arXiv Machine Learning
Jun 8
Sparsely gated tiny linear experts
arXiv:2606. 07414v1 Announce Type: new Abstract: Sparsity allows scaling model parameters without proportionally increasing computational cost.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Jun 8
How reliable are LLMs when it comes to playing dice?
arXiv:2606. 07515v1 Announce Type: cross Abstract: We investigate the probabilistic reasoning capabilities of large language models through a controlled benchmarking study on discrete probability problems.
arXiv AI
Jun 8
STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation
arXiv:2606. 07036v1 Announce Type: cross Abstract: Synthetic histopathology image generation addresses critical challenges in computational pathology, including patient privacy and the growing need for large-scale training data for foundation models.
arXiv Machine Learning
Jun 8
Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes
arXiv:2606. 07127v1 Announce Type: new Abstract: Interactive agents trained only against task return can achieve high scores while failing to represent the mechanisms that make their actions succeed.
arXiv AI
Jun 8
Think Like a Pilot: Fine-Grained Long-Horizon UAV Navigation
arXiv:2606. 06836v1 Announce Type: cross Abstract: Language-guided UAV agents must execute long-horizon semantic instructions while producing smooth, physically feasible continuous flight commands, yet existing Vision-Language Navigation (VLN) benchmarks typically use discrete or coarse actions and existing UAV Vision-Language-Action (VLA) tasks focus on short, atomic maneuvers.
arXiv Machine Learning
Jun 8
$\alpha$-PFN: Fast Entropy Search via In-Context Learning
arXiv:2606. 07134v1 Announce Type: new Abstract: Information-theoretic acquisition functions such as Entropy Search (ES) offer a principled exploration-exploitation framework for Bayesian optimization (BO).
arXiv AI
Jun 8
VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models
arXiv:2602. 03160v2 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with the diverse spectrum of human values remains a central challenge: preference-based methods often fail to capture deeper motivational principles.
arXiv AI
Jun 8
Watch, Remember, Reason: Human-View Video Understanding with MLLMs
arXiv:2606. 07433v1 Announce Type: cross Abstract: Video understanding is being rapidly transformed by multimodal large language models (MLLMs), as research moves from short clips to long, multimodal, and knowledge-intensive video scenarios.
arXiv AI
Jun 8
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
arXiv:2606. 07412v1 Announce Type: cross Abstract: LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-quality SWE tasks.
arXiv AI
Jun 8
HKJudge: A Legal Discourse-Annotated Corpus for Interpreting What Courts Find, How They Reason, and What They Rule
arXiv:2606. 06679v1 Announce Type: cross Abstract: Court judgments are central to legal practice and jurisprudence, yet discourse analysis of Hong Kong judgments has received limited attention, owing largely to the absence of expert-annotated corpora.
arXiv AI
Jun 8
Human Adults and LLMs as Scientists: Who Benefits from Active Exploration?
arXiv:2606. 06464v1 Announce Type: cross Abstract: A long-standing finding in the causal learning literature is that adults struggle to identify conjunctive causal rules, where an effect requires the simultaneous presence of multiple causes, while performing better in disjunctive settings.
arXiv AI
Jun 8
Endogenous Resistance to Activation Steering in Language Models
arXiv:2602. 06941v2 Announce Type: replace-cross Abstract: Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.
arXiv Machine Learning
Jun 8
Trace Reconstruction with Language Models
arXiv:2507. 12927v2 Announce Type: replace Abstract: The general trace reconstruction problem seeks to recover an original sequence from its noisy copies independently corrupted by insertions, deletions, and substitutions.
arXiv AI
Jun 8
Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
arXiv:2604. 17433v2 Announce Type: replace-cross Abstract: Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but it comes at a high computational cost due to extensive sampling.
arXiv AI
Jun 8
Beyond Post-hoc Explanation: Toward Glassbox AI via Probabilistic Mediation
arXiv:2606. 07113v1 Announce Type: new Abstract: Large language models are rapidly becoming infrastructural components in high-stakes institutional settings, including public administration, legal reasoning, and healthcare, where opacity is not merely inconvenient but institutionally and legally untenable.
arXiv Machine Learning
Jun 8
CF-JEPA: Mask-free forward prediction with asymmetric encoder utilization for time-series representation learning
arXiv:2606. 07031v1 Announce Type: new Abstract: Self-supervised learning (SSL) for time-series representation learning is dominated by two paradigms: contrastive methods, which face challenges in constructing positive or negative pairs, and masking-based methods, which disrupt the temporal continuity of time-series signals.
arXiv AI
Jun 8
On the Geometry of On-Policy Distillation
arXiv:2606. 07082v1 Announce Type: cross Abstract: On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood.
arXiv Machine Learning
Jun 8
Breaking the Tuning Barrier: Zero-Hyperparameters Yield Multi-Corner Analysis Via Learned Priors
arXiv:2603. 13092v2 Announce Type: replace Abstract: Yield Multi-Corner Analysis validates circuits across 25+ Process-Voltage-Temperature corners, resulting in a combinatorial simulation cost of $O(K \times N)$ where $K$ denotes corners and $N$ exceeds $10^4$ samples per corner.
arXiv AI
Jun 8
Queen-Bee Agents: A BeeSpec-Centered Architecture for Governed Enterprise MCP Orchestration
arXiv:2606. 06545v1 Announce Type: cross Abstract: Enterprise agent systems increasingly need to connect large language models to private tools, internal knowledge, and Model Context Protocol (MCP) interfaces.
arXiv AI
Jun 8
Beyond Output Matching: Preserving Internal Geometry in NVFP4 LLM Distillation
arXiv:2606. 05682v2 Announce Type: replace Abstract: Demand for low-precision inference, including NVFP4-based approaches, has grown as large language models are increasingly deployed in latency and cost constrained production environments.