ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode

Search: “sft”

3 stories in the last 3d

Searchkeywordsmart Sortlatesthotimportancerelevance
DomainAllCyberAIWindow24h3d7d30dAllIn the wildImportant onlyShow duplicates
CategoryAllAI research 4
SeverityAllcritical 0high 0medium 0low 0info 4

Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL

ActObs adds observation-token supervision to SFT, yielding higher pass@k for Qwen3 agents after GRPO on Terminal-Bench 2.0 and code editing.

Researchers introduce ActObs, an SFT variant that supervises environment-observation tokens in agent trajectories in addition to action tokens, without extra data, parameters, tokens, or forward passes. On Qwen3-4B, GRPO initialized from ActObs achieves higher pass@k at every sampling budget on Terminal-Bench 2.0, and on Qwen3-8B it trades some pass@1 for +3.4 pp at pass@16 while solving more distinct tasks. The benefit transfers to unseen code-editing tasks on aider-polyglot (+4.2 pp pass@1 at 4B scale). The authors trace the advantage to gradient analysis showing joint supervision preserves environment prediction and policy entropy, improving downstream RL exploration.

Hugging Face daily papersupdated · 20h agofirst · 1d agoAI research 2 sources

Multi-Dimensional Prosody Judgment For Live Streaming Speech Synthesis

Researchers introduce Live-ProsodyJudge and D-LPJ, Gemini-distilled Qwen3-Omni judges that decouple multi-dimensional prosody scores for live streaming TTS evaluation.

Researchers introduce Live-ProsodyJudge (LPJ), a pairwise TTS prosody evaluator distilled from Gemini into Qwen3-Omni for cost-effective live streaming speech synthesis evaluation. They identify verdict coupling, where multi-dimensional judges collapse dimension scores into a single preference bit, and propose Decoupled-Live-ProsodyJudge (D-LPJ) using masked SFT and a span-local GRPO strategy. Balanced-order LPJ beats a single Gemini call in point accuracy, and in a Best-of-8 TTS selection tournament the chosen utterance falls in the human top-3 for 85.29% of high-confidence cases.

arXiv cs.AI / cs.LG / cs.CL · 1d agoAI research

What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity

Pruning study across four LLM architectures finds dense models degrade sharply on smart-home tool calling while MoE models tolerate far more.

Researchers systematically study pruning-induced degradation in smart-home tool calling across four LLMs spanning dense Transformer, dense hybrid, and mixture-of-experts architectures, combining depth, width, hybrid, and expert pruning methods, and evaluate over 19,500 instances from three datasets after post-pruning supervised fine-tuning. Dense models show narrow safe pruning regions followed by sharp degradation, while MoE models tolerate substantially more pruning. Pruning degrades grounded specificity (operation, device, argument, value) before schema-level intent, and aggressive dense pruning can induce systematic over-refusal.

arXiv cs.AI / cs.LG / cs.CL · 2d agoAI research