arXiv:2605.14457v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) reasoning has become a foundation for eliciting multi-step reasoning in large language models, but recent studies show that its benefits do not scale monotonically with chain length: while longer CoT generally enables a model to tackle harder problems, on a given problem, accuracy typically increases with CoT length […]
DCFold: Efficient Protein Structure Generation with Single Forward Pass
arXiv:2605.17899v1 Announce Type: cross Abstract: AlphaFold3 introduces a diffusion-based architecture that elevates protein structure prediction to all-atom resolution with improved accuracy. This state-of-the-art performance has established AlphaFold3 as a foundation model for diverse generation and design tasks. However, its iterative design substantially increases inference time, limiting practical deployment in downstream settings such as virtual screening […]
RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
arXiv:2509.21319v3 Announce Type: replace-cross Abstract: Reinforcement Learning with Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) are the main RL paradigms used in LLM post-training, each offering distinct advantages. However, RLHF struggles with interpretability and reward hacking because it relies on human judgments that usually lack explicit criteria, whereas RLVR is limited in […]
Probing Persona-Dependent Preferences in Language Models
arXiv:2605.13339v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can be said to have preferences: they reliably pick certain tasks and outputs over others, and preferences shaped by post-training and system prompts appear to shape much of their behaviour. But models can also adopt different personas which have radically different preferences. How is this implemented […]
SuReNav: Superpixel Graph-based Constraint Relaxation for Navigation in Over-constrained Environments
arXiv:2602.06807v2 Announce Type: replace-cross Abstract: We address the over-constrained planning problem in semi-static environments. The planning objective is to find a best-effort solution that avoids all hard constraint regions while minimally traversing the least risky areas. Conventional methods often rely on pre-defined area costs, limiting generalizations. Further, the spatial continuity of navigation spaces makes it […]
Attention Sinks and Outliers in Attention Residuals
arXiv:2605.17887v1 Announce Type: cross Abstract: We propose OASIS, an outlier- and sink-aware technique built on inter-layer null signaling. As AttnResidual architectures introduce an additional depth-wise normalization channel, they improve inter-layer routing flexibility but also exacerbate attention sinks, activation outliers, and the resulting degradation in inference stability and quantization robustness. OASIS addresses this issue by introducing […]
Black-Box Optimization From Small Offline Datasets via Meta Learning with Synthetic Tasks
arXiv:2604.12325v2 Announce Type: replace-cross Abstract: We consider the problem of offline black-box optimization, where the goal is to discover optimal designs (e.g., molecules or materials) from past experimental data. A key challenge in this setting is data scarcity: in many scientific applications, only small or poor-quality datasets are available, which severely limits the effectiveness of […]
BLAgent: Agentic RAG for File-Level Bug Localization
arXiv:2605.17965v1 Announce Type: cross Abstract: Bug localization remains a key bottleneck in downstream software maintenance tasks, including root cause analysis, triage, and automated program repair (APR), despite recent advances in large language model (LLM)-based repair systems. File-level bug localization is especially critical in hierarchical pipelines, where errors can propagate to downstream stages such as statement-level […]
Multi-agent AI systems outperform human teams in creativity
arXiv:2605.17885v1 Announce Type: cross Abstract: Although artificial intelligence (AI) now matches or exceeds human performance across numerous cognitive tasks, creativity remains a highly contested frontier. As AI systems based on large language models (LLMs) are increasingly adopted in research and innovation, it is essential to understand and augment their creativity. Here we demonstrate that multi-agent […]
TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model
arXiv:2605.18013v1 Announce Type: cross Abstract: Segment Anything Model 2 (SAM 2) serves as a core foundation model in the field of video segmentation. Building upon the original SAM model, it introduces a memory bank mechanism and demonstrates outstanding performance in tasks such as semi-supervised video object segmentation and tracking anything. However, the complex computational characteristics […]
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
arXiv:2605.12825v2 Announce Type: replace-cross Abstract: We introduce Orthrus, a simple and efficient dual-architecture framework that unifies the exact generation fidelity of autoregressive Large Language Models (LLMs) with the high-speed parallel token generation of diffusion models. The sequential nature of standard autoregressive decoding represents a fundamental bottleneck for high-throughput inference. While diffusion language models attempt to […]
Subject-Specific Analysis of Self-Initiated Attention Shifts from EEG with Controlled Internal and External Attention Conditions
arXiv:2605.18251v1 Announce Type: cross Abstract: Self-initiated attention shifts play a critical role in voluntary behavior but are difficult to study due to the absence of explicit temporal markers. While previous studies have examined their neural correlates, it remains unclear how multi-dimensional electroencephalography (EEG) features contribute to their characterization within an interpretable computational framework. In this […]