AIAIAny
  • Search
  • Collection
  • Category
  • Tag
  • Daily AI
AIAIAny

Tag

Explore by tags

AIAIAny

Curated AI Resources for Everyone

[email protected]

Powered by airss.app

Product
  • Search
  • Collection
  • Category
  • Tag
Resources
  • Blog
Company
  • Privacy Policy
  • Terms of Service
  • Sitemap
Copyright © 2026 All Rights Reserved.
  • All

  • 30u30

  • ASR

  • ChatGPT

  • GNN

  • IDE

  • RAG

  • agent-skills

  • ai

  • ai-agent

  • ai-api

  • ai-api-management

  • ai-client

  • ai-coding

  • ai-demos

  • ai-deploy

  • ai-development

  • ai-framework

  • ai-image

  • ai-image-demos

  • ai-inference

  • ai-infra

  • ai-leaderboard

  • ai-library

  • ai-rank

  • ai-security

  • ai-serving

  • ai-tools

  • ai-train

  • ai-video

  • ai-workflow

  • AIGC

  • algorithms

  • alibaba

  • amazon

  • android

  • annotated-cif

  • anthropic

  • arabic

  • audio

  • aws

  • benchmark

  • benchmarks

  • bf16

  • biology

  • biomolecular-design

  • blender

  • blog

  • book

  • bun

  • bytedance

  • chatbot

  • chatgpt

  • chemistry

  • claude

  • claude-code

  • cli

  • clickhouse

  • code

  • codex

  • coding

  • coding-agents

  • comfyui

  • common-crawl

  • copilot

  • course

  • cpu

  • cuda

  • cursor

  • datasets

  • deepmind

  • deepseek

  • depth

  • desktop

  • devops

  • diffusers

  • distillation

  • distributed-systems

  • dna

  • docker

  • drug-discovery

  • dsh

  • dsh-plugin

  • edge

  • egocentric

  • electron

  • embeddings

  • embodied-ai

  • engineering

  • evaluation

  • facebook

  • finance

  • flow-matching

  • foundation

  • foundation-model

  • fp4

  • fp8

  • gcode

  • gcp

  • gemini

  • gemini-cli

  • gemma

  • genomics

  • gguf

  • gitHub

  • github

  • go

  • google

  • gpu

  • gradient-booting

  • grok

  • groq

  • gsq

  • heretic

  • hermes

  • huggingface

  • hy_v4

  • image

  • image-to-code

  • imatrix

  • imu

  • ios

  • java

  • javascript

  • json

  • kimi

  • kotlin

  • kubernetes

  • laion

  • llama.cpp

  • LLM

  • llm

  • long-horizon

  • lora

  • mLOps

  • manipulation

  • math

  • mcap

  • mcp

  • mcp-client

  • mcp-server

  • meta

  • meta-ai

  • meta-pytorch

  • metal

  • microsoft

  • mixture-of-experts

  • mlops

  • mlx

  • mobile

  • mocap

  • moe

  • multilingual

  • multimodal

  • muse

  • muse-spark

  • mysql

  • navigation

  • nli

  • NLP

  • nlp

  • nodejs

  • numpy

  • nvfp4

  • nvidia

  • ocr

  • ollama

  • onnx

  • openai

  • opencode

  • pandas

  • paper

  • parquet

  • physical-reasoning

  • physics

  • pi

  • plugin

  • plugins

  • polars

  • postgres

  • prefix-caching

  • privacy

  • programming

  • prompt-engineering

  • protein

  • protein-design

  • pruning

  • pwa

  • python

  • pytorch

  • quantization

  • qwen

  • rco

  • react

  • reasoning

  • red-teaming

  • redis

  • refactoring

  • renders

  • reranker

  • research

  • retrieval

  • RL

  • rl

  • robotics

  • routing

  • rust

  • safetensors

  • science

  • security

  • segmentation

  • sft

  • shodan

  • skillkit

  • slam

  • software-engineering

  • sora

  • speech

  • sqlite

  • ssh

  • structural-biology

  • stt

  • supabase

  • swe

  • swift

  • synthetic

  • tensorrt

  • terminal

  • text-generation

  • text-to-code

  • thinking

  • threejs

  • trae

  • training-data

  • transformers

  • translation

  • tts

  • turkish

  • tutorial

  • typescript

  • unsloth-dynamic

  • vibe-coding

  • video

  • vision

  • visual-to-code

  • vllm

  • voice

  • vue

  • vulkan

  • vultr

  • web-search

  • webdataset

  • windsurf

  • world-model

  • writing

  • xAI

  • xai

  • youtube

Large Language Model Papers·2026
Icon for item

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

Jiyan He, Guang Liang +20

Presents an open 7B dense foundation model for mathematical reasoning and tool-assisted web search, supporting 256K-token context. Key features: hybrid gated sliding-window + global attention for efficient long-context training, FP8 Muon optimizer, progressive 16K→64K→256K curriculum, and open-source weights, data, and recipes.

