安裝中文字典英文字典辭典工具!
安裝中文字典英文字典辭典工具!
|
- HCL-FF: Hierarchical and Contrastive Learning for Forward . . .
Deep neural networks trained with backpropagation have achieved outstanding performance in vision tasks but remain biologically implausible, computationally demanding, and difficult to interpret The Forward-Forward (FF) algorithm offers a promising alternative by training each layer independently through local goodness objectives However, its purely local optimization lacks hierarchical
- Rethinking RL for LLM Reasoning: Its Sparse Policy Selection . . .
Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not teach new strategies; it redistributes probability mass over solutions the base model already contains In this work, we ask: if RL merely steers the model toward paths it already knows, is the RL optimization loop itself necessary? Through token
- SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for . . .
LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed: a few popular large models receive most requests, while many smaller tail models remain underutilized We propose \\textbf{SPECTRE} (Parallel \\textbf{SPEC}ulative Decoding with a Multi-\\textbf{T}enant \\textbf{RE}mote Drafter), a serving framework that reuses underutilized
- [2605. 23904] SkillOpt: Executive Strategy for Self-Evolving . . .
Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, and none of which reliably improves over its starting point under feedback We argue the skill should instead be trained as the external state of a frozen agent, with the same discipline that makes weight-space
- RecRM-Bench: Benchmarking Multidimensional Reward Modeling . . .
The integration of Large Language Model (LLM) agents is transforming recommender systems from simple query-item matching towards deeply personalized and interactive recommendations Reinforcement Learning (RL) provides an essential framework for the optimization of these agents in recommendation tasks However, current methodologies remain limited by a reliance on single dimensional outcome
- [2605. 15195] VGGT-$Ω$ - arXiv. org
Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also providing geometry-aware features useful for other tasks Here, we show that the quality of these models scales predictably with model and data size We do so by introducing VGGT-$Ω$, which substantially improves reconstruction accuracy, efficiency
- FinHarness: An Inline Lifecycle Safety Harness for Finance . . .
Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows However, boundary filters often miss irreversible mid-trajectory tool calls, while post-hoc LLM judges perform auditing only after termination -- too late for intervention and at a computational cost that scales linearly with trace length We present FinHarness
|
|
|