…AI-generated summary RLVR and OPD have become standard paradigms for post-training . We provide a unified analysis of these two paradigms in consolidating multiple expert capabilities into a single model, identifying…
…stable features carry most of the reconstruction- and prediction-relevant signal , while unstable features have weak marginal impact and are dominated by low-frequency surface-form triggers in both activation statistics and…
…they can be identified by massive activation values along a small set of hidden-state dimensions and are biased toward early graph-token positions. However, this activation-level saliency does not imply…
…enables faithful, decoupled evaluation of retrieval and generation, and CARVE, a simple method that runs parallel retrievers across configurations and employs chunk-adaptive reranking to identify the winning configuration for each chunk…
…AI-generated summary Recent advancements in large audio language models have extended Chain-of-Thought (CoT) reasoning into the auditory domain , enabling models to tackle increasingly complex acoustic and spoken tasks. To…
…MinT provides one infrastructure example for managing adapter identity , revision , provenance , evaluation , and serving residency . Together, the results suggest that PEFT can be a compact substrate for persistent personal models rather than…
…a feed-forward generator with a parameter-free K-source mean-pool and a monocular-temporal to multi-view-spatial two-phase schedule that anchors against identity-prior collapse onto the smaller…
…language models under concept drift conditions, achieving improved robustness and performance through constraint-aware optimization techniques. AI-generated summary This paper identifies a critical yet underexplored challenge in reasoning alignment from multiple…
…SpeechEditBench provides a rigorous diagnostic framework to identify bottlenecks in Speech LLMs, thereby facilitating the development of next-generation Speech LLMs with more robust and precise instruction-guided editing capabilities. Data and…
…modern serving stacks assume identical KV lengths across heads, so heterogeneity traps freed memory as page fragmentation , spends up to 25% of prefill time reclaiming scattered pages, and skews GPU workloads that…