We have 8 of 187 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Extrapolative temporal knowledge graph reasoning (TKGR) predicts future facts from historical snapshots. Most existing methods train once on an early prefix of the timeline and then use a frozen model for all future timestamps. We argue that this fixed-prefix protocol is misaligned with extrapolation. It learns from a...
RoVR-GSPO is introduced, a dual-channel robust optimizer that addresses group-relative policy optimization failure modes separately and shows consistent improvements over GSPO, while controlled perturbation studies demonstrate stronger robustness to reward contamination and token-ratio anomalies.
Reward hacking occurs when policy optimization exploits a brittle reward interface or an overly permissive proxy objective, improving the training score without improving the underlying response quality. This phenomenon is amplified in group-relative policy optimization: an unsupported reward can shift the group baseli...
NaviScale is proposed for semantic-map-based object navigation (ObjectNav), whose predictor can be trained on pairs of partial and complete semantic maps without reconstructing a complete 3D environment for every training sample.
UnpairGR is proposed, which learns a unified semantic-ID space from paired, image-only, and text-only observations, which confines modality-specific processing to lightweight input projections while sharing the subsequent Transformer and residual codebooks across all observation conditions.
WDL-OPD is introduced, a mixture-constrained co-training method with two trainable policies that shows that freezing the auxiliary recovers an anchor-plus-contrast proxy target closely related to OPD$^2$ and W2S-OPD, whereas joint training creates branch-level degrees of freedom that a static delta cannot express.
This work proposes Dimension-to-Composition Routing (D2C-Routing), which routes content-side and expression-side evidence to supervised dimension heads before a learned gated composition layer predicts the final label.
This work proposes a multi-granularity knowledge refinement approach to prune historical TKGs, which selectively removes irrelevant edges and unnecessary nodes at both the edge and node levels.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
