arXiv:2605.15877v1 Announce Type: cross Abstract: Continual learning enables neural networks to learn tasks sequentially without forgetting previously acquired knowledge. However, neural networks suffer from catastrophic forgetting, where learning new tasks degrades performance on earlier ones. We address this problem with Shapley Neuron Valuation (SNV), a principled framework that quantifies Neuron importance in continual learning, grounded […]
Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation
arXiv:2605.15913v1 Announce Type: cross Abstract: Block attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reuse in long-context scenarios such as Retrieval-Augmented Generation (RAG). However, its broader application is hindered by two key challenges: the difficulty of segmenting input text into meaningful, self-contained […]
SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution
arXiv:2605.15308v1 Announce Type: new Abstract: LLM-driven program evolution has emerged as a powerful tool for automated scientific discovery, yet existing frameworks offer no principled guide for designing their individual components and provide no guarantee that the search converges. We introduce SMCEvolve, which recasts program search as sampling from a reward-tilted target distribution and approximates it […]
From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery
arXiv:2605.15412v1 Announce Type: cross Abstract: Modern quantitative trading increasingly relies on systematic models to extract predictive signals from large-scale financial data, where alpha factor discovery plays a central role in transforming market observations into tradable signals. Recent LLM-based methods have shown promise in automating factor generation, but most of them still rely on prompt-level generation–evaluation–feedback […]
Evaluating Design Video Generation: Metrics for Compositional Fidelity
arXiv:2605.16223v1 Announce Type: cross Abstract: Generative video models are increasingly used in design animation tasks, yet no standardized evaluation framework exists for this domain. Unlike natural video generation, design animation imposes structured constraints: specific components shall animate with prescribed motion types, directions, speed and timing, while non-animated regions must remain stable and layout structure must […]
Navigating Potholes with Geometry-Aware Sharpness Minimization
arXiv:2605.16134v1 Announce Type: cross Abstract: Sharpness-aware minimization (SAM) encourages flat minima by perturbing parameters along directions of high loss curvature, but treats all parameter directions uniformly, ignoring the underlying loss geometry. We introduce LLQR+SAM, which combines SAM with a learned preconditioner obtained from the recently proposed LLQR framework, a second-order method that recasts steepest descent […]
SDOF: Taming the Alignment Tax in Multi-Agent Orchestration with State-Constrained Dispatch
arXiv:2605.15204v1 Announce Type: new Abstract: Multi-agent orchestration frameworks such as LangChain, LangGraph, and CrewAI route tasks through graph-based pipelines but do not enforce the stage constraints that govern real business processes. We present SDOF, a framework that treats multi-agent execution as a constrained state machine. SDOF operates through two primary defensive layers, implemented by three […]
Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schr”odinger Samplers
arXiv:2605.16126v1 Announce Type: cross Abstract: For a fixed flow-based generative model under a small inference budget, sample quality can depend strongly on where the sampler spends its few function evaluations. Flow matching and Schr”odinger bridges define probability paths, yet their inference grids are usually heuristic or inherited from one-endpoint diffusion. We derive a conditional-marginal entropy-rate […]
Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning
arXiv:2605.15315v1 Announce Type: new Abstract: LLM-powered coding agents spend the majority of their token budget reading repository files, yet much of the retrieved code is irrelevant to the task at hand. Existing learned pruners compress this context with a single-objective sequence labeler, collapsing all facets of code relevance into one score and one transition matrix. […]
CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
arXiv:2605.15120v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving planners are commonly trained by imitating a single logged trajectory, yet evaluated by rule-based planning metrics that measure safety, feasibility, progress, and comfort. This creates a training–evaluation mismatch: trajectories close to the logged path may violate planning rules, while alternatives farther from the demonstration can remain valid […]
Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
arXiv:2605.15416v1 Announce Type: cross Abstract: Jung et al. (2025) introduce a hypothesis testing framework for guaranteeing agreement between large language models (LLMs) and human judgments, relying on the assumption that the model’s estimated confidence is monotonic with respect to human-disagreement risk. In practice, however, this assumption may be violated, and the generalization behavior of the […]
DeepSlide: From Artifacts to Presentation Delivery
arXiv:2605.15202v1 Announce Type: new Abstract: Presentations are a primary medium for scholarly communication, yet most AI slide generators optimize the artifact (a visually plausible deck) while under-optimizing the delivery process (pacing, narrative, and presentation preparation). We present DeepSlide, a human-in-the-loop multi-agent system that supports preparing the full presentation process, from requirement elicitation and time-budgeted narrative […]