BIG new idea in interpretability called Patterning The basic idea: given a desired generalization/structure, determine what training data produces it So they treat what circuits/algorithms the model learns as something you can solve for by measuring how sensitive those internal
@askalphaxiv
-
LLM Sandbox Unlocks General Agentic Intelligence Without Code
By
–
"LLM-in-Sandbox Elicits General Agentic Intelligence" This paper shows that giving an LLM a virtual computer it can browse, write files, and run code, instead of only generating text, can unlock general agent behavior and increase performance across non-code domains WITHOUT
-
Fine-Tuning Video Models for Visuomotor Robot Control
By
–
"Fine-Tuning Models for Visuomotor Control and Planning" This paper proposes Cosmos Policy, showing a pretrained latent video diffusion model (Cosmos-Predict2) can be adapted into a SoTA robot policy via a single post-training stage on robot demonstrations, without
-
Test-Time Learning: RL Discovers Solutions During Inference
By
–
Learning to Discover at Test Time This paper TTT-Discover shows that by replacing best-of-N prompting with RL at test time on a continuous verifiable reward (via LoRA), it can learn from its own attempts and reliably push past the prior performance. The “learn-while-solving”
-
Qwen3-TTS Open-Source Real-Time Voice Stack Released
By
–
Qwen3-TTS just cracked open-source TTS! Qwen3-TTS turns a Qwen3 LM into an instruction-steerable real-time voice stack by jointly training a speaker encoder + a dual-track text/acoustic token backbone Under the hood, it uses hierarchical multi-token prediction over RVQ
-
NVIDIA GRPO Multi-Reward Optimization Technical Advances
By
–
Trending on alphaXiv: The proper way to do multi-reward GRPO from NVIDIA GRPO’s “normalize the summed reward” step can wash out real tradeoffs by collapsing different reward combinations into identical advantage values eg. tradeoffs into the same advantage where “got 1
-
LLMs Extract Copyrighted Books Via Simple Prompting Loop
By
–
extracting entire copyrighted books from production LLMs Researchers extracted near-verbatim copies of Harry Potter & 1984 from Claude 3.7 Sonnet using just a simple two-phase continue loop. Gemini 2.5 Pro & Grok 3 didn't even need jailbreaking, they complied directly
-
AhmedSQRD Answers Questions on alphaXiv Research Paper
By
–
Author @AhmedSQRD will be answering questions on alphaXiv: https://
alphaxiv.org/abs/2601.02671 -
Epiplexity: Measuring Learnable Structure for Bounded Intelligence
By
–
Now Trending on alphaXiv From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence This paper introduces epiplexity, a way to measure how much learnable & reusable structure a computationally limited model can extract from data This
-
Visual Tokenizers Enhanced: Semantic Objectives Beyond VAE Pixel-Level Accuracy
By
–
VAE-only visual tokenizers has hit a wall for diffusion, as better pixel-level accuracy does NOT lead to higher-quality generation To be truly effective, this MiniMax paper adds semantic objectives via CLIP + self-supervision during tokenizer pretraining, having the latent space