Papers

3,241 in the directory.

Browse AI research papers and methods. Search paper profiles, read recorded summaries and follow source links for the full research.

A–Z Recently synced

WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editing taaft Image generation and editing models have advanced rapidly, yet remain unreliable when prompts requi… 2026-09-04 published
WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents taaft Multimodal search agents extend parametric knowledge with newly emerging and long-tail evidence fro… 2026-08-28 published
Weak-to-Strong Generalization via Direct On-Policy Distillation taaft Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-m… 2026-07-06 published
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision OpenAI Widely used alignment techniques, such as reinforcement learning from human feedback (RLHF), rely o… 2023-12-14 published
WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data taaft Recent advances in wearable sensing enable continuous monitoring of physiological and behavioral si… 2026-09-04 published
Weather-Conditioned Depth Anything taaft Monocular depth estimation foundation models, such as the Depth Anything series, have achieved rema… 2026-09-04 published
WeatherNext 3: Increasing resolution and performance of global weather models with raw observations taaft State-of-the-art AI weather models have shown impressive medium-range forecast skill and computatio… 2026-09-03 published
WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading taaft Multi-bit watermarking for large language models enables content source tracing by embedding user-i… 2026-09-02 published
Web Price Extraction: State of the Art and an Adaptive Browserless Implementation taaft Price extraction from websites is a key task for market monitoring, price comparison, and business… 2026-09-01 published
WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents taaft The emerging W3C WebMCP proposal enables LLM agents to invoke tools exposed by web pages. In multi-… 2026-08-25 published
WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts taaft Existing benchmarks for MLLM-generated web artifacts assess interaction through local evidence and… 2026-06-02 published
WebWorld: The Browser as a World Model for Self-Improving Web Code taaft VLM-driven self-improvement of web code has a structural flaw: the model that proposes the repair i… 2026-08-31 published
WEECFP-SuRGE: Wide Embedded Extended Connectivity Fingerprint with Substructure Rotary Graph-distance Encoding taaft Computational molecular property prediction requires representations that capture local chemistry,… 2026-09-04 published
Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric taaft In typical multimodal contrastive learning, such as CLIP, encoders produce one point in the latent… 2024-04-30 published
What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams taaft Open domain question answering (OpenQA) tasks have been recently attracting more and more attention… 2020-09-28 published
What Do CAE Simulation Agents Really Need Beyond a Generic Harness? taaft Computer-aided engineering (CAE) simulation is among the largest and most demanding areas of engine… 2026-09-03 published
What Do Medical Vision-Language Models Learn in Radiology? Transfer, Alignment, and Source-Proxy Leakage Under Distribution Shift taaft Medical vision-language models (VLMs) can appear reliable in-domain while failing when acquisition… 2026-08-26 published
What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation taaft Large Language Models (LLMs) often help users generate artifacts through iterative cycles of genera… 2026-09-03 published
What Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions taaft LLM agents integrated with external resources gain complex task capabilities, yet the unified natur… 2026-08-25 published
What is Smoothness? taaft Smoothness of a function on the real line is reflected in the decay of its Fourier transform, which… 2026-09-03 published
What Is Worth Representing? Representational Empowerment for Continual Model Construction taaft The first problem of modeling the world is not just estimating the right parameters or causal struc… 2026-09-02 published
What Makes Agent Memory Useful for Reliable Unanswerable Question Handling? taaft Reliable handling of unanswerable questions (UAQs) is critical for trustworthy LLM-based agents. Al… 2026-08-28 published
What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents taaft LLM agents increasingly rely on generated interaction data to learn how to interact with external e… 2026-08-27 published
What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning taaft Instruction tuning is a standard technique employed to align large language models to end tasks and… 2023-12-25 published
What Matters for Aggressive Decoding-Time KV Eviction? Temporal Aggregation and Ranking Preservation taaft Decoding-time KV cache compression research focuses heavily on designing better token scoring funct… 2026-09-03 published
What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection taaft On-Policy Distillation (OPD) has emerged as a widely adopted post-training paradigm for enhancing l… 2026-09-04 published
What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies taaft Visuomotor imitation policies can achieve high performance under in-distribution visual conditions… 2026-09-04 published
What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models taaft Self-supervised video foundation models learn rich spatiotemporal representations, yet it remains u… 2026-09-01 published
When 3D Gaussian Splatting Recovers Real Surfaces taaft When does 3D Gaussian Splatting (3DGS) recover the true scene surface rather than just overfitting… 2026-08-30 published
When Agents Implement Systems: A Case Study in Defects, Detection, and Evaluation Rigor taaft As LLM coding agents increasingly perform end-to-end engineering work, we lack empirical characteri… 2026-09-02 published
When AI Shows Its Work, Is It Actually Working? Step-Level Evaluation Reveals Frontier Language Models Frequently Bypass Their Own Reasoning taaft Language models increasingly show their work by writing step-by-step reasoning before answering. Bu… 2026-03-24 published
When an AI searches for the equation behind your data, one dial steers it Transformer Lab Trains a small RL model for symbolic regression on the Feynman equations benchmark. The simplicity… Transformer Lab
When Can a Machine Trust a Statute? A Survival Certificate for Machine-Extracted Legal Logic taaft Statutes are increasingly parsed by machines before people read them, and the parsers disagree: on… 2026-09-01 published
When Decodability Is Not Enough: Logical Validity Representations, Behavioral Dissociation, and Causal Tests in Language Models taaft Large language models can look capable of logical reasoning, but correct or incorrect answers alone… 2026-09-02 published
When Do Anchor-Based Pointwise LLM Rerankers Help? Retriever Quality, Statistical Scope, and Anchor Design taaft Anchor-based pointwise LLM reranking scores each candidate against a shared reference passage to re… 2026-08-11 published
When Do Frozen VLMs Respond to Image-Free Object-Token Edits? An Answer-Key-Free Protocol and What It Reveals taaft Answering what-if queries about a scene with a VLM usually means injecting the assumption as text o… 2026-09-03 published