Continuous audio encoders compress audio along feature and time axes through latent width and frame rate, but their joint effect on downstream performance remains unclear. We train sixteen encoders spanning four widths and four frame rates, with downstream adapters and probes, using matched training protocols. Despite...
Kyudan Jung, Sehyun Lee, Song-ha Jo et al.· 0 citations
As human--AI interactions become more conversational, full-duplex speech language models capable of natural real-time dialogue are growing in importance. Beyond generating appropriate responses, these models must coordinate turn-taking, backchanneling, and floor management in real time. Reinforcement learning (RL) prov...
Kyudan Jung, Hyunsin Park, Yoonhyung Lee et al.· 0 citations
Human hand-object demonstrations offer a reusable source of dexterous robot manipulation data, but transferring them across embodiments requires physically feasible retargeting. Existing physics-based approaches face limitations in retargeting success, motion-specific training efficiency, or both. To address these limi...
Kyungmin Lee, Sibeen Kim, Dongyoon Hwang et al.· 0 citations
Recent audio deepfake detectors separate bona fide speech from synthetic speech, yet it remains unclear which stage of a text-to-speech system supplies the detection evidence. We address this with controlled resynthesis and detector adaptation in an F5-TTS-BigVGAN pipeline. Since vocoder reconstruction of a real mel ca...
Eunji Shin, Kyudan Jung, Jihwan Kim et al.· 0 citations
A novel LLM-based CDSR model, DuELRec: Domain-Gated Dual Experts with LLMs for Cross-Domain Sequential Recommendation, equipped with an item-aware attention transformation module, which aggregates textual subtokens into item-level representations and enforces block-level attention masking.
Hyeongjun Yun, Kihyuk Song, Jaegul Choo et al.· 0 citations
RECAST is a robot navigation framework that combines the reasoning of a VLM with the spatial grounding of vision foundation models to build an Actionable Cost map and improves success over the strongest prior method.
Incheol Cho, Jintae Park, Jinkyu Kim et al.· 0 citations
PIA, a personal intelligence agent deployed alongside a consumer health agent, is presented, a personal intelligence agent deployed alongside a consumer health agent that receives the agent's natural-language requests, decides for itself whether and how to write or read, and turns conversations into typed clinical reco...
Jeonghun Yoon, Dongchan Kim, Hongyeon Yu et al.· 0 citations
Across model-level safety on HarmBench and agent-level safety on AgentHarm, Membrane achieves the highest F1 on all six modern jailbreak attacks, and benign refusal on AgentHarm stays at 7-14%, well below the 28-85% range of prior guards.
Minseok Choi, Seung-Moo Yang, Dongjin Kim et al.· arXiv.org· 2 citations
SNAP, a speaker-nulling framework, is introduced that reduces speaker entanglement and encourages detectors to focus on artifact-related patterns, leading to state-of-the-art performance.
Kyudan Jung, Ji-Hoon Kim, Minwoo Lee et al.· arXiv.org· 0 citations
Vision-language-action (VLA) models predict robot actions from visual observations and language instructions. These actions are defined in the robot's own 3D coordinate frame, yet most VLAs observe the scene in the camera frame, creating a frame mismatch between where the scene is observed and where actions are defined...
Byungkun Lee, Dongyoon Hwang, Dongjin Kim et al.· 1 citation
ReDesign is presented, an agentic framework that grows an editable layer hierarchy by selecting and composing specialized tools across modalities, and achieves strong visual fidelity while delivering the highest editability across layout, color, and text edits.
Jooyeol Yun, Jintae Park, Hyesu Lim et al.· arXiv.org· 2 citations· ⚡1
A unified latency decomposition framework for dLLMs is introduced to disentangle factors and analyze their impact on inference speed in real deployments, and categorize acceleration techniques along three axes covering algorithmic innovations, architectural and system optimizations, and inference-time scaling.
Daehoon Gwak, Minhyung Lee, Junwoo Park et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
