ML News
new
|
past
|
best
|
rss
|
submit
about
61.
Decision Models as Policy Gates for Coding Agents
(
arxiv.org
)
2 points
by
ghshephard
14 days ago
|
hide
|
past
|
pdf
|
discuss
62.
Automatic Construction of Strong Simple Baselines
(
arxiv.org
)
3 points
by
cellington
14 days ago
|
hide
|
past
|
pdf
|
discuss
63.
USDB: Scaling Storage for Next-Generation Recommender Systems at ByteDance
(
arxiv.org
)
49 points
by
1equalsequals1
14 days ago
|
hide
|
past
|
pdf
|
8 comments
64.
GSLM2 MultiStream Speech Rep Learning and Gen Spoken Language Modeling
(
arxiv.org
)
3 points
by
mrkn1
14 days ago
|
hide
|
past
|
pdf
|
discuss
65.
Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction
(
arxiv.org
)
1 point
by
FrontiersMind
14 days ago
|
hide
|
past
|
pdf
|
discuss
66.
Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention
(
arxiv.org
)
1 point
by
FrontiersMind
14 days ago
|
hide
|
past
|
pdf
|
discuss
67.
Evaluating DeepSeek v4.1 Flash-1017 for loss of control and harmful manipulation
(
arxiv.org
)
2 points
by
eunos
15 days ago
|
hide
|
past
|
pdf
|
discuss
68.
h1: A Taste of the Bitter Lesson in Automated Theorem Proving
(
arxiv.org
)
2 points
by
matt_d
15 days ago
|
hide
|
past
|
pdf
|
discuss
69.
M4Bench: Evaluating Procedural Specification for Clinical EHR Derivation Agents
(
arxiv.org
)
1 point
by
arbayi
15 days ago
|
hide
|
past
|
pdf
|
discuss
70.
From GPU to TPU with Coding Agents: What Works, What Fails, and What It Costs?
(
arxiv.org
)
1 point
by
matt_d
15 days ago
|
hide
|
past
|
pdf
|
discuss
71.
Agentic backdoors via pretraining poisoning
(
arxiv.org
)
109 points
by
gmays
15 days ago
|
hide
|
past
|
pdf
|
31 comments
72.
The DeepMind learning to play Go from scratch breakthrough for general models?
(
arxiv.org
)
2 points
by
redwood
15 days ago
|
hide
|
past
|
pdf
|
discuss
73.
Training Foundation Models with a Single Algorithm
(
arxiv.org
)
2 points
by
simonpure
15 days ago
|
hide
|
past
|
pdf
|
discuss
74.
Forking Fast: Efficiently Estimating Uncertainty Dynamics in Text Generation
(
arxiv.org
)
4 points
by
Klaster_1
15 days ago
|
hide
|
past
|
pdf
|
discuss
75.
FreeToken: Datacenter-class intelligence on the hardware you own
(
arxiv.org
)
3 points
by
lioeters
15 days ago
|
hide
|
past
|
pdf
|
3 comments
76.
CEPO: General Framework for Improving Prompt Optimization in Multi-Agent Systems
(
arxiv.org
)
2 points
by
matt_d
15 days ago
|
hide
|
past
|
pdf
|
discuss
77.
Context as Infrastructure: Knowledge Compilation for Retrieval in Agent Harness
(
arxiv.org
)
3 points
by
yingfeng
15 days ago
|
hide
|
past
|
pdf
|
discuss
78.
DMA-Latte: Expanding the Reach of DMA Offloads to Latency-Bound ML Communication
(
arxiv.org
)
1 point
by
matt_d
16 days ago
|
hide
|
past
|
pdf
|
discuss
79.
When Modernization Breaks Working Code: A Study of LLMs on Legacy PHP
(
arxiv.org
)
22 points
by
tambourine_man
16 days ago
|
hide
|
past
|
pdf
|
14 comments
80.
Open Harness for Canvas-Native Multimodal Creative Agents
(
arxiv.org
)
1 point
by
andsoitis
16 days ago
|
hide
|
past
|
pdf
|
discuss
81.
End-to-End Learning of Hierarchical World Models for Visual Planning
(
arxiv.org
)
1 point
by
andsoitis
16 days ago
|
hide
|
past
|
pdf
|
discuss
82.
Symplectic Latent Dynamics for World Models
(
arxiv.org
)
2 points
by
andsoitis
16 days ago
|
hide
|
past
|
pdf
|
discuss
83.
Proving and improving the Platonic Representation Hypothesis with JEPAs
(
arxiv.org
)
172 points
by
Anon84
16 days ago
|
hide
|
past
|
pdf
|
85 comments
84.
Agentic Backdoors via Pretraining Poisoning
(
arxiv.org
)
2 points
by
espeed
16 days ago
|
hide
|
past
|
pdf
|
1 comment
85.
Evolving Agent Teams
(
arxiv.org
)
1 point
by
anigbrowl
17 days ago
|
hide
|
past
|
pdf
|
discuss
86.
UlaCache: Unified Logical Addressing for Sparse LLM Serving
(
arxiv.org
)
3 points
by
wslh
17 days ago
|
hide
|
past
|
pdf
|
discuss
87.
MCF: Move queries, not KV caches
(
arxiv.org
)
1 point
by
wslh
17 days ago
|
hide
|
past
|
pdf
|
discuss
88.
GAAC: Lossless KV Cache Compression for Faster LLM Inference
(
arxiv.org
)
2 points
by
wslh
17 days ago
|
hide
|
past
|
pdf
|
3 comments
89.
Gandalf: Extending SSD Lifespan for LLM KV Cache Offloading
(
arxiv.org
)
1 point
by
wslh
17 days ago
|
hide
|
past
|
pdf
|
discuss
90.
Towards a virtual embryo that can predict what happens when genes change
(
arxiv.org
)
2 points
by
Betelbuddy
17 days ago
|
hide
|
past
|
pdf
|
discuss
More
About
|
RSS
|
RSS (all)
|
HN arXiv