Tag

Rethinking RAG in Long Videos: What to Retrieve and How to Use It?

Proposes chunk-level multimodal retrieval and chunk-adaptive reranking for retrieval-augmented generation on long egocentric videos; introduces V-RAGBench to decouple retrieval vs. generation evaluation and CARVE to run parallel retrievers and select per-chunk configurations.

AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation

Trains a transformer-based graph encoder with RL-guided adaptive masking so retrieved subgraphs embed relationships that better align with frozen LLM text encoders, improving GraphRAG performance with non-parametric retrievers on GraphQA benchmarks.

Explorer_LLM_Rec_Competition

Provides anonymized multi-domain user behavior sequences and content metadata (short video, ads, e-commerce, live) for cross-domain recommendation, semantic-ID mapping, and content-understanding tasks. Key tables include per-user multi-domain behavior (~500k rows), pid→three-segment semantic IDs, captions, and level-3 tags; all item IDs are hashed for privacy.

Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory

Provides a reflexive agentic framework for long-horizon video understanding that replaces costly iterative reasoning with dual contextual states: a consolidated global multimodal script and parametric latent states for fast retrieval and response, improving speed and memory efficiency.

Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation

Reconstructs historical experience into latent memory tokens and weaves short- and long-term latent memories directly into vision-language-action reasoning to improve long-horizon robotic manipulation. Uses a four-part pipeline (curator, seeker, condenser, weaver) so memory participates natively in multimodal action formation.

ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory

Provides a deliberative Agent OS layer for robots that handles scene-conditioned planning, context-isolated skill execution, multi-stage verification, persistent multi-modal graph memory, and edge–cloud collaboration. Introduces EmbodiedWorldBench (16 scenes, 200+ tasks) and a failure-driven self-evolution loop; shows improved task success and strong memory benchmark scores.

NVIDIA Nemotron-3-Embed-1B-BF16

Generates 2048-d multilingual text embeddings for retrieval and semantic search, suited for RAG and dense retrieval. Pruned and distilled from the Ministral-3 family into a ~1.14B BF16 model, supports long contexts (up to 32,768 tokens) and optimized for NVIDIA GPU inference.

SynthComp

Evaluates retrievers and search agents on synthetic multi-hop questions that require assembling a complete set of supporting evidence. Provides English and Russian variants (395 questions each), a fixed dense index embedded with Qwen3-Embedding-8B, and BrowseComp-Plus evaluation integrations.

TRuST

Provides 324 Russian short-answer web-search tasks with gold supporting documents to evaluate fixed-index retrievers and search agents. Tasks span eight topical categories and five retrieval challenge types (multihop, structured evidence, temporal, entity disambiguation, comparative) and use a Qwen3-Embedding-8B index for evaluation.

Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory

Measures how agent memory systems miss implicitly associated facts by introducing InMind, a 125-task benchmark with paired controls that separate stored-vs-retrieval vs knowledge gaps. Quantifies a large retrieval-interface blind spot and points to routing as the core open problem.

LFM2.5-Encoder-350M

A 350M-parameter multilingual bidirectional masked-language encoder with an 8,192-token context window, intended for fine-tuning on classification, token-level tasks, retrieval/reranking and semantic-similarity; optimized for long-context CPU inference and on-device use.

Interpretable MEG Decoding of Perceived Speech: Cortical Sources and the Stimulus Features That Drive Retrieval

Retrieves short speech segments from MEG recordings with a compact interpretable neural decoder trained against wav2vec 2.0 embeddings, and maps decoder weights to cortical source space to reveal which acoustic and linguistic features drive retrieval.