🔄 In a Training Loop

Equan P.

junwatu

·

https://junwatu.com

AI & ML interests

LLM integrations & fine tuning

Recent Activity

liked a dataset about 23 hours ago

codepawl/asset-index

liked a model 3 days ago

speridlabs/idol

updated a Space 3 days ago

junwatu/ocr-man

View all activity

Organizations

junwatu 's Spaces 43

Reproduction: Hermes: An Evidence-Driven Agentic Framework for Trustworthy and Explainable AI-Generated Video Detection

Browse research logbook and collaborate with a coding agent

Reproduction: Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation

Explore and collaborate on research logbooks online

Reproduction: ProtoVAR: Efficient Dataset Distillation via Prototype-Guided Visual Autoregressive Modeling

Explore and update a collaborative research logbook

Reproduction: Reward-free Alignment for Conflicting Objectives

Reproduction: Discrete Survival Knowledge Distillation for Competing Risks Analysis

Explore a research logbook and sync findings with an AI agent

Reproduction: The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents

Collaborate with your coding agent using a shared logbook

Reproduction: GePBench: Evaluating Fundamental Geometric Perception for Multimodal Large Language Models

Explore and sync experiment logs with an AI coding agent

Reproduction: Self-Refining Video Sampling

Collaborate with an AI agent to maintain a synced experiment logbook

Reproduction: DenseSteer: Steering Small Language Models towards Dense Math Reasoning

Collaborate on research logs with AI assistance

Reproduction: CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception

Explore and share visual search logbook with AI agents

Reproduction: CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs

Explore research logbook and collaborate with AI agent

Reproduction: Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics

Explore and collaborate on a research logbook online

Reproduction: TarGATE: Target-Aware Data Selection via Token-Attenuation Gates

Browse project logs and collaborate with AI agent

Reproduction: Trifuse: Enhancing Attention-Based GUI Grounding via Multimodal Fusion

Explore and sync research logs with an AI agent

Reproduction: Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens

Explore research logbooks and sync with an AI coding agent

Reproduction: Implicit Safety Alignment from Crowd Preferences

Explore and collaborate on a research logbook online

Reproduction: A Provable Expressiveness Hierarchy in Hybrid Linear-Full Attention

Explore and collaborate on a research logbook online

Reproduction: CountsDiff: A diffusion model on the natural numbers for generation and imputation of count-based data

Explore and sync experiment logs for the CountsDiff model

Reproduction: A model of errors in transformers

Explore logbook entries and collaborate with a coding agent