehensive code generation research.

Large reasoning models (LRMs) are proficient at generating explicit, step-by-step reasoning sequences before producing final answers. However, such detailed reasoning can introduce substantial computational overhead and latency, particularly for simple problems. To address this overthinking problem, we explore how to equip LRMs with adaptive thinking capabilities, enabling them to dynamically decide whether to engage in explicit reasoning based on problem complexity. Building on R1-style distilled models, we observe that inserting a simple ellipsis ("...") into the prompt can stochastically trigger either a thinking or no-thinking mode, revealing a latent controllability in the reasoning behavior. Leveraging this property, we propose AutoThink, a multi-stage reinforcement learning (RL) framework that progressively optimizes reasoning policies via stage-wise reward shaping. AutoThink learns to invoke explicit reasoning only when necessary, while defaulting to succinct responses for simpler tasks. Experiments on five mainstream mathematical benchmarks demonstrate that AutoThink achieves favorable accuracy-efficiency trade-offs compared to recent prompting and RL-based pruning methods. It can be seamlessly integrated into any R1-style model, including both distilled and further fine-tuned variants. Notably, AutoThink improves relative accuracy by 6.4% while reducing token usage by 52% on DeepSeek-R1-Distill-Qwen-1.5B, establishing a scalable and adaptive reasoning paradigm for LRMs.

One of the principal challenges in building VLM-powered GUI agents is visual grounding--localizing the appropriate screen region for action execution based on both the visual content and the textual plans. Most existing work formulates this as a text-based coordinate generation task. However, these approaches suffer from several limitations: weak spatial-semantic alignment due to lack of explicit spatial supervision; inability to handle ambiguous supervision targets, as singlepoint predictions penalize valid variations; and a mismatch between the dense nature of screen coordinates and the coarse, patch-level granularity of visual features extracted by models like Vision Transformers. In this paper, we propose GUI-Actor, a VLM-based method for coordinate-free GUI grounding. At its core, GUI-Actorintroduces an attention-based action head that learns to align a dedicated token with all relevant visual patch tokens, enabling the model to propose one or more action regions in a single forward pass. In line with this, we further design a grounding verifier to evaluate and select the most plausible action region from the candidates proposed for action execution. Extensive experiments show that GUI-Actoroutperforms prior state-of-the-art methods on multiple GUI action grounding benchmarks, with improved generalization to unseen screen resolutions and layouts. Notably, GUI-Actor-7B achieves scores of 40.7 with Qwen2-VL and 44.6 with Qwen2.5-VL as backbones, outperforming UI-TARS72B (38.1) on ScreenSpot-Pro, with significantly fewer parameters and training data. Furthermore, by incorporating the verifier, we find that fine-tuning only the newly introduced action head ( 100M parameters for 7B model) while keeping the VLM backbone frozen is sufficient to achieve performance comparable to previous state-of-the-art models, highlighting that GUI-Actor can endow the underlying VLM with effective grounding capabilities without compromising its general-purpose strengths.

Large language models are increasingly used as judges (LLM-as-a-judge) to evaluate model outputs at scale, but their assessments often diverge systematically from human judgments.

Large language models (LLMs) have facilitated a wide range of applications with distinct service-level objectives (SLOs), from latency-sensitive online tasks like interactive chatbots to throughput-oriented offline workloads like data synthesis. The existing deployment model, which dedicates machines to each workload, simplifies SLO management but often leads to poor resource utilization. This paper introduces HyGen, an interference-aware LLM serving system that enables efficient co-location of online and offline workloads while preserving SLOs. HyGen incorporates two key innovations: (1) performance control mechanisms, including a latency predictor to estimate batch execution time and an SLO-aware profiler to quantify latency interference, and (2) SLO-aware offline scheduling policies that maximize serving throughput and prevent starvation. Our evaluation on production workloads shows that HyGen achieves up to 3.9-5.8