If you're interested in multimodal reasoning, math LLMs, or vision-language models, do check out our paper! #MultimodalAI #LLMs #MathReasoning #VisionLanguage #AIForScience #VisualReasoning #SymbolicReasoning #GeometricReasoning
15
Search
I started a new project: lowbit-math-reasoning
Initial setup:
- Qwen3.5-9B quantized with GPTQ (8-bit / 4-bit)
・mssfj/Qwen3.5-9B-GPTQ-INT8 / -INT4
Next: GSM8K/MATH/HLE(MATH) evaluation to measure reasoning collapse under lowbit constraints.
#LLM #Quantization #MathReasoning
1
46
Pi Day reminder: math = reasoning, not recall. π🧠
Ask one better question today: “Why does that work?”
#PiDay #MathReasoning #ConceptualUnderstanding #MathTeacherY
4
8
682
180
VisTIRA: Closing the Image-Text Modality Gap in Visual Math Reasoning via Structured Tool Integration
Preprint: VisTIRA is introduced to improve visual math reasoning by integratin…
arxiv.org/abs/2601.14440 #AI #MathReasoning #MachineLearning #Preprint #Arxiv #ScienceNews
VisTIRA: Closing the Image-Text Modality Gap in Visual Math...
Vision-language models (VLMs) lag behind text-only language models on mathematical reasoning when the same problems are presented as images rather than text. We empirically characterize this as a...
From arxiv.org 6
Love seeing my 5th Grade AC Math students engage with review through interactive fraction comparisons using Cobb District Math lessons on CTLS. Strong visuals + student thinking = meaningful math learning. 👏
@fakfamily @CobbMathDept #engagedlearning #5thgrade #mathreasoningZ
3
68
We just shared a new post on the blog all about transforming secondary math teaching, one small shift at a time.
Read the post and share your thoughts!
👉 na2.hubs.ly/H02fSl-0
#MathIsFigureoutable #MathEducation #MathReasoning9
1
1
1
396
That’s the heart of my new post: Transforming Teaching 6–12: Small Shifts, Big Impact.
Check it out → na2.hubs.ly/H02c5tm0
#MathIsFigureoutable #MathReasoning
3
3
555
Building math reasoning with the “double & halve” strategy today! 🧠
25×16 → 50×8 = 400
Flexible thinking for the win!
@fakfamily
#5thGradeMath #MathReasoningO
1
86
Tool Up or Tap Out: How Multi-TAG Elevates Math Reasoning with Smarter LLM Workflows cognaptus.com/blog/2025-07-2… #LLMs #mathreasoning #toolaugmentation #AIframeworks #inference-timescaling
9
Incorrect Answers Enhance Math Reasoning: Insights from Qwen2.5-Math and RLVR
#ReinforcementLearning #MathReasoning #AIInnovation #MachineLearning #BusinessSolutions
itinai.com/incorrect-answ…
Incorrect Answers Enhance Math Reasoning: Insights from Qwen2.5-Math and RLVR – AI Lab itinai.com
Enhancing Math Reasoning through Reinforcement Learning Improving Math Reasoning with Reinforcement Learning Introduction Recent advancements in artificial inte
From itinai.com 12
NVIDIA AceReason-Nemotron: Advancing Math and Code Reasoning with Reinforcement Learning
#NVIDIAAI #ReinforcementLearning #MathReasoning #CodeReasoning #ArtificialIntelligence
br>itinai.com/nvidia-acereas…
1
38
JUST IN: Study finds 1-shot RLVR significantly boosts math reasoning in LLMs. Using just one example improves accuracy by 73.6%, matching larger datasets' performance. Self-reflection and generalization also enhanced across tasks and models. #LLMs #MathReasoning
16
🚀 New model alert! Introducing "skywork_skywork-or1-math-7b" 🧠, a powerful math reasoning model with 69.8 AIME24 and 52.3 AIME25 scores! Try it with LocalAI: `local-ai run skywork_skywork-or1-math-7b` 💥 #LocalAI #AIModel #MathReasoning
1
115