Autonomous Scientific Discovery via Iterative Meta-Reflection
Autonomous scientific discovery systems offer the potential to accelerate research by automating the process of hypothesis generation and validation. However, current systems opera...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement
As video corpora continue to expand in both scale and task complexity, there is increasing demand for approaches that retrieve relevant videos from large-scale corpora (inter-video...
RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue
Open-source libraries and tools are widely reused, but compatibility maintenance is expensive. Once maintainers leave, useful repositories can stop working as runtimes and dependen...
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 ...
Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks
Lightweight machine learning models are increasingly proposed for intrusion detection in Industrial Internet of Things (IIoT) networks due to their suitability for resource-constra...
Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?
Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime a...
RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules
We present RuleChef, a framework that uses large language models (LLMs) to generate executable rules for NLP tasks such as text classification, Named Entity Recognition (NER), or r...
When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers
LLM agents increasingly rely on retrieval buffers to store and reuse past experience, yet the cache management policies governing these buffers remain largely ad-hoc. We formalize ...
Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination
Accelerating materials discovery requires AI systems that can generate scientifically valid hypotheses through multi-step, domain-grounded reasoning. Standard large language models...
Discrete Diffusion Language Models for Interactive Radiology Report Drafting
Diffusion language models, which generate text by denoising a token canvas bidirectionally instead of emitting tokens left to right, have become competitive with autoregressive (AR...
CausalMix: Data Mixture as Causal Inference for Language Model Training
In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via proxy models, but they rely o...
Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts
Vision-Language-Action (VLA) models often fail to perform the same learned tasks under environmental shifts, such as changes in camera pose and shifts to a different but similar ro...
ABot-M0.5: Unified Mobility-and-Manipulation World Action Model
Mobile manipulation is a key capability for general-purpose robots, yet remains challenging for current embodied learning methods. VLA policies are typically reactive and lack expl...
Valdi: Value Diffusion World Models
World models can enable Model Predictive Control (MPC), but this requires dynamics prediction that is both fast enough for online use and expressive enough to represent uncertain f...
The State-Prediction Separation Hypothesis
Transformers use the same forward computation stream to both predict the next token and store useful state for future token predictions. We formulate the state-prediction separatio...
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Fine-grained visual reasoning remains challenging for vision-language models, especially when small but critical visual cues are buried in high-resolution images. Existing approach...
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 capture...
TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive
Generative models have achieved remarkable progress, yet applying them to satellite imagery remains challenging. Unlike natural imagery, satellite scenes are structured by spatiall...
PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking
This paper explores multi-turn visual reasoning and observes that MLLMs repeatedly fail to localize the target, leading to long, redundant trajectories. We attribute this failure t...
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. Suc...
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
We present Seed2.0, a model series that takes a meaningful step toward solving complex, real-world tasks. Our approach begins with identifying users' genuine needs and constructing...
ASPIRE: Agentic /Skills Discovery for Robotics
Traditional robot programming is challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling diverse configurations and execution...
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 ...
InstanceControl: Controllable Complex Image Generation without Instance Labeling
Controllable image generation methods, such as ControlNet, have demonstrated a remarkable capacity to introduce visual conditions(e.g., depth maps) to guide image generation. Howev...