8958 papers
This paper introduces MERA, a novel retrieval-augmented multimodal framework that combines hierarchical multi-expert gating with a reliability-aware fusion strategy based on Dempster-Shafer theory to achieve state-of-the-art performance in protein active site identification.
This paper introduces CLEO, a system enabling real-time collaborative context awareness for human-agent co-creation, and presents a decision model derived from two user studies that clarifies when designers should delegate, direct, or work concurrently with AI agents based on process visibility and interaction patterns.
This paper introduces Whisper-RIR-Mega, a benchmark dataset pairing clean LibriSpeech utterances with real room impulse responses to evaluate and demonstrate the performance degradation of various Whisper models under reverberant conditions, while providing open-source resources for reproducible research on robust ASR.
This paper introduces RigidSSL, a rigidity-aware self-supervised learning framework that pretrains on static and dynamic protein structures using a bi-directional flow matching objective to jointly optimize geometric understanding and conformational dynamics, thereby significantly improving protein designability, novelty, and the modeling of realistic conformational ensembles.
This paper proposes a neuro-symbolic approach that synergistically integrates Large Language Models with constraint solvers to iteratively generate and verify auxiliary lemmas, thereby significantly improving the ability to solve constraints involving inductive definitions compared to state-of-the-art solvers.
This paper presents a multi-source qualitative study that identifies four key themes—AI Governance and Human Authority, Human-in-the-Loop Iterative Refinement, AI System Lifecycle and Operational Constraints, and Human-AI Team Collaboration and Coordination—to address the fragmented operational guidance for structuring human roles and oversight in AI application development.
This paper introduces "Companion," an embodied AI system that integrates a drawing robot with Large Language Models to facilitate bidirectional, speech-and-sketch-based co-creation, transforming the robot from a passive tool into a playful artistic partner capable of generating professionally recognized visual stories.
Through an exploratory design study with researchers, this paper identifies key friction points in systematic literature reviews and introduces ARC, a design probe that integrates multi-database search and transparent AI assistance to reduce administrative burden and enable strategic, verifiable scholarly exploration.
This paper proposes "Traversal-as-Policy," a framework that distills sandboxed execution logs into verifiable Gated Behavior Trees to replace implicit LLM policies with explicit, state-conditioned macro traversals, thereby significantly improving success rates, eliminating safety violations, and reducing computational costs across diverse autonomous agent benchmarks.
RoboLayout is a differentiable 3D scene generation framework that extends LayoutVLM by integrating explicit reachability constraints and a local refinement stage to create semantically coherent, physically feasible indoor environments tailored to the specific capabilities of diverse embodied agents.
This paper provides a guide for NLP researchers and interdisciplinary scientists on popular digital molecular representations inspired by natural language processing and their applications in AI-driven chemistry and materials science.
The paper introduces Omni-C, a single dense Transformer encoder that compresses heterogeneous modalities (text, audio, and image) into shared representations via unimodal contrastive pretraining, thereby eliminating the parameter overhead and routing complexity of Mixture-of-Expert architectures while achieving comparable performance with significantly reduced memory usage.
This paper introduces NGDBench, a comprehensive benchmark designed to evaluate neural models' ability to manage and query structured graph data across diverse domains using the full Cypher language, revealing significant current limitations in reasoning and robustness despite the models' success with unstructured text.
This study evaluates the Boltz-2 AI model for drug discovery and finds that while it offers rapid structural predictions, it lacks the energetic accuracy and resolution required for reliable lead identification, necessitating the continued use of physics-based methods for refinement.
The paper introduces JAWS, a probabilistic regularization strategy that dynamically modulates Jacobian constraints based on local physical complexity to resolve the contraction-dissipation dilemma, thereby enabling memory-efficient, short-horizon optimization to achieve superior long-term stability and accuracy in neural operator rollouts for dynamical systems.
VDCook is a self-evolving, configurable video data operating system that enables researchers and domain teams to automatically generate, update, and manage specialized video training datasets for MLLMs through natural language queries, integrated retrieval-synthesis modules, and automated metadata annotation.
This paper examines how the rapid advancement of AI, particularly with foundation models and unstructured data, introduces new challenges in latency, scalability, and interpretability for human-data interaction, arguing for a paradigm shift that redefines human-machine roles and integrates cognitive and perceptual principles to build more effective, human-centered analytical systems.
The paper introduces EigenData, a self-evolving multi-agent platform that automates the synthesis, auditing, and repair of high-quality function-calling training data, demonstrating its effectiveness by systematically correcting the Berkeley Function-Calling Leaderboard (BFCL-V3) to achieve model rankings that better correlate with human judgments of functional correctness.
This paper demonstrates that the Continuous-Time Koopman Autoencoder (CT-KAE) serves as a lightweight, stable, and efficient surrogate model for long-horizon ocean state forecasting, outperforming autoregressive Transformer baselines by maintaining bounded errors and consistent large-scale statistics over 2083-day rollouts while enabling resolution-invariant predictions.
This paper introduces a formal framework for "model change" in description logic concepts, distinguishing between eviction, reception, and revision, and demonstrates that revision is a distinct operation that cannot be simply reduced to a combination of the other two while analyzing their compatibility within EL and ALC logics.