SERL: Self-Examining Reinforcement Learning on Open-Domain

Reinforcement Learning (RL) has been shown to improve the capabilities of large language models (LLMs). However, applying RL to open-domain tasks faces two key challenges: (1) the inherent subjectivity of these tasks prevents the verifiable rewards as required by Reinforcement Learning with Verifiable Rewards (RLVR); (2) Reinforcement Learning from Human Feedback (RLHF) relies on external reward mechanisms. To overcome these limitations, we propose Self-Examining Reinforcement Learning (SERL), a novel self-improving framework where the LLM serves as both Actor and Judge. SERL introduces two synergistic reward mechanisms without any external signals. On the one hand, to improve the Actor's capability, we derive rewards from Copeland-style pairwise comparison judgments across a group of generated responses. On the other hand, a self-consistency reward that encourages coherent judgments is proposed to improve the Judge's reliability. This process refines the Judge's capability, which in turn provides a more robust reward for Actor. Experiments show that our method outperforms existing self-improvement training methods. SERL improves the LC win rate of Qwen3-8B on AlpacaEval 2 from 52.37% to 59.90%. To the best of our knowledge, our method achieves state-of-the-art performance among self-improving approaches. Furthermore, it achieves a performance comparable to significantly larger models like Qwen3-32B, demonstrating superior effectiveness and robustness on open-domain tasks.

Seeing is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding

Multimodal Large Language Models (MLLMs) have unlocked powerful cross-modal capabilities, but still significantly suffer from hallucinations. As such, accurate detection of hallucinations in MLLMs is imperative for ensuring their reliability in practical applications. To this end, guided by the principle of "Seeing is Believing", we introduce VBackChecker, a novel reference-free hallucination detection framework that verifies the consistency of MLLMgenerated responses with visual inputs, by leveraging a pixellevel Grounding LLM equipped with reasoning and referring segmentation capabilities. This reference-free framework not only effectively handles rich-context scenarios, but also offers interpretability. To facilitate this, an innovative pipeline is accordingly designed for generating instruction-tuning data (R-Instruct), featuring rich-context descriptions, grounding masks, and hard negative samples. We further establish R^2 -HalBench, a new hallucination benchmark for MLLMs, which, unlike previous benchmarks, encompasses real-world, rich-context descriptions from 18 MLLMs with high-quality annotations, spanning diverse object-, attribute, and relationship-level details. VBackChecker outperforms prior complex frameworks and achieves state-of-the-art performance on R^2 -HalBench, even rivaling GPT-4o's capabilities in hallucination detection. It also surpasses prior methods in the pixel-level grounding task, achieving over a 10% improvement. All codes, data, and models are available at https://github.com/PinxueGuo/VBackChecker.

Divide-and-Conquer Decoupled Network for Cross-Domain Few-Shot Segmentation

Cross-domain few-shot segmentation (CD-FSS) aims to tackle the dual challenge of recognizing novel classes and adapting to unseen domains with limited annotations. However, encoder features often entangle domain-relevant and category-relevant information, limiting both generalization and rapid adaptation to new domains. To address this issue, we propose a Divide-and-Conquer Decoupled Network (DCDNet). In the training stage, to tackle feature entanglement that impedes cross-domain generalization and rapid adaptation, we propose the Adversarial-Contrastive Feature Decomposition (ACFD) module. It decouples backbone features into category-relevant private and domain-relevant shared representations via contrastive learning and adversarial learning. Then, to mitigate the potential degradation caused by the disentanglement, the Matrix-Guided Dynamic Fusion (MGDF) module adaptively integrates base, shared, and private features under spatial guidance, maintaining structural coherence. In addition, in the fine-tuning stage, to enhanced model generalization, the Cross-Adaptive Modulation (CAM) module is placed before the MGDF, where shared features guide private features via modulation ensuring effective integration of domain-relevant information. Extensive experiments on four challenging datasets show that DCDNet outperforms existing CD-FSS methods, setting a new state-of-the-art for cross-domain generalization and few-shot adaptation.

