Salesforce AI research team present FOFPred, a language driven future optical flow prediction framework that connects large vision language models with diffusion transformers for dense motion forecasting in control and video generation settings. FOFPred takes one or more images and a natural language instruction such as ‘moving the bottle from right to left’ and predicts 4 future optical flow frames that describe how every pixel is expected to move over time. https://arxiv.org/pdf/2601.10781 Future optical flow as a motion representation Optical flow is the apparent per pixel displacement between two frames. FOFPred focuses on future optical flow, which means predicting dense…

In this tutorial, we demonstrate how a semi-centralized Anemoi-style multi-agent system works by letting two peer agents negotiate directly without a manager or supervisor. We show how a Drafter and a Critic iteratively refine an output through peer-to-peer feedback, reducing coordination overhead while preserving quality. We implement this pattern end-to-end in Colab using LangGraph, focusing on clarity, control flow, and practical execution rather than abstract orchestration theory. Check out the FULL CODES here. !pip -q install -U langgraph langchain-openai langchain-core import os import json from getpass import getpass from typing import TypedDict from langchain_openai import ChatOpenAI from langgraph.graph import StateGraph, END…

Liquid AI has released LFM2.5-1.2B-Thinking, a 1.2 billion parameter reasoning model that runs fully on device and fits in about 900 MB on a modern phone. What needed a data center 2 years ago can now run offline on consumer hardware, with a focus on structured reasoning traces, tool use, and math, rather than general chat. Position in the LFM2.5 family and core specs LFM2.5-1.2B-Thinking is part of the LFM2.5 family of Liquid Foundation Models, which extends the earlier LFM2 architecture with more pre-training and multi stage reinforcement learning for edge deployment. The model is text only and general purpose…

Knowledge Graphs and their limitations With the rapid growth of AI applications, Knowledge Graphs (KGs) have emerged as a foundational structure for representing knowledge in a machine-readable form. They organize information as triples—a head entity, a relation, and a tail entity—forming a graph-like structure where entities are nodes and relationships are edges. This representation allows machines to understand and reason over connected knowledge, supporting intelligent applications such as question answering, semantic analysis, and recommendation systems Despite their effectiveness, Knowledge Graphs (KGs) have notable limitations. They often lose important contextual information, making it difficult to capture the complexity and richness of…

GLM-4.7-Flash is a new member of the GLM 4.7 family and targets developers who want strong coding and reasoning performance in a model that is practical to run locally. Zhipu AI (Z.ai) describes GLM-4.7-Flash as a 30B-A3B MoE model and presents it as the strongest model in the 30B class, designed for lightweight deployment where performance and efficiency both matter. Model class and position inside the GLM 4.7 family GLM-4.7-Flash is a text generation model with 31B params, BF16 and F32 tensor types, and the architecture tag glm4_moe_lite. It supports English and Chinese, and it is configured for conversational use.…

Microsoft Research has released OptiMind, an AI based system that converts natural language descriptions of complex decision problems into mathematical formulations that optimization solvers can execute. It targets a long standing bottleneck in operations research, where translating business intent into mixed integer linear programs usually needs expert modelers and days of work. What OptiMind Is And What It Outputs? OptiMind-SFT is a specialized 20B parameter Mixture of Experts model in the gpt oss transformer family. About 3.6B parameters are active per token, so inference cost is closer to a mid sized model while keeping high capacity. The context length is…

In this tutorial, we build an end-to-end streaming voice agent that mirrors how modern low-latency conversational systems operate in real time. We simulate the complete pipeline, from chunked audio input and streaming speech recognition to incremental language model reasoning and streamed text-to-speech output, while explicitly tracking latency at every stage. By working with strict latency budgets and observing metrics such as time to first token and time to first audio, we focus on the practical engineering trade-offs that shape responsive voice-based user experiences. Check out the FULL CODES here. import time import asyncio import numpy as np from collections import deque…

Nous Research has introduced NousCoder-14B, a competitive olympiad programming model that is post trained on Qwen3-14B using reinforcement learning (RL) with verifiable rewards. On the LiveCodeBench v6 benchmark, which covers problems from 08/01/2024 to 05/01/2025, the model reaches a Pass@1 accuracy of 67.87 percent. This is 7.08 percentage points higher than the Qwen3-14B baseline of 60.79 percent on the same benchmark. The research team trained the model on 24k verifiable coding problems using 48 B200 GPUs over 4 days, and released the weights under the Apache 2.0 license on Hugging Face. https://nousresearch.com/nouscoder-14b-a-competitive-olympiad-programming-model/ Benchmark focus and what Pass@1 means LiveCodeBench v6…

In this tutorial, we build a hands-on comparison between a synchronous RPC-based system and an asynchronous event-driven architecture to understand how real distributed systems behave under load and failure. We simulate downstream services with variable latency, overload conditions, and transient errors, and then drive both architectures using bursty traffic patterns. By observing metrics such as tail latency, retries, failures, and dead-letter queues, we examine how tight RPC coupling amplifies failures and how asynchronous event-driven designs trade immediate consistency for resilience. Throughout the tutorial, we focus on practical mechanisms, retries, exponential backoff, circuit breakers, bulkheads, and queues that engineers use to…

Vercel has released agent-skills, a collection of skills that turns best practice playbooks into reusable skills for AI coding agents. The project follows the Agent Skills specification and focuses first on React and Next.js performance, web design review, and claimable deployments on Vercel. Skills are installed with a command that feels similar to npm, and are then discovered by compatible agents during normal coding flows. Agent Skills format Agent Skills is an open format for packaging capabilities for AI agents. A skill is a folder that contains instructions and optional scripts. The format is designed so that different tools can…