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

Beyond Information Seeking: Severity-Aware Question Supervision for Proactive Medical Dialogue taaft Proactive medical dialogue requires an agent to decide what to ask from incomplete patient informat… 2026-08-25 published
Beyond Landmark Extraction: A Framework for Robust Geometric Feature Construction in Structured Image Classification taaft Much of the literature on structured image recognition has disproportionately focused on the compar… 2026-09-01 published
Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM taaft Existing research on object hallucination in multimodal large language models (MLLMs) predominantly… 2026-08-31 published
Beyond Magnitude: Contrastive Routing for Modular Mixture-of-Experts taaft In current Mixture-of-Experts architectures, routing is performed based on representations dominate… 2026-09-01 published
Beyond Modality Harmony: Orthogonal Purification and Topology-Guided MoE for Conflict-Aware Multimodal Recommendation taaft Multimodal Recommender Systems (MRSs) typically rely on a flawed "modality harmony" assumption, pre… 2026-09-02 published
Beyond Optimal Rates in Stochastic Optimization: Trajectory-Adaptive Stopping Rules taaft Stochastic gradient descent (SGD) is typically analyzed at a deterministic horizon chosen before th… 2026-08-26 published
Beyond Outcome Gaps: Process-Aware Fairness Diagnosis for LLM-based Multi-Agent Decision Systems taaft LLM-based multi-agent systems (MAS) are increasingly considered for high-stakes decision-making, ye… 2026-09-02 published
Beyond Pairwise Graphs in Science: Hypergraph Adaptive Wavelet Operators for Parametric PDEs taaft Physical systems are often modeled by solution operators that map input fields, parameters, geometr… 2026-08-28 published
Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting taaft Block drafters propose several tokens in one forward pass, before earlier target tokens are realise… 2026-08-27 published
Beyond Polarization: The Generative Constraint of Chain-of-Thought in Pointwise Reranking taaft In pointwise document reranking, Chain-of-Thought models typically underperform direct scoring mode… 2026-08-31 published
Beyond Problem Solving: Large Language Models for Emotional and Reflective Support in Mathematics Learning taaft Intelligent Tutoring Systems (ITSs) traditionally focus their adaptive support on cognitive aspects… 2026-09-02 published
Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training taaft Synthetic textbook data has improved language model pre-training, but prior work largely treats the… 2026-07-30 published
Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding taaft Streaming video understanding requires multimodal large language models (MLLMs) to process continuo… 2026-09-03 published
Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph Memory taaft Hardware kernel optimization requires repeated compilation, correctness testing, profiling, and rev… 2026-08-26 published
Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization Evaluation taaft LLM-based evaluators of natural language generation (NLG) quality are widely deployed as scoring to… 2026-09-01 published
Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess taaft Searchless chess networks reach human master strength from a single forward pass by imitating a str… 2026-08-27 published
Beyond Semantic Accuracy: Consequence-Aware Evaluation for Safety-Critical Language Understanding taaft Can language models be trusted in safety- critical operations? In such settings, strong per- forman… 2026-08-25 published
Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness taaft How do the methods used to train language models to refuse harmful requests shape how that refusal… 2026-09-03 published
Beyond Small Patches: Black-Box Detection and Purification of Diverse Backdoor Triggers taaft Deep neural networks (DNNs) are increasingly deployed in real-world vision systems, yet their predi… 2026-09-02 published
Beyond Stationarity in Time Series: Discovering Causal Structures and Latent Regimes via Markov Blankets taaft This paper introduces Regime-aware Constraint-Based and Noise-Based causal discovery with Markov Bl… 2026-09-04 published
Beyond Straightness: Non-Crossing Flow Matching via Quantile AlignTree Coupling taaft The performance of Flow Matching largely depends on the quality of the coupling between the source… 2026-09-03 published
Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving taaft Chain-of-thought (CoT) reasoning powers generative models by eliciting intermediate steps before pr… 2026-08-31 published
Beyond the Editing Canvas: Evidence Divergence in OOXML-to-LLM Ingestion taaft LLM pipelines increasingly ingest Office Open XML (OOXML) documents (Word, Excel, and PowerPoint fi… 2026-08-26 published
Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training taaft Recent advances in video generation models have achieved impressive results. However, these models… 2026-03-26 published
Beyond the Image Plane: World-Grounded Queries for Multi-Object Tracking taaft Monocular videos record 3D scenes as sequences of 2D image-plane projections, obscuring depth and s… 2026-09-01 published
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models Amazon Language models demonstrate both quantitative improvement and new qualitative capabilities with inc… 2022-06-09 published
Beyond the Payload: How User Invocation Shapes Coding Agent Vulnerability to Repository Poisoning taaft Coding agents are increasingly used for software engineering tasks, including bootstrapping project… 2026-08-31 published
Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models taaft Diffusion large language models (dLLMs) generate text through iterative denoising rather than left-… 2026-08-31 published
Beyond Uncertainty: Multi-Solver Disagreement Rewards for Self-Evolving Reasoning Curricula taaft Self-evolving reasoning frameworks train a Challenger to generate questions exposing a Solver's wea… 2026-08-30 published
Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR taaft Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) for multimodal large langu… 2026-03-27 published
BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network taaft Generative adversarial network (GAN)-based vocoders have been intensively studied because they can… 2023-09-06 published
Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature taaft Text watermarks for large language models (LLMs) have been commonly used to identify the origins of… 2024-06-04 published
Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems taaft Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and… 2026-09-02 published
Billion-scale similarity search with GPUs Meta Platforms Similarity search finds application in specialized database systems handling complex data such as i… 2017-02-28 published
BiMix: A Bivariate Data Mixing Law for Language Model Pretraining taaft Large language models have demonstrated remarkable capabilities across various tasks, primarily att… 2024-05-23 published
Bioinfoysis Technical Report taaft Large language model agents have shown promise in bioinformatics, but most existing systems focus p… 2026-09-03 published