Top 10 AI research papers of 2025

Top 10 AI research papers of 2025

AI research in 2025 was defined by major shifts. The industry moved beyond chatbots and into thinking systems, autonomous agents and multimodal systems. In the past year, companies like Google DeepMind, OpenAI, Anthropic, Meta, DeepSeek, and NVIDIA have pushed AI research into new territory with papers focusing on reasoning, coding agencies, reinforcement learning, and critical … Read more

Compression Coding and Tuned Quantization Instructions for LLMs with FP8, GPTQ, and SmoothQuant Quantization using llmcompressor

Compression Coding and Tuned Quantization Instructions for LLMs with FP8, GPTQ, and SmoothQuant Quantization using llmcompressor

import subprocess, sys def pip(*pkgs): subprocess.check_call([sys.executable, “-m”, “pip”, “install”, “-q”, *pkgs]) pip(“llmcompressor”, “compressed-tensors”, “transformers>=4.45”, “accelerate”, “datasets”) import os, gc, time, json, math from pathlib import Path import torch from transformers import AutoModelForCausalLM, AutoTokenizer from datasets import load_dataset assert torch.cuda.is_available(), “Enable a GPU: Runtime > Change runtime type > T4 GPU” print(“GPU:”, torch.cuda.get_device_name(0), “| CUDA:”, torch.version.cuda, … Read more

Vercel Labs Introduces Zero, a Programming Language Designed for AI Agents to Learn, Modify, and Deploy Native Programs

Vercel Labs Introduces Zero, a Programming Language Designed for AI Agents to Learn, Modify, and Deploy Native Programs

Vercel Labs 01 / 09 · Overview ZeroProgramming LanguageAgents A diagnostic programming language that provides AI agents with structured diagnostics,typed maintenance metadata, and machine-readable documents — near sub-10 KiB native binaries. Programming Language Native agent v0.1.1 Apache-2.0 For testing Context 02 / 09 · Why Zero Exists Agent maintenance loop problem Most programming languages ​​produce … Read more

How to Build an MCP-Style AI Agent Program with Dynamic Tool Exposure Planning, Execution, and Content Injection

How to Build an MCP-Style AI Agent Program with Dynamic Tool Exposure Planning, Execution, and Content Injection

class RoutedAgent: def __init__(self, server: MCPToolServer, router: HybridMCPRouter, model: str): self.server = server self.router = router self.model = model def discover_exposed_tools(self, exposed_tool_names: List[str]) -> List[Dict[str, Any]]: return [t for t in self.server.tools_list() if t[“name”] in exposed_tool_names] def plan(self, task: str, exposed_tools: List[Dict[str, Any]]) -> PlanOutput: instructions = “”” You are a planning agent in an … Read more

How to Filter Text and Images for Free

How to Filter Text and Images for Free

Looking to add a layer of security to your chatbot, image analyzer or any other LLM-based program? I would strongly suggest you try OpenAI’s benchmark model: omni-moderation-latestthis can help your system recognize if the input may be harmful or not, that is very free. We will look at the background of the model, how to … Read more

Supertone Releases Supertonic v3: An On-Device Text-to-Speech Model With 31 Language Support, Fewer Reading Failures, and Highlighter

Supertone Releases Supertonic v3: An On-Device Text-to-Speech Model With 31 Language Support, Fewer Reading Failures, and Highlighter

Supertone has released Supertonic 3, the third generation of its on-device, ONNX-based text-to-speech system. Supertonic 3 ships with support for 31 languages, improved reading accuracy, fewer repetitive failures and skips, and ONNX public goods compatible with v2. Lightning Fast, On-Device, Multilingual and Accurate TTS. Changed from v2 to v3 Compared to Supertonic 2, Supertonic 3 … Read more

How to Build a Django-Unfold Admin Dashboard with Custom Models, Filters, Actions, and KPIs

How to Build a Django-Unfold Admin Dashboard with Custom Models, Filters, Actions, and KPIs

(ROOT / “shop” / “admin.py”).write_text(”’ from django.contrib import admin, messages from django.contrib.auth.admin import (UserAdmin as DjangoUserAdmin, GroupAdmin as DjangoGroupAdmin) from django.contrib.auth.models import User, Group from django.shortcuts import redirect from django.utils.html import format_html from django.utils.translation import gettext_lazy as _ from unfold.admin import ModelAdmin, TabularInline from unfold.contrib.filters.admin import ( ChoicesDropdownFilter, RangeNumericFilter, RangeDateFilter, MultipleChoicesDropdownFilter, ) from unfold.decorators import … Read more

Poetiq’s Meta-System Automatically Builds Model-Agnostic Harness Enhanced All LLM Tested in LiveCodeBench Pro Without Fine-Tuning

Poetiq’s Meta-System Automatically Builds Model-Agnostic Harness Enhanced All LLM Tested in LiveCodeBench Pro Without Fine-Tuning

Poetiq has recently published very interesting results showing that its Meta-System has reached a new state of the art in LiveCodeBench Pro (LCB Pro), a competitive coding benchmark, by automatically building and optimizing its logic harness – without fine-tuning any base model or accessing internal models. Result: GPT 5.5 High with Poetiq’s harness scores 93.9% … Read more

Cline Releases Cline SDK: Open-Source Agent Runtime Now Powers Its CLI and Kanban, with Portable IDE Extensions

Cline Releases Cline SDK: Open-Source Agent Runtime Now Powers Its CLI and Kanban, with Portable IDE Extensions

Cline had an ‘agency’ before it was cool, but building on the bleeding edge often leads to some structural debt. Over time, the agent loop and VS Code extension became a package deal—making it a headache to maintain or migrate to a new environment. It is difficult to maintain layering properties in a solid context. … Read more

Annual AI Event

Annual AI Event

You are a product of your environment, so choose to have the best. In the age of AI, this adage is as true as the day it was uttered. If you’re going to compete in this fast-paced AI environment with innovation around every corner, being among the industry leaders will do you a lot of … Read more