InsightGen uses thematic clustering and graph neighborhood selection to generate diverse, relevant insights for open-ended document-grounded questions and releases the SCOpE-QA dataset of 3000 questions.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
verdicts
UNVERDICTED 7representative citing papers
MARLaaS enables concurrent RL fine-tuning across up to 32 tasks using LoRA adapters and a disaggregated asynchronous architecture, matching single-task performance while improving accelerator utilization by 4.3x and cutting end-to-end time by 85%.
Decision theory shows that LLM cascades are structurally limited by always incurring the cheap model's cost before deciding to escalate, with the best performance given by the envelope of pairwise cascades rather than fixed chains or many stages.
Quest speeds up long-context LLM self-attention by up to 2.23x via query-dependent selection of top-K critical KV cache pages, cutting overall latency by 7.03x with negligible accuracy loss.
SABA improves LLM performance on detective puzzle benchmarks by recursively fusing information into a base state and using queries to resolve missing premises before concluding.
CalibAdv calibrates GRPO advantage signals for search agents by downscaling excessive negative advantages using intermediate-step correctness, improving performance and training stability across three models and seven benchmarks.
Proposes Modality-Aware Credit Assignment (MoCA) with blindfolded-reasoning proxy to reward perception fidelity separately from reasoning in VLMs.
citing papers explorer
-
An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA
InsightGen uses thematic clustering and graph neighborhood selection to generate diverse, relevant insights for open-ended document-grounded questions and releases the SCOpE-QA dataset of 3000 questions.
-
MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service
MARLaaS enables concurrent RL fine-tuning across up to 32 tasks using LoRA adapters and a disaggregated asynchronous architecture, matching single-task performance while improving accelerator utilization by 4.3x and cutting end-to-end time by 85%.
-
Is Escalation Worth It? A Decision-Theoretic Characterization of LLM Cascades
Decision theory shows that LLM cascades are structurally limited by always incurring the cheap model's cost before deciding to escalate, with the best performance given by the envelope of pairwise cascades rather than fixed chains or many stages.
-
Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
Quest speeds up long-context LLM self-attention by up to 2.23x via query-dependent selection of top-K critical KV cache pages, cutting overall latency by 7.03x with negligible accuracy loss.
-
Self-Awareness before Action: Mitigating Logical Inertia via Proactive Cognitive Awareness
SABA improves LLM performance on detective puzzle benchmarks by recursively fusing information into a base state and using queries to resolve missing premises before concluding.
-
Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agents
CalibAdv calibrates GRPO advantage signals for search agents by downscaling excessive negative advantages using intermediate-step correctness, improving performance and training stability across three models and seven benchmarks.
-
Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning
Proposes Modality-Aware Credit Assignment (MoCA) with blindfolded-reasoning proxy to reward perception fidelity separately from reasoning in VLMs.