ax@ax-radar:~/papers $ grep -E 'arxiv|paper' sources/tags
45 srcsignal 72%cycle 04:32

papers · 2026-05-03

9 papers · updated 3m ago
2026-05-03 · Sun
22:36
36d ago
HuggingFace Papers (takara mirror)· rssEN22:36 · 05·03
Cripping AI: Reimagining AI Through Lived Disability Experiences
The paper proposes cripping AI as a framework and applies it to 3 cases: deafness and sign language AI, blindness and visual assistive AI, and stuttering and speech AI.
#Safety#Alignment#Multimodal#Research release
why featured
HKR-H/K/R all pass, but the post offers a framework and 3 cases without empirical results, model data, or reproducible tests. That keeps it in all, below the 72 featured line.
editor take
The paper uses 3 cases to attack ableist evals; accessibility as a patch leaves datasets, metrics, and product assumptions rotten.
HKR breakdown
hook knowledge resonance
open source
66
SCORE
H1·K1·R1
22:01
36d ago
HuggingFace Papers (takara mirror)· rssEN22:01 · 05·03
Enhanced LLM Reasoning by Optimizing Reward Functions with Search-Driven Reinforcement Learning
The paper optimizes reward functions while holding Llama-3.2-3B-Instruct fixed, generating 50 candidates over five rounds and reaching F1 0.795 on GSM8K with the best ensemble.
#Reasoning#Alignment#Fine-tuning#Llama
why featured
HKR-K passes via concrete setup and GSM8K result; HKR-H and HKR-R are weak because this is a method paper with limited industry pull. Scored in the 60-71 research band.
editor take
Fixed Llama-3.2-3B hits 0.795 GSM8K F1 via reward search; random five-reward control at 0.047 makes this credible.
HKR breakdown
hook knowledge resonance
open source
64
SCORE
H0·K1·R0
18:32
36d ago
HuggingFace Papers (takara mirror)· rssEN18:32 · 05·03
Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization
Judge-R1 uses a dynamic planning agent to retrieve statutes and precedents from multiple sources, then applies GRPO with a legal reward function to optimize judgment document generation; experiments use the JuDGE benchmark, but the post does not disclose exact scores.
#Agent#RAG#Reasoning#Judge-R1
why featured
HKR-K passes via a testable agentic RAG plus GRPO reward setup, but HKR-H is a dry academic title and HKR-R stays narrow to legal-AI builders. No hard exclusion; low-60s all-tier signal.
editor take
Judge-R1 adds agentic legal retrieval plus GRPO; no JuDGE scores are disclosed, so treat “significantly outperforms” as unproven.
HKR breakdown
hook knowledge resonance
open source
62
SCORE
H0·K1·R0
17:47
36d ago
HuggingFace Papers (takara mirror)· rssEN17:47 · 05·03
Phase-Aware Bounded-Loss Transport for Distributed Machine Learning Training
DBLP adjusts gradient loss tolerance by training phase and cuts end-to-end training time by 24.4% on average, with a 33.9% maximum reduction, while reaching up to 5.88x single-round communication latency speedups during microburst events versus the baseline.
#Fine-tuning#Inference-opt#DBLP#Research release
why featured
HKR-H/K/R pass, but the story is narrow distributed-training transport rather than a broad model or product release. Concrete speedup numbers keep it in all, below featured.
editor take
DBLP cuts training time 24.4% on average. But model scale, topology, and baseline are undisclosed, so 5.88x is not portable yet.
HKR breakdown
hook knowledge resonance
open source
68
SCORE
H1·K1·R1

more

feeds

admin