…Memory is organized as relation-specific graph views over shared memory nodes, where each edge is associated with a trainable relation feature vector encoding multiple relational signals. Given a query, an LLM…
…To address this, we propose Stream-R1, a Reliability-Perplexity Aware Reward Distillation framework that adaptively reweights the distillation objective at both rollout and spatiotemporal-element levels through a single shared reward…
…Although methods like Negative Sample Reinforcement (NSR) mitigate this issue by upweighting penalty from negative samples, they may suppress the semantic distributions shared between positive and negative responses. To boost reasoning ability…
…We instantiate this loop with specialist agents that partition recipe surfaces and share measured lineage across trials. The central empirical finding is that lineage feedback lets agents turn evaluator outcomes, including crashes…
…Our framework factorizes the policy into candidate generation and ranking while sharing a single LLM backbone, and jointly trains them with an order-invariant coverage reward and a position-aware utility reward…
…View arXiv page View PDF Add to collection Community Sharing OmniOPD, our latest work that does on-policy distillation without requiring the teacher's logits — while outperforming methods that need them. No…
…To address this gap, we present OpenSTBench, a unified multidimensional evaluation framework that organizes heterogeneous speech translation outputs into a shared evaluation format. OpenSTBench supports both S2TT and S2ST systems in offline…
…reshapes the language model via shared parameters rather than via the latent variable it nominally optimizes. View arXiv page View PDF GitHub 0 Add to collection Community Latent visual reasoning (LVR) inserts…
…Motivated by this finding, we propose Geometry-Conflict Wasserstein Merging (GCWM), a data-free update-integration method that constructs a shared Wasserstein metric via Gaussian Wasserstein barycenters and uses geometry conflict to…
…Starting from a pretrained VLA policy, LWD closes the loop between deployment, shared physical experience, policy improvement , and redeployment by using autonomous rollouts and human interventions collected across a robot fleet. To…