read more:
alphaxiv.org/abs/2603.28765 [Translated from EN to English]
→ View original post on X — @askalphaxiv, 2026-04-02 06:54 UTC
@askalphaxiv
-
Discover the full article on alphaxiv.org
By
–
-
Adaptive Block-Scaled Data Types for Efficient 4-bit LLM Quantization
By
–
“Adaptive Block-Scaled Data Types” A lot of 4-bit LLM quantization assumes every block should use the same number format, this paper argues that’s the wrong abstraction. So they let each 16-value block choose between FP4 and scaled INT4, depending on which gives lower error. This format, IF4 (Int/Float 4), reuses the unused sign bit of the shared FP8 scale factor to store the choice, so it gets adaptivity with no extra storage overhead. This is because at 4 bits, precision is so scarce that matching the format to the local value distribution really matters. The result is lower quantization error and better performance than existing 4-bit block-scaled formats in both training and PTQ.
→ View original post on X — @askalphaxiv, 2026-04-02 06:54 UTC
-
New Scientific Publication Available on AlphaXIV
By
–
read more:
https://www.alphaxiv.org/abs/2603.18297 [Translated from EN to English]→ View original post on X — @askalphaxiv, 2026-04-01 17:53 UTC
-
Check out the full list on alphaxiv.org
By
–
check out the full list: alphaxiv.org/shared/folder/0… [Translated from EN to English]
→ View original post on X — @askalphaxiv, 2026-03-31 19:31 UTC
-
World Models Research Reading List: JEPA and Recent Advances
By
–
As Yann LeCun and his team has brought a new wave of World Models research into 2026, we have compiled a reading list to recap some of the must-read papers to get you up-to-date about JEPA & World Modeling!
→ View original post on X — @askalphaxiv, 2026-03-31 19:31 UTC
-
Discover the full article on alphaxiv.org
By
–
read more: alphaxiv.org/abs/2603.27646 [Translated from EN to English]
→ View original post on X — @askalphaxiv, 2026-03-31 19:29 UTC
-
PKU Physics Teams Launch PRBench AI Research Benchmark
By
–
20 research teams over at PKU that specializes in physics have published this frontier physics benchmark called PRBench, assessing if AI can read the paper, implement the methods from scratch, and reproduce the results. In the benchmark, it puts 30 physics papers into end-to-end
-
Meta-Harness: Optimizing LLM Model Harnesses End-to-End
By
–
"Meta-Harness: End-to-End Optimization of Model Harnesses" A big portion of agentic LLM performance relies on human-designed harness around the model, not just the weights. On top of that, how well a harness is designed could impact a model's performance heavily. So this paper
-
Memory Sparse Attention Scales Models to 100M Token Context
By
–
Scaling Attention to 100M context!? Memory Sparse Attention introduces an idea where instead of rereading an entire 100M-token entry, it learns to jump straight into the relevant memories and reason from them end-to-end. More specifically, it first encodes documents into
-
Scientific Article arXiv 2603.25040 from March 30 2026
By
–
read more: https://alphaxiv.org/abs/2603.25040