#foundation-model#llm#fp8#long-horizon#math+7
Reinforcement Learning Papers·2026
Icon for item

Bellman Policy Optimization

Zhuoqing Song, Haotian Xu +2·Apodex US, Inc., Princeton University

Reframes Policy Mirror Descent for autoregressive LLM generation into a critic-free, trajectory-level objective using the Bellman equations to avoid per-token value estimation. Derives a practical token-level loss with a smoothed mismatch-correction weight and shows improved math-reasoning accuracy on benchmarks.

#rl#LLM#reasoning#paper#qwen+3
Large Language Model Papers·2026
Icon for item

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Yuxiao Yang, Tianrun Yu +7

Analyzes why on-policy distillation can produce excessively long student rollouts by identifying termination-token mismatch between students and teachers, and proposes aggregating functionally equivalent EOS tokens as a shared semantic stopping action to mitigate length inflation.

#distillation#qwen#gemma#llm#nlp+3
Machine Learning Foundation Papers·2026
Icon for item

PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs

Zhentao Tan, Jianrong Zhang +2·Affiliation: Zhejiang University. *Corresponding author., Affiliation: [email protected], [email protected], [email protected]

Learns dynamics-aligned latent representations for parametric PDE forecasting using masked-latent predictive pretraining, a geometry projector that aligns latent trajectory geometry, and a physics-structured latent predictor that separates shared evolution from parameter-dependent responses.

#paper#physics#research#pytorch#benchmarks+3
Large Language Model Papers·2026
Icon for item

Questioning the Questions: Sustaining Self-Evolution in Reasoning Models

Jinyuan Li, Chengsong Huang +5·Washington University in St. Louis, University of Michigan, Ann Arbor

Analyzes why self-evolving reasoning models collapse under repeated self-training and proposes R-Quest: a feedback-driven pipeline that trains solvers to reject invalid questions and uses a frozen base model to detect task-level repetition, filtering training data to sustain multi-round gains.

#reasoning#paper#llm#benchmarks#math+2
Hugging Face
AI Dataset·2026
Icon for item

openai/math as Harbor environments

FineEnvs, OpenAI +3

Provides 369 Harbor sandbox tasks ported from OpenAI's openai/math: each task is a Lean theorem with missing `sorry` proofs that an agent must complete, graded by a strict Comparator exact-match verifier. Includes task definitions, generator, and manifest for RL/code-agent evaluation.

#math#rl#coding-agents#huggingface#benchmark+3
Large Language Model Papers·2026
Icon for item

TPPO: Tracking-Value PPO For Language Model Reasoning

Futing Wang, Chenxi Li +7·Zhejiang University, Westlake University +5

Improves token-level credit assignment for RL fine-tuning of language models by parameterizing the critic as cumulative, position-wise log-odds increments (Tracking-Value PPO), enabling more accurate value-evolution tracking under sparse terminal rewards and boosting math-reasoning and coding benchmarks.

#rl#LLM#reasoning#qwen#math+3
Hugging Face
AI Model·2026
Icon for item

TwIL-8B

webAI

An 8.79B reasoning model tuned for contest math, code, and instruction following from Granite 4.2. Its balanced and verbose variants trade shorter reasoning traces for more extensive problem solving.

#LLM#reasoning#math#code#RL+3
Large Language Model Papers·2026
Icon for item

Recovering Reliable Supervision via Critique-Guided On-Policy Distillation

Kaixiang Zhao, Tianrun Yu +5·Brigham Young University, University of North Carolina at Chapel Hill

Restores recoverability in on-policy distillation by having the teacher generate critiques of incorrect student rollouts, guide a critique-free student rewrite, and score the revised solution as privileged context; yields improved math-reasoning performance, largest gains on competition problems.

#distillation#qwen#reasoning#math#LLM+2
Hugging Face
AI Model·2026
Icon for item

Qwen3.5-4B-Qwenputer

Divyansh Agrawal

Compiles a deterministic RISC-V CPU into a language model’s weights, enabling exact arithmetic and C or MicroPython execution without an external tool runtime. It uses Gated DeltaNet state as memory and remains experimental.

#qwen#LLM#cpu#math#transformers+1
Reinforcement Learning Papers·2026
Icon for item

DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Models

Hongze Chen, Miao Pan +8·Zhejiang University, National University of Singapore +1

Estimates how committed tokens improve predictions at remaining masked positions, then uses those contributions to refine reinforcement-learning signals for diffusion language models. On LLaDA-8B-Instruct, it raises MATH500 and GSM8K scores by up to 9.0 and 5.3 points.

#RL#reasoning#LLM#NLP#paper+1
Large Language Model Papers·2026
Icon for item

Scaling Mathematical Proof Supervision from Structured Textbooks

Youqing Fang, Zhouqi Hua +8·University of Science and Technology of China, Fudan University +2

Turns university mathematics textbooks into structured proof-training data while preserving chapter order, proposition–proof links, and dependencies. The authors report a 16.7-point average gain over the base model across six evaluations.

#paper#math#reasoning#datasets#training-data+2
  • Previous
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • Next