Efficient Table Retrieval and Understanding with Multimodal Large Language Models

Tabular data is frequently captured in image form across a wide range of real-world scenarios such as financial reports, handwritten records, and document scans. These visual representations pose unique challenges for machine understanding, as they combine both structural and visual complexities. While recent advances in Multimodal Large Language Models (MLLMs) show promising results in table understanding, they typically assume the relevant table is readily available. However, a more practical scenario involves identifying and reasoning over relevant tables from large-scale collections to answer user queries. To address this gap, we propose TabRAG, a framework that enables MLLMs to answer queries over large collections of table images. Our approach first retrieves candidate tables using jointly trained visual-text foundation models, then leverages MLLMs to perform fine-grained reranking of these candidates, and finally employs MLLMs to reason over the selected tables for answer generation. Through extensive experiments on a newly constructed dataset comprising 88,161 training and 9,819 testing samples across 8 benchmarks with 48,504 unique tables, we demonstrate that our framework significantly outperforms existing methods by 7.0% in retrieval recall and 6.1% in answer accuracy, offering a practical solution for real-world table understanding tasks.

A2Eval: Agentic and Automated Evaluation for Embodied Brain

Current embodied VLM evaluation relies on static, expert-defined, manually annotated benchmarks that exhibit severe redundancy and coverage imbalance. This labor intensive paradigm drains computational and annotation resources, inflates costs, and distorts model rankings, ultimately stifling iterative development. To address this, we propose Agentic Automatic Evaluation (A2Eval), the first agentic framework that automates benchmark curation and evaluation through two collaborative agents. The Data Agent autonomously induces capability dimensions and assembles a balanced, compact evaluation suite, while the Eval Agent synthesizes and validates executable evaluation pipelines, enabling fully autonomous, high-fidelity assessment. Evaluated across 10 benchmarks and 13 models, A2Eval compresses evaluation suites by 85%, reduces overall computational costs by 77%, and delivers a 4.6x speedup while preserving evaluation quality. Crucially, A2Eval corrects systematic ranking biases, improves human alignment to Spearman's rho=0.85, and maintains high ranking fidelity (Kendall's tau=0.81), establishing a new standard for high-fidelity, low-cost embodied assessment. Our code and data will be public soon.

Physics-Informed Chebyshev Polynomial Neural Operator for Parametric Partial Differential Equations

Neural operators have emerged as powerful deep learning frameworks for approximating solution operators of parameterized partial differential equations (PDE). However, current methods predominantly rely on multilayer perceptrons (MLPs) for mapping inputs to solutions, which impairs training robustness in physics-informed settings due to inherent spectral biases and fixed activation functions. To overcome the architectural limitations, we introduce the Physics-Informed Chebyshev Polynomial Neural Operator (CPNO), a novel mesh-free framework that leverages a basis transformation to replace unstable monomial expansions with the numerically stable Chebyshev spectral basis. By integrating parameter dependent modulation mechanism to main net, CPNO constructs PDE solutions in a near-optimal functional space, decoupling the model from MLP-specific constraints and enhancing multi-scale representation. Theoretical analysis demonstrates the Chebyshev basis's near-minimax uniform approximation properties and superior conditioning, with Lebesgue constants growing logarithmically with degree, thereby mitigating spectral bias and ensuring stable gradient flow during optimization. Numerical experiments on benchmark parameterized PDEs show that CPNO achieves superior accuracy, faster convergence, and enhanced robustness to hyperparameters. The experiment of transonic airfoil flow has demonstrated the capability of CPNO in characterizing complex geometric problems.

Hard Constraints Meet Soft Generation: Guaranteed Feasibility for LLM-based Combinatorial Optimization

Large language models (LLMs) have emerged as promising general-purpose solvers for combinatorial optimization (CO), yet they fundamentally lack mechanisms to guarantee solution feasibility which is critical for real-world deployment. In this work, we introduce FALCON, a framework that ensures 100\% feasibility through three key innovations: (i) \emph{grammar-constrained decoding} enforces syntactic validity, (ii) a \emph{feasibility repair layer} corrects semantic constraint violations, and (iii) \emph{adaptive Best-of-$N$ sampling} allocates inference compute efficiently. To train the underlying LLM, we introduce the Best-anchored Objective-guided Preference Optimization (BOPO) in LLM training, which weights preference pairs by their objective gap, providing dense supervision without human labels. Theoretically, we prove convergence for BOPO and provide bounds on repair-induced quality loss. Empirically, across seven NP-hard CO problems, FALCON achieves perfect feasibility while matching or exceeding the solution quality of state-of-the-art neural and LLM-based solvers.

SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization

Reinforcement learning with verifiable rewards has emerged as a powerful paradigm for training intelligent agents. However, existing methods typically employ binary rewards that fail to capture quality differences among trajectories achieving identical outcomes, thereby overlooking potential diversity within the solution space. Inspired by the ``sweet spot'' concept in tennis-the racket's core region that produces optimal hitting effects, we introduce \textbf{S}weet \textbf{S}pot \textbf{L}earning (\textbf{SSL}), a novel framework that provides differentiated guidance for agent optimization. SSL follows a simple yet effective principle: progressively amplified, tiered rewards guide policies toward the sweet-spot region of the solution space. This principle naturally adapts across diverse tasks: visual perception tasks leverage distance-tiered modeling to reward proximity, while complex reasoning tasks reward incremental progress toward promising solutions. We theoretically demonstrate that SSL preserves optimal solution ordering and enhances the gradient signal-to-noise ratio, thereby fostering more directed optimization. Extensive experiments across GUI perception, short/long-term planning, and complex reasoning tasks show consistent improvements over strong baselines on 12 benchmarks, achieving up to 2.5X sample efficiency gains and effective cross-task transferability. Our work establishes SSL as a general principle for training capable and robust agents.

Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning

Reinforcement learning has empowered large language models to act as intelligent agents, yet training them for long-horizon tasks remains challenging due to the scarcity of high-quality trajectories, especially under limited resources. Existing methods typically scale up rollout sizes and indiscriminately allocate computational resources among intermediate steps. Such attempts inherently waste substantial computation budget on trivial steps while failing to guarantee sample quality. To address this, we propose \textbf{Spark} (\textbf{S}trategic \textbf{P}olicy-\textbf{A}ware explo\textbf{R}ation via \textbf{K}ey-state dynamic branching), a novel framework that selectively branches at critical decision states for resource-efficient exploration. Our key insight is to activate adaptive branching exploration at critical decision points to probe promising trajectories, thereby achieving precise resource allocation that prioritizes sampling quality over blind coverage. This design leverages the agent's intrinsic decision-making signals to reduce dependence on human priors, enabling the agent to autonomously expand exploration and achieve stronger generalization. Experiments across diverse tasks (e.g., embodied planning), demonstrate that \textsc{Spark} achieves superior success rates with significantly fewer training samples, exhibiting robust generalization even in unseen scenarios.

CPiRi: Channel Permutation-Invariant Relational Interaction for Multivariate Time Series Forecasting

Current methods for multivariate time series forecasting can be classified into channel-dependent and channel-independent models. Channel-dependent models learn cross-channel features but often overfit the channel ordering, which hampers adaptation when channels are added or reordered. Channel-independent models treat each channel in isolation to increase flexibility, yet this neglects inter-channel dependencies and limits performance. To address these limitations, we propose \textbf{CPiRi}, a \textbf{channel permutation invariant (CPI)} framework that infers cross-channel structure from data rather than memorizing a fixed ordering, enabling deployment in settings with structural and distributional co-drift without retraining. CPiRi couples \textbf{spatio-temporal decoupling architecture} with \textbf{permutation-invariant regularization training strategy}: a frozen pretrained temporal encoder extracts high-quality temporal features, a lightweight spatial module learns content-driven inter-channel relations, while a channel shuffling strategy enforces CPI during training. We further \textbf{ground CPiRi in theory} by analyzing permutation equivariance in multivariate time series forecasting. Experiments on multiple benchmarks show state-of-the-art results. CPiRi remains stable when channel orders are shuffled and exhibits strong \textbf{inductive generalization} to unseen channels even when trained on \textbf{only half} of the channels, while maintaining \textbf{practical efficiency} on large-scale datasets. The source code is released at https://github.com/JasonStraka/CPiRi.

DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation

Open-vocabulary semantic segmentation aims to assign labels to every pixel in an image based on text labels. Existing approaches typically utilize vision-language models (VLMs), such as CLIP, for dense prediction. However, VLMs, pre-trained on image-text pairs, are biased toward salient, object-centric regions and exhibit two critical limitations when adapted to segmentation: (i) Foreground Bias, which tends to ignore background regions, and (ii) Limited Spatial Localization, resulting in blurred object boundaries. To address these limitations, we introduce DiSa, a novel saliency-aware foreground-background disentangled framework. By explicitly incorporating saliency cues in our designed Saliency-aware Disentanglement Module (SDM), DiSa separately models foreground and background ensemble features in a divide-and-conquer manner. Additionally, we propose a Hierarchical Refinement Module (HRM) that leverages pixel-wise spatial contexts and enables channel-wise feature refinement through multi-level updates. Extensive experiments on six benchmarks demonstrate that DiSa consistently outperforms state-of-the-art methods.

FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning

Reinforcement learning (RL) for large language models (LLMs) is increasingly bottlenecked by rollout (generation), where long output sequence lengths make attention and KV-cache memory dominate end-to-end step time. FP8 offers an attractive lever for accelerating RL by reducing compute cost and memory traffic during rollout, but applying FP8 in RL introduces unique engineering and algorithmic challenges: policy weights change every step (requiring repeated quantization and weight synchronization into the inference engine) and low-precision rollouts can deviate from the higher-precision policy assumed by the trainer, causing train-inference mismatch and potential instability. This report presents a practical FP8 rollout stack for LLM RL, implemented in the veRL ecosystem with support for common training backends (e.g., FSDP/Megatron-LM) and inference engines (e.g., vLLM/SGLang). We (i) enable FP8 W8A8 linear-layer rollout using blockwise FP8 quantization, (ii) extend FP8 to KV-cache to remove long-context memory bottlenecks via per-step QKV scale recalibration, and (iii) mitigate mismatch using importance-sampling-based rollout correction (token-level TIS/MIS variants). Across dense and MoE models, these techniques deliver up to 44% rollout throughput gains while preserving learning behavior comparable to BF16 baselines.

Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning

The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a high-dimensional optimization challenge. Existing approaches often rely on a single model or fixed tool-calling logic, failing to exploit the performance variations across heterogeneous model-tool pairs. In this paper, we present ATLAS (Adaptive Tool-LLM Alignment and Synergistic Invocation), a dual-path framework for dynamic tool usage in cross-domain complex reasoning. ATLAS operates via a dual-path approach: (1) \textbf{training-free cluster-based routing} that exploits empirical priors for domain-specific alignment, and (2) \textbf{RL-based multi-step routing} that explores autonomous trajectories for out-of-distribution generalization. Extensive experiments across 15 benchmarks demonstrate that our method outperforms closed-source models like GPT-4o, surpassing existing routing methods on both in-distribution (+10.1%) and out-of-distribution (+13.1%) tasks. Furthermore, our framework shows significant gains in visual reasoning by orchestrating specialized multi-modal tools.