arXiv:2506.23287v2 Announce Type: replace-cross Abstract: In single-cell research, tracing and analyzing high-throughput single-cell differentiation trajectories is crucial for understanding biological processes. Key to this is the robust modeling of hierarchical structures that govern cellular development. Traditional methods face limitations in computational cost, performance, and stability. VAE-based approaches have made strides but still require branch-specific network […]
Towards Reliable LLM Evaluation: Correcting the Winner’s Curse in Adaptive Benchmarking
arXiv:2605.05973v1 Announce Type: cross Abstract: Adaptive prompt and program search makes LLM evaluation selection-sensitive. Once benchmark items are reused inside tuning, the observed winner’s score need not estimate the fresh-data performance of the full tune-then-deploy procedure. We study inference for this procedure-level target under explicit tuning budgets. We propose SIREN, a selection-aware repeated-split reporting protocol […]
Milestone-Guided Policy Learning for Long-Horizon Language Agents
arXiv:2605.06078v1 Announce Type: cross Abstract: While long-horizon agentic tasks require language agents to perform dozens of sequential decisions, training such agents with reinforcement learning remains challenging. We identify two root causes: credit misattribution, where correct early actions are penalized due to terminal failures, and sample inefficiency, where scarce successful trajectories result in near-total loss of […]
A Review of Large Language Models for Stock Price Forecasting from a Hedge-Fund Perspective
arXiv:2605.05211v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in quantitative finance for stock price forecasting. This review synthesizes recent applications of LLMs in this domain, including extracting sentiment from financial news and social media, analyzing financial reports and earnings-call transcripts, tokenizing or symbolizing stock price series, and constructing multi-agent trading systems. […]
PPO-Based Dynamic Positioning of HAPS-BS in Wind-Disturbed Stratospheric Maritime Networks
arXiv:2605.05240v1 Announce Type: cross Abstract: High-Altitude Platform Stations (HAPS) offer a promising solution for wide-area wireless coverage in maritime regions lacking terrestrial infrastructure. However, maintaining reliable performance is challenging due to dynamic ship mobility and atmospheric disturbances, particularly stratospheric wind effects on HAPS positioning. This paper proposes a deep reinforcement learning (DRL)-based framework for dynamic […]
Feature Starvation as Geometric Instability in Sparse Autoencoders
arXiv:2605.05341v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are used to disentangle the dense, polysemantic internal representations of large language models (LLMs) into interpretable, monosemantic concepts. However, standard $ell_1$-regularized SAEs suffer from feature starvation (dead neurons) and shrinkage bias, often requiring computationally expensive heuristic resampling and nondifferentiable hard-masking methods to bypass these challenges. We argue […]
Robustness of Graph Self-Supervised Learning to Real-World Noise: A Case Study on Text-Driven Biomedical Graphs
arXiv:2605.05463v1 Announce Type: cross Abstract: Graph Self-Supervised Learning (GSSL) offers a powerful paradigm for learning graph representations without labeled data. However, existing work assumes clean, manually curated graphs. Recent advances in NLP enable the large-scale automatic extraction of knowledge graphs from text, opening new opportunities for GSSL while introducing substantial real-world noise. This type of […]
EGA: Adapting Frozen Encoders for Vector Search with Bounded Out-of-Distribution Degradation
arXiv:2605.05674v1 Announce Type: cross Abstract: Vector search systems built on frozen vision encoders face queries from unseen classes at deployment, yet existing adapter training collapses under this shift: high-capacity adapters with global contrastive losses silently reassign unseen-class samples to wrong seen-class clusters, dropping worst-case Label Precision by over 40 points below the frozen baseline in […]
Logic-Regularized Verifier Elicits Reasoning from LLMs
arXiv:2605.05893v1 Announce Type: cross Abstract: Verifiers are crucial components for enhancing modern LLMs’ reasoning capability. Typicalverifiers require resource-intensive superviseddataset construction, which is costly and faceslimitations in data diversity. In this paper, wepropose LOVER, an unsupervised verifier regularized by logical rules. LOVER treats theverifier as a binary latent variable, utilizinginternal activations and enforcing three logical constraints […]
Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven
arXiv:2605.06014v1 Announce Type: cross Abstract: Uniform random rotations (URRs) are a common preprocessing step in modern quantization approaches used for gradient compression, inference acceleration, KV-cache compression, model weight quantization, and approximate nearest-neighbor search in vector databases. In practice, URRs are often replaced by randomized Hadamard transforms (RHTs), which preserve orthogonality while admitting fast implementations. The […]
Autoregressive Visual Generation Needs a Prologue
arXiv:2605.06137v1 Announce Type: cross Abstract: In this work, we propose Prologue, an approach to bridging the reconstruction-generation gap in autoregressive (AR) image generation. Instead of modifying visual tokens to satisfy both reconstruction and generation, Prologue generates a small set of prologue tokens prepended to the visual token sequence. These prologue tokens are trained exclusively with […]
GlazyBench: A Benchmark for Ceramic Glaze Property Prediction and Image Generation
arXiv:2605.06641v1 Announce Type: new Abstract: Developing ceramic glazes is a costly, time-consuming process of trial and error due to complex chemistry, placing a significant burden on independent artists. While recent advances in multimodal AI offer a modern solution, the field lacks the large-scale datasets required to train these models. We propose GlazyBench, the first dataset […]