arXiv AI
Aug 17
Content Based Video Narration of Gameplay with Vision Language Models
arXiv:2608. 14016v1 Announce Type: cross Abstract: Live game commentary is scarce: it exists for professional esports broadcasts and almost nowhere else.
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv AI
Aug 17
Depth-Aware Sensitivity Analysis of Mixture-of-Experts Models via Magnitude-Based Expert Masking
arXiv:2608. 13565v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale large language models (LLMs) while preserving computational efficiency through sparse activation.
arXiv AI
Aug 17
Engineering Signals of Human-AI Collaboration in the Agentic Coding Era: A Longitudinal Analysis of 33,228 Pull Requests from vLLM and SGLang with Implications for Biomedical AI Agents and Bioinformatics Pipeline Developmen
arXiv:2608. 13884v1 Announce Type: cross Abstract: The rapid adoption of AI coding assistants and autonomous agentic development systems has coincided with major changes in the pace and structure of open-source software engineering.
arXiv AI
Aug 17
Self-Supervised Visual On-Policy Distillation
arXiv:2608. 14144v1 Announce Type: cross Abstract: Visual on-policy distillation relies heavily on an informative teacher-student asymmetry, through either a larger, stronger teacher or privileged supervision, such as reference answers or ground-truth regions of interest.
arXiv Machine Learning
Aug 17
Learning-Guided Sparsification of Dynamic Graphs in Robotic Exploration
arXiv:2604. 16509v2 Announce Type: replace-cross Abstract: Many robotic exploration algorithms rely on graph structures for frontier-based exploration and dynamic path planning.
arXiv AI
Aug 17
ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models
arXiv:2608. 14022v1 Announce Type: cross Abstract: Action-conditioned video world models require low-latency causal generation and reliable responses to game-native controls.
arXiv AI
Aug 17
Correcting What You Cannot See: Credit Assignment for Perception Distillation in Multimodal Reasoners
arXiv:2607. 28336v3 Announce Type: replace Abstract: On-policy distillation provides dense supervision for multimodal reasoners, but its trajectory-level reward cannot determine whether a failed answer arose from perception or subsequent reasoning.
arXiv AI
Aug 17
VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning
arXiv:2604. 09508v2 Announce Type: replace-cross Abstract: Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents.
Simon Willison
Aug 16
Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things
Friday's big release was Qwen 3. 8 27B , an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba's Qwen research lab.
Hugging Face Trending Papers
Aug 16
Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discovery
Retrieval-Augmented Generation over knowledge graphs (Graph-RAG) has emerged as a powerful paradigm for grounding large language models in domain-specific corpora. However, existing systems face persi...
Hugging Face Trending Papers
Aug 16
GraniKV: Asymmetric Granularity KV-Cache Paging for Multi-Agent Systems with Long Shared Prefix
Production paged-serving engines apply uniform paging granularity to the KV cache, even though the two regions of a multi-agent workload have opposite storage requirements: a long shared prefix demand...
Hugging Face Trending Papers
Aug 16
Dynamic Multi-Byte Prediction With Hierarchical Language Models
Byte-level hierarchical language models (LMs) have recently emerged as a robust alternative to their popular counterparts that use subword tokenization. However, generating one byte at a time remains...
Hugging Face Trending Papers
Aug 15
TRACE-BN: Transferring Bangla-English Tutoring Behavior to a Sub-1B Offline Language Model
Bangla-English tutoring requires more than producing a correct translation: learners also need explanations of grammar differences, awareness of their likely errors, and targeted practice. We present...
Hugging Face Trending Papers
Aug 14
Towards Efficient Multimodal and Multilingual Opinion Extraction for STI: A QLoRA-Based Fine-Tuning Approach
Recent advances in large language models (LLMs) have reshaped semantic analysis. Opinion Extraction (OE) for Science and Technology Intelligence (STI) requires concise core opinions from large information streams.
Hugging Face Trending Papers
Aug 14
QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction
As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model...
arXiv Machine Learning
Aug 14
Subtract, Transport, or Replay? Auditable Deletion from Language-Model Memory
arXiv:2607. 27539v2 Announce Type: replace Abstract: Exact deletion from persistent language-model memory depends on whether a record's effect remains addressable after later computation.
arXiv Machine Learning
Aug 14
Training Under Challenge: Executable Certificates and Challenge-Closed Optimality for Neural Networks
arXiv:2608. 12655v1 Announce Type: new Abstract: A flat training curve does not reveal whether a neural network has reached a global optimum, is locally trapped, is representation-limited, or is mismatched to its trainer.
arXiv AI
Aug 14
EGRL: Edge generation-guided relation-aware learning for RNA-protein interaction prediction
arXiv:2608. 12906v1 Announce Type: cross Abstract: RNA-Protein Interactions (RPIs) are critical for regulating cellular functions.
arXiv Machine Learning
Aug 14
Intern-S2-Preview: Scientific Agentic Foundation Model
arXiv:2608. 13505v1 Announce Type: new Abstract: Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and environments, and sustain progress across long task horizons.
arXiv Machine Learning
Aug 14
I-SDPO: Instance-Level Adaptive Self-Distillation Policy Optimization
arXiv:2608. 12957v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) learns from reward differences within a rollout group, but receives no useful relative signal when every sampled response is incorrect.