Ishan Gupta
@code_igx
25 🇮🇳, Hustler @RITtigers NY 🇺🇸 | RnD on Quantum AI, Superintelligence & Systems | Ex- @Broadcom @VMware
Talvez você curta
Brillinant new @Google paper proposes Supervised Reinforcement Learning (SRL), a step-wise reward method that trains small models to plan and verify actions instead of guessing final answers. The big deal is that SRL turns reasoning into many graded steps, so 7B models actually…
DeepSeek's OCR model has gained tremendous attention. I went through the paper, and here's the gist: 1. Model converts text to an image. 2. Then converts the image to image tokens. 3. Finally converts image tokens to text. Results: 10× compression with ~97% accuracy. 20×…
Hottest paper on AlphaXiv 📈 Language Models are Injective and Hence Invertible Every prompt maps to a unique hidden state and can be exactly reconstructed with this paper’s algorithm SIPIT. This means the model’s internal activations are the full prompt in disguise!!
Must-read AI research of the week: ▪️ Supervised Reinforcement Learning (SRL) ▪️ SPICE: Self-Play In Corpus Environments Improves Reasoning ▪️ Reasoning-Aware GRPO using Process Mining ▪️ Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets ▪️ The Era of…
Swarm inference is a brilliantly powerful idea. 💡 Turns a pile of small models into one frontier-level answer that beats most SOTA single-model setups. In this paper @fortytwo wires many small models into a peer-ranked swarm that answers as one, and it beats big single SOTA…
Holy shit... this might be the next big paradigm shift in AI. 🤯 Tencent + Tsinghua just dropped a paper called Continuous Autoregressive Language Models (CALM) and it basically kills the “next-token” paradigm every LLM is built on. Instead of predicting one token at a time,…
This paper shows LLM legal interpretations are unstable and often unlike what ordinary people think. Shows LLMs can look confident while missing how non-experts read legal language. The authors test many models on insurance scenarios using simple yes or no questions. Small…
A large solar-powered AI satellite constellation would be able to prevent global warming by making tiny adjustments in how much solar energy reached Earth
Memory in AI agents seems like a logical next step after RAG evolved to agentic RAG. RAG: one-shot read-only Agentic RAG: read-only via tool calls Memory in AI agents: read-and-write via tool calls Obviously, it's a little more complex than this. I make my case here:…
2023: Prompt engineering is a critical skill 2025: Context engineering is a critical strategy My colleagues just dropped a 41-page guide on context engineering. It covers: • Prompting techniques: Choosing the right words still matters • Query Augmentation & Retrieval: Finding…
RAG vs. CAG, clearly explained! RAG is great, but it has a major problem: Every query hits the vector database. Even for static information that hasn't changed in months. This is expensive, slow, and unnecessary. Cache-Augmented Generation (CAG) addresses this issue by…
This is an accurate picture of orbital rocket launches so far this year. 90% Falcon with the massive @SpaceX Starship standing out very clearly.
All 258 rockets launched in 2025 so far, chronologically and at scale.
Stanford just published a huge 470-page study 📕 "The Principles of Diffusion Models" Explains how diffusion models turn noise into data and ties their main ideas together. It starts from a forward process that adds noise over time, then learns the exact reverse. The reverse…
A must-read paper → Fundamentals of Building Autonomous LLM Agents Reviews the core cognitive subsystems that make up autonomous LLM-powered agents, including: - Perception - Reasoning & planning: CoT, MCTS, ReAct, Tree-of-Thought (ToT) techniques - Long- & short-term memory -…
The paper shows deep sequence models store facts as geometry, not only as lookup tables. The big deal here is that geometric memory can make multi hop reasoning a 1 step check instead of many steps. The key finding is that geometric and associative memories compete, and…
Microsoft did it again! Building with AI agents almost never works on the first try. You spend days tweaking prompts, adding examples, hoping it gets better. Nothing systematic, just guesswork. This is exactly what Microsoft's Agent Lightning solves. It's an open-source…
Starship lunar variant update
Starship continues to simultaneously be the fastest path to returning humans to the surface of the Moon and a core enabler of the Artemis program’s goal to establish a permanent, sustainable presence on the lunar surface → spacex.com/updates/#moon-…
🚨 This might be the biggest leap in AI agents since ReAct. Researchers just dropped DeepAgent a reasoning model that can think, discover tools, and act completely on its own. No pre-scripted workflows. No fixed tool lists. Just pure autonomous reasoning. It introduces…
𝗟𝗘𝗔𝗞𝗘𝗗: 100s of premium AI Agents... These exact Agents sell for $𝟱,𝟬𝟬𝟬+ 𝗽𝗲𝗿 𝗯𝘂𝗶𝗹𝗱, 𝗲𝗮𝘀𝗶𝗹𝘆... Inside the file you get: → Lead qualification agents → Content generation pipelines → Appointment booking automation → Cold outreach sequences → Data…
United States Tendências
- 1. New York 35.7K posts
- 2. #questpit 19.4K posts
- 3. Van Jones 7,316 posts
- 4. Sauer 2,674 posts
- 5. $LMT $450.50 Lockheed F-35 N/A
- 6. #wednesdaymotivation 2,684 posts
- 7. $SENS $0.70 Senseonics CGM N/A
- 8. 5th of November 22.3K posts
- 9. #5SOS_SELFIEDAY N/A
- 10. IEEPA 2,175 posts
- 11. Good Wednesday 34K posts
- 12. $APDN $0.20 Applied DNA N/A
- 13. Balmain 3,220 posts
- 14. Hump Day 16.6K posts
- 15. #Wednesdayvibe 1,994 posts
- 16. Enhanced 12.4K posts
- 17. Socialism 120K posts
- 18. Miss Piggy 2,553 posts
- 19. The GOP 306K posts
- 20. Alastor 44.6K posts
Talvez você curta
-
Prithvi Raj
@prithvi137 -
Daniel Walsh
@rhatdan -
OCI
@OCI_ORG -
Murat Demirbas (Distributolog)
@muratdemirbas -
Vedant Shrotria
@VedantShrotria -
Bret Fisher
@BretFisher -
LitmusChaos | Chaos Engineering Made Easy
@LitmusChaos -
Uma Mukkara
@Uma_Mukkara -
Matt Hargett
@syke -
David Flanagan
@rawkode -
Kathy Zant
@kathyzant -
Felix Rieseberg
@felixrieseberg -
Mat Velloso
@matvelloso
Something went wrong.
Something went wrong.