Zhemal Khamidun
Head of AI at Alpina Digital, CPO of AlpinaGPT (~30-person engineering & AI team). Founder of Vibe Academy & Hamidun Consulting, author of the AI channel «Готовим ИИшницу» (@jemal_hamidun).
DecisionPivot Tests 40 Solver Models: Up to a 26-Point Gap at Equal Accuracy
DecisionPivot's 40,033-item benchmark shows two 27B models 2.6 points apart on the reference track diverge by 25.9 points on contrastive groups.
S-Agent 2.0 teaches a coding agent to understand 3D and beats SpatialClaw by 7.8 points
A ready-made coding agent with a set of 3D tools lifted Qwen3.8-27B to 66.5 on MMSI-Bench and 82.3 on ReVSI. Gemini-3.8-Flash reached 74.1 and 90.5.
RiseHarness Teaches Terminal Agents to Fix Their Own Harness Without Fine-Tuning
RiseHarness iteratively improves the harness of terminal agents with frozen weights. It compares successful and failed runs of the same task and validates each…
Agent Mosaic: LLM Agents Assemble Secrets From Harmless Documents in 7% of Responses
Layer Looping Cuts Diffusion LLM Training Costs by Up to 3.3x
FrontierCS 2 tested 12 AI agents on R&D tasks: the best passed 58%
SplatLab writes its own 3D Gaussian Splatting papers and beats baselines by up to +3.78 dB
Survey: Robots Are Learning to Improve Their Own Learning, but Evidence Is Still Missing
A new survey carries recursive self-improvement from code into the physical world and names four conditions under which robot gains accumulate instead of vanishing.
ToM2Vec Teaches LLM Agents to Model Their Partners in Latent Tokens
ToM2Vec builds a partner's theory of mind in continuous tokens and wins in Hanabi, Overcooked-AI and negotiation, including games with an unfamiliar GPT-5.4.
LASAGNA Tests 450 RAG Configurations: The Promised +47% Gain Turns Into Just +17%
LoopRec Picks Compute Depth for Each Item and Beats Baselines on 4 Backbones
RealMe Builds 2K Volumetric Video from a Handful of Cameras Using Diffusion
PACE compresses linear LLM state to 4 bits and saves a third of the memory
Researchers Propose PAPAV Framework: Only 3 of 64 Benchmarks Test Verification
A new paper compares computer-use agents and robots through five PAPAV functions. Of 64 benchmarks, 5 assess outcome prediction and only 3 assess result…
NUS Teaches a Model to Find What It Described: gIoU Rises From 57.5% to 68.2%
Generalized CycleGRPO links describing a region and finding it from text in a single RL loop, with no reference captions and no LLM judge. On GroundingSuite, gIoU…