Dora
PulseAugur coverage of Dora — every cluster mentioning Dora across labs, papers, and developer communities, ranked by signal.
3 天有情绪数据
-
Developer trains personal voice adapter on Qwen3-8B for $1.50
A developer successfully trained a personal voice adapter using DoRA on the Qwen3-8B model for just $1.50. The process involved using 6,128 personal Telegram messages to fine-tune the model, resulting in an adapter that…
-
BSides Bratislava 2026 conference presentations now online
The presentations from the BSides Bratislava 2026 cybersecurity conference are now publicly available. These talks cover a range of topics including AI, DORA, and threat intelligence. The organizers expressed gratitude …
-
Qwen 3.7 ships with tunable censorship, NVIDIA fine-tunes robot video generation
Qwen has released version 3.7 of its language model, which features a specific circuit for political censorship that can be modified without losing factual knowledge. NVIDIA's Cosmos Predict 2.5 model can now be fine-tu…
-
New benchmark reveals AI agents struggle with complex financial tasks
A new benchmark called Herculean has been developed to assess the financial intelligence of AI agents, revealing that current frontier models struggle with complex tasks like hedging and auditing. This highlights a sign…
-
Compress Then Adapt? No, Do It Together via Task-aware Union of Subspaces
Researchers have introduced JACTUS, a novel framework that unifies parameter-efficient fine-tuning (PEFT) and low-rank compression for adapting large pretrained models. Unlike sequential methods, JACTUS jointly optimize…
-
DORA system accelerates LLM reinforcement learning by 2-4x with novel asynchronous rollout
Researchers have developed DORA, a novel asynchronous reinforcement learning system designed to accelerate language model training. DORA addresses the bottleneck caused by long-tailed trajectories in the rollout phase b…
-
NVIDIA Cosmos Predict 2.5 fine-tuned for robots; new ShadowPEFT method emerges
NVIDIA has released a guide for fine-tuning its Cosmos Predict 2.5 world model for robot video generation using parameter-efficient techniques like LoRA and DoRA. This method allows for adaptation to specific domains, s…