ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
Research dissemination, turning a paper into a poster, a talk video, and a blog post, is still a manual last mile. Prior automation treats each artifact…
Papers 5469 stories
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testing targets expert-designed safety violations, and the…
Wan-Streamer v0.2: Higher Resolution, Same Latency
We present Wan-Streamer v0.2, a latency-preserving upgrade of the native-streaming, end-to-end audio-visual interaction model. v0.2 keeps the v0.1 modeling formulation, but raises the interactive output stream…
ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes
Large language models have made research ideation increasingly accessible, yet effective idea development requires more than generating candidate directions. Researchers must ground a problem in current…
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction
Repository-level vulnerability reproduction is a demanding software engineering (SE) task: an agent must inspect a codebase, infer the input grammar that reaches a vulnerable path, construct…
Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care
Specialist epilepsy expertise is scarce in resource-constrained settings, making LLM-based decision support attractive for frontline clinicians managing longitudinal treatment. Such systems must adapt to local prescribing…
Measuring the Gap Between Human and LLM Research Ideas
LLMs are increasingly used to brainstorm research ideas, but existing evaluations mostly judge individual ideas by novelty, feasibility, or expert preference. We instead ask: how far…
Generated Contents Enrichment
We study Generated Contents Enrichment (GCE), a conditional image-generation task in which a sparse scene description is first enriched through an explicit scene representation and then…
AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer
Depth-of-field control is a fundamental tool in photography, yet post-capture bokeh editing from a single image remains challenging. A practical editor should handle images captured under…
DataComp-VLM: Improved Open Datasets for Vision-Language Models
Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curation strategies. We introduce DataComp for…
Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment
Cloud removal (CR) is essential for optical remote sensing, serving as a prerequisite for reliable downstream interpretation, such as semantic segmentation and change detection. However, existing…
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training quantization (PTQ) is the natural…
MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering
As grounded QA systems are increasingly deployed in AI assistants, accurately attributing generated answers to evidence is critical for user trust and model safety. While unimodal…
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
Vision-Language-Action (VLA) foundation models have recently achieved strong progress in embodied intelligence. To reduce policy-call frequency while preserving temporal coherence, most generative policies adopt an action…
Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming
The fast growth of open-source AI infrastructure, from model serving engines and agent platforms to the Model Context Protocol (MCP) ecosystem and the language models themselves,…
AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation
GraphRAG is an extension of retrieval-augmented generation (RAG) that supports large language models (LLMs) by referring to graph-structured data as external knowledge. While this technique ideally…
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability or collapse. One…
Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots
Embodied AI models now span vision-language-action (VLA) models and world-action models (WAMs), but practical deployment remains fragmented across model-specific Python stacks, backend assumptions, and robot-side glue…
Scaling Laws for Grid-Based Approximate Nearest Neighbor Search in High Dimensions
Grid-based approaches to approximate nearest neighbor (ANN) search have been absent from modern scaling analyses. We present a systematic characterization of a multiprobe grid algorithm with…
Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting
Traffic matrices (TMs) capture network-wide origin-destination demand and are central to traffic engineering, yet accurate whole-matrix forecasting remains challenging when prediction must be performed under the…
WARP: Weight-Space Analysis for Recovering Training Data Portfolios
Foundation models are routinely released to the public, yet the data recipes used to train them -- such as domain mixture weights that determine how different…
AutoMem: Automated Learning of Memory as a Cognitive Skill
Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge--a capacity known in cognitive science as metamemory. We…
DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation
Large Language Model (LLM)-based agents can solve complex procedural tasks by interacting with environments over multiple turns, but this ability typically depends on large models, long…
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
In long-context use, large language models frequently synthesize answers from the meaning of a relevant context span rather than literally copy-pasting them. Identifying which attention heads…