Register and share your invite link to earn from video plays and referrals.

Search results for RLツアー
RLツアー community
One keyword maps to one global community path.
Create community
People
Not Found
Tweets including RLツアー
RL World Cup - Tonga lead Samoa in gripping match that will decide England's fate
RL teaches models to work longer, but reasoning is dependent on domain-specific post-training. Baseten's Head of Model Training @oneill_c sat down with @dwarkesh_sp to explain horizon generalization and what's next at the frontier. Full episode here:
Show more
"RL will kill us" "no it won't. have you trained a model?" "no. have you?" "no"
RL is the way to go for coding, math, etc, it’s now pretty clear, but what about writing/prose? What is the solution to really improve models there?
RL hold-out-1 experiment im curious about to study how model specialization relates to model capacity and data allocation for how many domains to specialize for a common way to get a model to specialize in N domains is Multi-Teacher-On-Policy Distillation train N specialized teachers, do OPD with routing for a set of prompts to teach a model all those abilities for a given domain like data viz -> if we remove X% of the teachers (ie. Don’t specialize on those skills), does our performance on data viz increase? how is this affected by which domains get left out? does it suffer if similar domains are removed but benefit if very different domains are? we still see vertical focused specialized models like GPT-Cyber clearly looks like allocating a lot of data and parameters for a given vertical boosts perf in that vertical more than a general purpose mixture points towards a future where the specialist models always win for high value domains
Show more
RL reward is a very lossy way to codify real-world feedback. Thus, it’s very important for ML engineers to actually use the products daily.
RL fine-tuning is now live for @nvidiaai Nemotron 3 on Fireworks, starting with Nemotron 3 Super (LoRA). Train with GRPO and serve the model in one place. We price by GPU-hour, not per token, so long multi-turn rollouts don't blow up your bill. Training shapes →
Show more
In RL for streaming video, where a model keeps deciding whether to answer now or keep waiting, the way credit is handed out turn by turn has been too coarse 🎥 Turns Matter: Advancing Streaming Video RL via Turn-Level Credit 📌 Overview The paper proposes TurnWise, a GRPO extension that assigns credit per turn for streaming video understanding. It needs no critic and no extra rollouts. 🚧 The problem ・Prior work gives every turn the same trajectory-level advantage ・A redundant reply inherits credit from an earlier success, and a useful follow-up is penalized for an earlier failure ・Token-mean loss weights long replies more heavily than short "wait" decisions 🔧 Method ・Keep the actions up to a turn, replace later ones with silence (NO REPLY), and score the result to separate each turn's contribution ・Average the loss within each turn, then across turns, so replies and waits get equal weight 🧪 Results ・On ProactiveVQA, Qwen2.5-VL-3B reaches 43.56 average PAUC, 3.96 points above the strongest alternative (39.60) ・Qwen3-VL-4B reaches 42.44, 6.26 points above ThinkStream (36.18) ・Repetitive replies drop 61.5% compared with credit-only training Evaluation covers two models and three benchmarks, and variance across seeds is not reported. #VideoUnderstanding# #ReinforcementLearning#
Show more
Anthropic RL-trained Claude Haiku 4.5 to be an alignment auditor inside Petri, their production auditing scaffold. Training Alignment Auditors via Reinforcement Learning Paper:
Show more
In RL training, a vLLM rollout engine and a Megatron trainer can run the same policy yet disagree on a token's logprob due to floating-point non-associativity. SkyRL's IsoExec combines an execution contract with a unified model, aligning rounding-sensitive execution choices across rollout and training. Bitwise parity holds across different TP, EP, and SP layouts. For Gated DeltaNet, the chunkwise-parallel recurrent algorithm makes parallel training and prefill bitwise identical to recurrent decode. Qwen3.5-35B-A3B, DAPO, 8xH100, 50 steps: logprob diff 1.6e-2 to 6.7e-7, full-step overhead 25.3% ✅ vLLM's scheduler and CUDA graphs still apply. Thanks to @JiangAlexander1 and the SkyRL team at @NovaSkyAI. 🔗
Show more