arXiv:2603.04663v2 Announce Type: replace-cross Abstract: Standard Retrieval-Augmented Generation (RAG) architectures fail in high-stakes financial domains due to two fundamental limitations: the inherent arithmetic incompetence of Large Language Models (LLMs) and the distributional semantic conflation of dense vector retrieval (e.g., mapping “Net Income” to “Net Sales” due to contextual proximity). In deterministic domains, a 99% accuracy […]
OTESGN: Optimal Transport-Enhanced Syntactic-Semantic Graph Networks for Aspect-Based Sentiment Analysis
arXiv:2509.08612v3 Announce Type: replace-cross Abstract: Aspect-based sentiment analysis (ABSA) aims to identify aspect terms and determine their sentiment polarity. While dependency trees combined with contextual semantics provide structural cues, existing approaches often rely on dot-product similarity and fixed graphs, which limit their ability to capture nonlinear associations and adapt to noisy contexts. To address these […]
SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning
arXiv:2603.05437v2 Announce Type: replace-cross Abstract: Weakly-Supervised Dense Video Captioning aims to localize and describe events in videos trained only on caption annotations, without temporal boundaries. Prior work introduced an implicit supervision paradigm based on Gaussian masking and complementary captioning. However, existing method focuses merely on generating non-overlapping masks without considering their semantic relationship to corresponding […]
Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows
arXiv:2603.08126v1 Announce Type: cross Abstract: Coordinated audio generation based on video inputs typically requires a strict audio-visual (AV) alignment, where both semantics and rhythmics of the generated audio segments shall correspond to those in the video frames. Previous studies leverage a two-stage design where the AV encoders are firstly aligned via contrastive learning, then the […]
DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding
arXiv:2603.08145v1 Announce Type: cross Abstract: Preference-based alignment methods (e.g., RLHF, DPO) typically optimize a single scalar objective, implicitly averaging over heterogeneous human preferences. In practice, systematic annotator and user-group disagreement makes mean-reward maximization brittle and susceptible to proxy over-optimization. We propose **Disagreement-Aware Alignment via Risk-Constrained Decoding (DARC)**, a retraining-free inference-time method that frames response selection […]
Bridging Domains through Subspace-Aware Model Merging
arXiv:2603.05768v2 Announce Type: replace-cross Abstract: Model merging integrates multiple task-specific models into a single consolidated one. Recent research has made progress in improving merging performance for in-distribution or multi-task scenarios, but domain generalization in model merging remains underexplored. We investigate how merging models fine-tuned on distinct domains affects generalization to unseen domains. Through an analysis […]
Autonomous AI Agents for Option Hedging: Enhancing Financial Stability through Shortfall Aware Reinforcement Learning
arXiv:2603.06587v1 Announce Type: new Abstract: The deployment of autonomous AI agents in derivatives markets has widened a practical gap between static model calibration and realized hedging outcomes. We introduce two reinforcement learning frameworks, a novel Replication Learning of Option Pricing (RLOP) approach and an adaptive extension of Q-learner in Black-Scholes (QLBS), that prioritize shortfall probability […]
Fast Explanations via Policy Gradient-Optimized Explainer
arXiv:2405.18664v3 Announce Type: replace-cross Abstract: The challenge of delivering efficient explanations is a critical barrier that prevents the adoption of model explanations in real-world applications. Existing approaches often depend on extensive model queries for sample-level explanations or rely on expert’s knowledge of specific model structures that trade general applicability for efficiency. To address these limitations, […]
SaiVLA-0: Cerebrum–Pons–Cerebellum Tripartite Architecture for Compute-Aware Vision-Language-Action
arXiv:2603.08124v1 Announce Type: cross Abstract: We revisit Vision-Language-Action through a neuroscience-inspired triad. Biologically, the Cerebrum provides stable high-level multimodal priors and remains frozen; the Pons Adapter integrates these cortical features with real-time proprioceptive inputs and compiles intent into execution-ready tokens; and the Cerebellum (ParaCAT) performs fast, parallel categorical decoding for online control, with hysteresis/EMA/temperature/entropy for […]
More Bang for the Buck: Process Reward Modeling with Entropy-Driven Uncertainty
arXiv:2503.22233v4 Announce Type: replace-cross Abstract: We introduce the Entropy-Driven Uncertainty Process Reward Model (EDU-PRM), a novel entropy-driven training framework for process reward modeling that enables dynamic, uncertainty-aligned segmentation of complex reasoning steps, eliminating the need for costly manual step annotations. Unlike previous Process Reward Models (PRMs) that rely on static partitioning and human labeling, EDU-PRM […]
ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training
arXiv:2603.04385v2 Announce Type: replace-cross Abstract: Feed-forward transformer models have driven rapid progress in 3D vision, but state-of-the-art methods such as VGGT and $pi^3$ have a computational cost that scales quadratically with the number of input images, making them inefficient when applied to large image collections. Sequential-reconstruction approaches reduce this cost but sacrifice reconstruction quality. We […]
Stochastic Reaction Networks Within Interacting Compartments with Content-Dependent Fragmentation
arXiv:2511.10223v2 Announce Type: replace-cross Abstract: Stochastic reaction networks with mass-action kinetics provide a useful framework for understanding processes — biochemical and otherwise — in homogeneous environments. However, cellular reactions are often compartmentalized, either at the cell level or within cells, and hence non-homogeneous. A general framework for compartmentalized chemistry with dynamic compartments was proposed in […]