Papers
-
PAPERDPDM routes agent decisions through one frozen conditional predictor instead of prompting
A paper proposes DPDM, which pairs a language model encoder with a frozen pretrained predictor so agents learn from deployment history without any weight updates.
-
PAPERNEO-VLA drops the vision encoder so action policies can read visual features at any depth
A paper from MMLab@NTU argues that vision-language-action models lose action-critical detail in their visual encoders and proposes NEO-VLA, an encoder-free design.
-
PAPERFactEmbed factorizes MLLM embeddings for composed image retrieval
A KAIST AI paper makes an MLLM imagine the requested image edit through factorized latents before building retrieval embeddings, and reuses those latents for cheap reranking.
-
PAPERRoute Anything studies when routing between models beats one fixed model
A new paper builds a 374,401-run trajectory matrix over 25 benchmarks and 452 candidate configurations to test how far learned routers can beat a single fixed candidate.
-
PAPERToolSpace builds agent training environments from real MCP tool traces
ToolSpace mines tool dependencies from real MCP execution traces, turns them into environments and checked tasks, and reports large gains for open models on long-horizon tool use.
-
PAPERReviso trains a video captioning agent to choose which visual evidence to inspect
An agentic video captioner plans what to look at from a low-frame-rate preview, revisits key segments with tools, and is trained with GRPO and cost-aware rewards.
-
PAPERServiceNow-AI Releases Apriel Voice 27B Preview Open Speech-Language Model
ServiceNow-AI introduces Apriel Voice 27B Preview, an open speech-language model built on Gemma 4 26B-A4B that unifies speech understanding, reasoning, and tool use with reported benchmarks.