TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use

Large language model (LLM)-based agents increasingly rely on tool use to complete real-world tasks. While existing works evaluate the LLMs' tool use capability, they largely focus on the final answers yet overlook the detailed tool usage trajectory, i.e., whether tools are selected, parameterized, and ordered correctly. We introduce TRAJECT-Bench, a trajectory-aware benchmark to comprehensively evaluate LLMs' tool use capability through diverse tasks with fine-grained evaluation metrics. TRAJECT-Bench pairs high-fidelity, executable tools across practical domains with tasks grounded in production-style APIs, and synthesizes trajectories that vary in breadth (parallel calls) and depth (interdependent chains). Besides final accuracy, TRAJECT-Bench also reports trajectory-level diagnostics, including tool selection and argument correctness, and dependency/order satisfaction. Analyses reveal failure modes such as similar tool confusion and parameter-blind selection, and scaling behavior with tool diversity and trajectory length where the bottleneck of transiting from short to mid-length trajectories is revealed, offering actionable guidance for LLMs' tool use.

Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving

Large language models (LLMs) have been widely used for problem-solving tasks. Most recent work improves their performance through supervised fine-tuning (SFT) with labeled data or reinforcement learning (RL) from task feedback. In this paper, we study a new perspective: the divergence in solutions generated by LLMs for a single problem. We show that higher solution divergence is positively related to better problem-solving abilities across various models. Based on this finding, we propose solution divergence as a novel metric that can support both SFT and RL strategies. We test this idea on three representative problem domains and find that using solution divergence consistently improves success rates. These results suggest that solution divergence is a simple but effective tool for advancing LLM training and evaluation.

UPRPRC: Unified Pipeline for Reproducing Parallel Resources -- Corpus from the United Nations

The quality and accessibility of multilingual datasets are crucial for advancing machine translation. However, previous corpora built from United Nations documents have suffered from issues such as opaque process, difficulty of reproduction, and limited scale. To address these challenges, we introduce a complete end-to-end solution, from data acquisition via web scraping to text alignment. The entire process is fully reproducible, with a minimalist single-machine example and optional distributed computing steps for scalability. At its core, we propose a new Graph-Aided Paragraph Alignment (GAPA) algorithm for efficient and flexible paragraph-level alignment. The resulting corpus contains over 713 million English tokens, more than doubling the scale of prior work. To the best of our knowledge, this represents the largest publicly available parallel corpus composed entirely of human-translated, non-AI-generated content. Our code and corpus are accessible under the MIT License.

Beyond Words: Enhancing Desire, Emotion, and Sentiment Recognition with Non-Verbal Cues

Desire, as an intention that drives human behavior, is closely related to both emotion and sentiment. Multimodal learning has advanced sentiment and emotion recognition, but multimodal approaches specially targeting human desire understanding remain underexplored. And existing methods in sentiment analysis predominantly emphasize verbal cues and overlook images as complementary non-verbal cues. To address these gaps, we propose a Symmetrical Bidirectional Multimodal Learning Framework for Desire, Emotion, and Sentiment Recognition, which enforces mutual guidance between text and image modalities to effectively capture intention-related representations in the image. Specifically, low-resolution images are used to obtain global visual representations for cross-modal alignment, while high resolution images are partitioned into sub-images and modeled with masked image modeling to enhance the ability to capture fine-grained local features. A text-guided image decoder and an image-guided text decoder are introduced to facilitate deep cross-modal interaction at both local and global representations of image information. Additionally, to balance perceptual gains with computation cost, a mixed-scale image strategy is adopted, where high-resolution images are cropped into sub-images for masked modeling. The proposed approach is evaluated on MSED, a multimodal dataset that includes a desire understanding benchmark, as well as emotion and sentiment recognition. Experimental results indicate consistent improvements over other state-of-the-art methods, validating the effectiveness of our proposed method. Specifically, our method outperforms existing approaches, achieving F1-score improvements of 1.1% in desire understanding, 0.6% in emotion recognition, and 0.9% in sentiment analysis. Our code is available at: https://github.com/especiallyW/SyDES.

Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

Recent advances in audio-driven avatar video generation have significantly enhanced audio-visual realism. However, existing methods treat instruction conditioning merely as low-level tracking driven by acoustic or visual cues, without modeling the communicative purpose conveyed by the instructions. This limitation compromises their narrative coherence and character expressiveness. To bridge this gap, we introduce Kling-Avatar, a novel cascaded framework that unifies multimodal instruction understanding with photorealistic portrait generation. Our approach adopts a two-stage pipeline. In the first stage, we design a multimodal large language model (MLLM) director that produces a blueprint video conditioned on diverse instruction signals, thereby governing high-level semantics such as character motion and emotions. In the second stage, guided by blueprint keyframes, we generate multiple sub-clips in parallel using a first-last frame strategy. This global-to-local framework preserves fine-grained details while faithfully encoding the high-level intent behind multimodal instructions. Our parallel architecture also enables fast and stable generation of long-duration videos, making it suitable for real-world applications such as digital human livestreaming and vlogging. To comprehensively evaluate our method, we construct a benchmark of 375 curated samples covering diverse instructions and challenging scenarios. Extensive experiments demonstrate that Kling-Avatar is capable of generating vivid, fluent, long-duration videos at up to 1080p and 48 fps, achieving superior performance in lip synchronization accuracy, emotion and dynamic expressiveness, instruction controllability, identity preservation, and cross-domain generalization. These results establish Kling-Avatar as a new benchmark for semantically grounded, high-fidelity audio-driven avatar synthesis.

Beyond Distribution Shifts: Adaptive Hyperspectral Image Classification at Test Time

Hyperspectral image (HSI) classification models are highly sensitive to distribution shifts caused by various real-world degradations such as noise, blur, compression, and atmospheric effects. To address this challenge, we propose HyperTTA, a unified framework designed to enhance model robustness under diverse degradation conditions. Specifically, we first construct a multi-degradation hyperspectral dataset that systematically simulates nine representative types of degradations, providing a comprehensive benchmark for robust classification evaluation. Based on this, we design a spectral-spatial transformer classifier (SSTC) enhanced with a multi-level receptive field mechanism and label smoothing regularization to jointly capture multi-scale spatial context and improve generalization. Furthermore, HyperTTA incorporates a lightweight test-time adaptation (TTA) strategy, the confidence-aware entropy-minimized LayerNorm adapter (CELA), which updates only the affine parameters of LayerNorm layers by minimizing prediction entropy on high-confidence unlabeled target samples. This confidence-aware adaptation prevents unreliable updates from noisy predictions, enabling robust and dynamic adaptation without access to source data or target annotations. Extensive experiments on two benchmark datasets demonstrate that HyperTTA outperforms existing baselines across a wide range of degradation scenarios, validating the effectiveness of both its classification backbone and the proposed TTA scheme. Code will be made available publicly.

MonoRelief V2: Leveraging Real Data for High-Fidelity Monocular Relief Recovery

This paper presents MonoRelief V2, an end-to-end model designed for directly recovering 2.5D reliefs from single images under complex material and illumination variations. In contrast to its predecessor, MonoRelief V1 [1], which was solely trained on synthetic data, MonoRelief V2 incorporates real data to achieve improved robustness, accuracy and efficiency. To overcome the challenge of acquiring large-scale real-world dataset, we generate approximately 15,000 pseudo real images using a text-to-image generative model, and derive corresponding depth pseudo-labels through fusion of depth and normal predictions. Furthermore, we construct a small-scale real-world dataset (800 samples) via multi-view reconstruction and detail refinement. MonoRelief V2 is then progressively trained on the pseudo-real and real-world datasets. Comprehensive experiments demonstrate its state-of-the-art performance both in depth and normal predictions, highlighting its strong potential for a range of downstream applications. Code is at: https://github.com/glp1001/MonoreliefV2.

Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization

The increasing sophistication of image manipulation techniques demands robust forensic solutions that can both reliably detect alterations and precisely localize tampered regions. Recent Multimodal Large Language Models (MLLMs) show promise by leveraging world knowledge and semantic understanding for context-aware detection, yet they struggle with perceiving subtle, low-level forensic artifacts crucial for accurate manipulation localization. This paper presents a novel Propose-Rectify framework that effectively bridges semantic reasoning with forensic-specific analysis. In the proposal stage, our approach utilizes a forensic-adapted LLaVA model to generate initial manipulation analysis and preliminary localization of suspicious regions based on semantic understanding and contextual reasoning. In the rectification stage, we introduce a Forensics Rectification Module that systematically validates and refines these initial proposals through multi-scale forensic feature analysis, integrating technical evidence from several specialized filters. Additionally, we present an Enhanced Segmentation Module that incorporates critical forensic cues into SAM's encoded image embeddings, thereby overcoming inherent semantic biases to achieve precise delineation of manipulated regions. By synergistically combining advanced multimodal reasoning with established forensic methodologies, our framework ensures that initial semantic proposals are systematically validated and enhanced through concrete technical evidence, resulting in comprehensive detection accuracy and localization precision. Extensive experimental validation demonstrates state-of-the-art performance across diverse datasets with exceptional robustness and generalization capabilities.

S2Sent: Nested Selectivity Aware Sentence Representation Learning

The combination of Transformer-based encoders with contrastive learning represents the current mainstream paradigm for sentence representation learning. This paradigm is typically based on the hidden states of the last Transformer block of the encoder. However, within Transformer-based encoders, different blocks exhibit varying degrees of semantic perception ability. From the perspective of interpretability, the semantic perception potential of knowledge neurons is modulated by stimuli, thus rational cross-block representation fusion is a direction worth optimizing. To balance the semantic redundancy and loss across block fusion, we propose a sentence representation selection mechanism S\textsuperscript{2}Sent, which integrates a parameterized nested selector downstream of the Transformer-based encoder. This selector performs spatial selection (SS) and nested frequency selection (FS) from a modular perspective. The SS innovatively employs a spatial squeeze based self-gating mechanism to obtain adaptive weights, which not only achieves fusion with low information redundancy but also captures the dependencies between embedding features. The nested FS replaces GAP with different DCT basis functions to achieve spatial squeeze with low semantic loss. Extensive experiments have demonstrated that S\textsuperscript{2}Sent achieves significant improvements over baseline methods with negligible additional parameters and inference latency, while highlighting high integrability and scalability.

A Scalable Pretraining Framework for Link Prediction with Efficient Adaptation

Link Prediction (LP) is a critical task in graph machine learning. While Graph Neural Networks (GNNs) have significantly advanced LP performance recently, existing methods face key challenges including limited supervision from sparse connectivity, sensitivity to initialization, and poor generalization under distribution shifts. We explore pretraining as a solution to address these challenges. Unlike node classification, LP is inherently a pairwise task, which requires the integration of both node- and edge-level information. In this work, we present the first systematic study on the transferability of these distinct modules and propose a late fusion strategy to effectively combine their outputs for improved performance. To handle the diversity of pretraining data and avoid negative transfer, we introduce a Mixture-of-Experts (MoE) framework that captures distinct patterns in separate experts, facilitating seamless application of the pretrained model on diverse downstream datasets. For fast adaptation, we develop a parameter-efficient tuning strategy that allows the pretrained model to adapt to unseen datasets with minimal computational overhead. Experiments on 16 datasets across two domains demonstrate the effectiveness of our approach, achieving state-of-the-art performance on low-resource link prediction while obtaining competitive results compared to end-to-end trained methods, with over 10,000x lower computational overhead.