Zubin

zubinb

·

AI & ML interests

None yet

Recent Activity

liked a model 1 day ago

endless-frontier/BigBang-v1

liked a model 1 day ago

Cactus-Compute/needle

liked a model 1 day ago

vectionlabs/Salience-27B-R4

View all activity

Organizations

None yet

upvoted 3 collections 1 day ago

Nanbeige4.2-3B MLX

MLX conversions of Nanbeige4.2-3B (Looped Transformer): bf16 + 2-8 bit quants. Needs mlx-lm PR #1597. • 8 items • Updated 18 days ago • 2

Nanbeige4.2-3B quants (looped transformer)

FP8 default, LoopShield 4-bit loop-aware placement, NVFP4A16 speed pick. Gates + failure modes on each card. • 4 items • Updated 17 days ago • 1

heretic-models

Madness and heresy • 69 items • Updated about 5 hours ago • 16

upvoted an article 4 days ago

Article

Deploy local agents everywhere with LFM2.5-2.6B

LiquidAI

•

5 days ago

• 76

upvoted a paper 8 days ago

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

Paper • 2607.27205 • Published 11 days ago • 139

upvoted 2 collections 9 days ago

🎯 Liquid Nanos

Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices • 36 items • Updated 6 days ago • 131

VisionPsy

SOTA General-Purpose Multimodal Vision-Language Models for Edge deployment • 4 items • Updated 10 days ago • 6

upvoted 2 papers 10 days ago

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

Paper • 2010.05646 • Published Oct 12, 2020 • 2

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference

Paper • 2508.05835 • Published Aug 7, 2025 • 2

upvoted a paper 11 days ago

Triplet-Block Diffusion RWKV

Paper • 2605.25969 • Published May 25 • 27

upvoted a collection 11 days ago

Web LLM Models

LiteRT models that can run on the Web • 17 items • Updated 14 days ago • 23

upvoted a collection 14 days ago

Tmax

Data and models associated with "Tmax: A simple recipe for terminal agents". paper: https://arxiv.org/abs/2606.23321 • 23 items • Updated Jun 23 • 19

upvoted 3 papers 15 days ago

K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs

Paper • 2605.09635 • Published 17 days ago • 64

LLMs Get Lost in Evolving User Intent

Paper • 2607.20734 • Published 18 days ago • 24

SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems

Paper • 2604.04514 • Published Apr 6 • 8

upvoted a collection 15 days ago

MIRA World Model

Developed with General Intuition (https://www.generalintuition.com/), in collaboration with Epic Games. MIRA is a Multiplayer Interactive World Model. • 2 items • Updated 25 days ago • 1

upvoted a collection 17 days ago

Cactus Hybrid

A small, on-device model is fast and private, but sometimes wrong. We post-train models to know when they are wrong, run on any framework. • 4 items • Updated 17 days ago • 9

upvoted a collection 20 days ago

Selene-1-Mini

13 items • Updated Mar 2 • 10

upvoted a paper 20 days ago

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

Paper • 2606.21627 • Published Jun 19 • 7

upvoted a collection 21 days ago

Bonsai 27B

10 items • Updated 25 days ago • 215