Adaptive Graph Learning with Transformer for Multi-Reservoir Inflow Prediction

Reservoir inflow prediction is crucial for water resource management, yet existing approaches mainly focus on single-reservoir models that ignore spatial dependencies among interconnected reservoirs. We introduce AdaTrip as an adaptive, time-varying graph learning framework for multi-reservoir inflow forecasting. AdaTrip constructs dynamic graphs where reservoirs are nodes with directed edges reflecting hydrological connections, employing attention mechanisms to automatically identify crucial spatial and temporal dependencies. Evaluation on thirty reservoirs in the Upper Colorado River Basin demonstrates superiority over existing baselines, with improved performance for reservoirs with limited records through parameter sharing. Additionally, AdaTrip provides interpretable attention maps at edge and time-step levels, offering insights into hydrological controls to support operational decision-making. Our code is available at https://github.com/humphreyhuu/AdaTrip.

VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Driving

Recent advancements in language-grounded autonomous driving have been significantly promoted by the sophisticated cognition and reasoning capabilities of large language models (LLMs). However, current LLM-based approaches encounter critical challenges: (1) Failure analysis reveals that frequent collisions and obstructions, stemming from limitations in visual representations, remain primary obstacles to robust driving performance. (2) The substantial parameters of LLMs pose considerable deployment hurdles. To address these limitations, we introduce VLDrive, a novel approach featuring a lightweight MLLM architecture with enhanced vision components. VLDrive achieves compact visual tokens through innovative strategies, including cycle-consistent dynamic visual pruning and memory-enhanced feature aggregation. Furthermore, we propose a distance-decoupled instruction attention mechanism to improve joint visual-linguistic feature learning, particularly for long-range visual tokens. Extensive experiments conducted in the CARLA simulator demonstrate VLDrive`s effectiveness. Notably, VLDrive achieves state-of-the-art driving performance while reducing parameters by 81% (from 7B to 1.3B), yielding substantial driving score improvements of 15.4%, 16.8%, and 7.6% at tiny, short, and long distances, respectively, in closed-loop evaluations. Code is available at https://github.com/ReaFly/VLDrive.

AdaDrive: Self-Adaptive Slow-Fast System for Language-Grounded Autonomous Driving

Effectively integrating Large Language Models (LLMs) into autonomous driving requires a balance between leveraging high-level reasoning and maintaining real-time efficiency. Existing approaches either activate LLMs too frequently, causing excessive computational overhead, or use fixed schedules, failing to adapt to dynamic driving conditions. To address these challenges, we propose AdaDrive, an adaptively collaborative slow-fast framework that optimally determines when and how LLMs contribute to decision-making. (1) When to activate the LLM: AdaDrive employs a novel adaptive activation loss that dynamically determines LLM invocation based on a comparative learning mechanism, ensuring activation only in complex or critical scenarios. (2) How to integrate LLM assistance: Instead of rigid binary activation, AdaDrive introduces an adaptive fusion strategy that modulates a continuous, scaled LLM influence based on scene complexity and prediction confidence, ensuring seamless collaboration with conventional planners. Through these strategies, AdaDrive provides a flexible, context-aware framework that maximizes decision accuracy without compromising real-time performance. Extensive experiments on language-grounded autonomous driving benchmarks demonstrate that AdaDrive state-of-the-art performance in terms of both driving accuracy and computational efficiency. Code is available at https://github.com/ReaFly/AdaDrive.

LaneDiffusion: Improving Centerline Graph Learning via Prior Injected BEV Feature Generation

Centerline graphs, crucial for path planning in autonomous driving, are traditionally learned using deterministic methods. However, these methods often lack spatial reasoning and struggle with occluded or invisible centerlines. Generative approaches, despite their potential, remain underexplored in this domain. We introduce LaneDiffusion, a novel generative paradigm for centerline graph learning. LaneDiffusion innovatively employs diffusion models to generate lane centerline priors at the Bird's Eye View (BEV) feature level, instead of directly predicting vectorized centerlines. Our method integrates a Lane Prior Injection Module (LPIM) and a Lane Prior Diffusion Module (LPDM) to effectively construct diffusion targets and manage the diffusion process. Furthermore, vectorized centerlines and topologies are then decoded from these prior-injected BEV features. Extensive evaluations on the nuScenes and Argoverse2 datasets demonstrate that LaneDiffusion significantly outperforms existing methods, achieving improvements of 4.2%, 4.6%, 4.7%, 6.4% and 1.8% on fine-grained point-level metrics (GEO F1, TOPO F1, JTOPO F1, APLS and SDA) and 2.3%, 6.4%, 6.8% and 2.1% on segment-level metrics (IoU, mAP_cf, DET_l and TOP_ll). These results establish state-of-the-art performance in centerline graph learning, offering new insights into generative models for this task.

