Tracked topic
…No manual reward weighting, no multi-stage curriculum, and at near single-reward training cost. To the best of our knowledge, we are the first to address reward balancing problem in multi…
…hf papers read 2606.09707 Don't have the latest CLI? curl -LsSf https://hf.co/cli/install.sh | bash No model linking this paper Cite arxiv.org/abs/2606.09707 in…
…by itself typically match the performance gains available through updating LLM parameters. There is no good reason for restricting learning to being in-context or in-weights. Moreover, humans also likely learn…
…the best open-weight model achieves only 58.6% accuracy, and a 34.9-point gap between open-weight and proprietary models highlights substantial room for improvement in complex chart and table…
…This view motivates FeatCal, which uses a small calibration set to calibrate the merged model weights layer by layer in forward order , reducing feature drift while staying close to merged weights and…
…by letting the continuous controller see the backbone tokens through per-layer caches, they decouple discrete planning from continuous actuation in a clean way that also seems to help interpretability. the depth…
…In this paper, we propose RoundPipe , a novel pipeline schedule that breaks the weight binding constraint on consumer GPU servers. RoundPipe treats GPUs as a pool of stateless execution workers and dynamically…
…AI-generated summary Low-Rank Adaptation (LoRA) reparameterizes a weight update as a product of two low-rank factors, but the Jacobian J_{G} of the generator mapping the factors to the…
…This yields an optimization mechanism that modulates the geometry of weight matrices while keeping their spectral norm fixed. We derive the Pion update rule, systematically examine its design choices, and analyze its…
…I have hypotheses (embedding norms, token-id frequency in pretraining, gradient norms at the trigger position) but I genuinely do not have a clean explanation yet. Weight-level detection works at 1…