MS2Edge: Towards Energy-Efficient and Crisp Edge Detection with Multi-Scale Residual Learning in SNNs

Edge detection with Artificial Neural Networks (ANNs) has achieved remarkable prog\-ress but faces two major challenges. First, it requires pre-training on large-scale extra data and complex designs for prior knowledge, leading to high energy consumption. Second, the predicted edges perform poorly in crispness and heavily rely on post-processing. Spiking Neural Networks (SNNs), as third generation neural networks, feature quantization and spike-driven computation mechanisms. They inherently provide a strong prior for edge detection in an energy-efficient manner, while its quantization mechanism helps suppress texture artifact interference around true edges, improving prediction crispness. However, the resulting quantization error inevitably introduces sparse edge discontinuities, compromising further enhancement of crispness. To address these challenges, we propose MS2Edge, the first SNN-based model for edge detection. At its core, we build a novel spiking backbone named MS2ResNet that integrates multi-scale residual learning to recover missing boundary lines and generate crisp edges, while combining I-LIF neurons with Membrane-based Deformed Shortcut (MDS) to mitigate quantization errors. The model is complemented by a Spiking Multi-Scale Upsample Block (SMSUB) for detail reconstruction during upsampling and a Membrane Average Decoding (MAD) method for effective integration of edge maps across multiple time steps. Experimental results demonstrate that MS2Edge outperforms ANN-based methods and achieves state-of-the-art performance on the BSDS500, NYUDv2, BIPED, PLDU, and PLDM datasets without pre-trained backbones, while maintaining ultralow energy consumption and generating crisp edge maps without post-processing.

MolChord: Structure-Sequence Alignment for Protein-Guided Drug Design

Structure-based drug design (SBDD), which maps target proteins to candidate molecular ligands, is a fundamental task in drug discovery. Effectively aligning protein structural representations with molecular representations, and ensuring alignment between generated drugs and their pharmacological properties, remains a critical challenge. To address these challenges, we propose MolChord, which integrates two key techniques: (1) to align protein and molecule structures with their textual descriptions and sequential representations (e.g., FASTA for proteins and SMILES for molecules), we leverage NatureLM, an autoregressive model unifying text, small molecules, and proteins, as the molecule generator, alongside a diffusion-based structure encoder; and (2) to guide molecules toward desired properties, we curate a property-aware dataset by integrating preference data and refine the alignment process using Direct Preference Optimization (DPO). Experimental results on CrossDocked2020 demonstrate that our approach achieves state-of-the-art performance on key evaluation metrics, highlighting its potential as a practical tool for SBDD.

ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference

The expansion of large language models is increasingly limited by the constrained memory capacity of modern GPUs. To mitigate this, Mixture-of-Experts (MoE) architectures activate only a small portion of parameters during inference, significantly lowering both memory demand and computational overhead. However, conventional MoE inference approaches, which select active experts independently at each layer, often introduce considerable latency because of frequent parameter transfers between host and GPU memory. In addition, current cross-layer prediction strategies, which are typically based on fixed steps, lack adaptability across different hardware platforms and workloads, thereby reducing their robustness and effectiveness. To address these challenges, we present ExpertFlow, a runtime system for MoE inference that combines adaptive expert prefetching and cache-aware routing. ExpertFlow continuously adjusts its prediction horizon for expert activation by leveraging runtime statistics such as transfer bandwidth, parameter dimensionality, and model feedback signals. Furthermore, it incorporates a hybrid cross-layer prediction scheme that fuses pregating information with intermediate computational states to anticipate future expert needs. By adaptively refining prefetching decisions and aligning them with actual usage behavior, ExpertFlow effectively decreases cache misses and removes latency caused by expert swap-ins. Our evaluation demonstrates that ExpertFlow reduces model stall time to less than 0.1% of the baseline, highlighting its capability to optimize MoE inference under stringent memory constraints.