{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CQTKGGO4WSOHHGZRWCVFCLTJ6P","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"94c63090e26cde57f8dcce0ea8168d497c2322296c933a94fd34b6e07f809f59","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T16:34:07Z","title_canon_sha256":"c1bb47a569861980dc3f4a931eea324a6ce674639501a0160e75e23586fea7d3"},"schema_version":"1.0","source":{"id":"2412.04317","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04317","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04317v1","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04317","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_12","alias_value":"CQTKGGO4WSOH","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_16","alias_value":"CQTKGGO4WSOHHGZR","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_8","alias_value":"CQTKGGO4","created_at":"2026-07-05T09:45:02Z"}],"graph_snapshots":[{"event_id":"sha256:9666be03ececc42a91873545e82817c4736bed1f0003fcdd03b3334629cd589d","target":"graph","created_at":"2026-07-05T09:45:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.04317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite a big leap forward in capability, multimodal large language models (MLLMs) tend to behave like a sloth in practical use, i.e., slow response and large latency. Recent efforts are devoted to building tiny MLLMs for better efficiency, but the plethora of visual tokens still used limit their actual speedup. In this paper, we propose a powerful and fast tiny MLLM called FlashSloth. Different from previous efforts, FlashSloth focuses on improving the descriptive power of visual tokens in the process of compressing their redundant semantics. In particular, FlashSloth introduces embedded visu","authors_text":"Bokai Lai, Bo Tong, Gen Luo, Ke Li, Rongrong Ji, Xiaoshuai Sun, Yiyi Zhou, Yunhang Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T16:34:07Z","title":"FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04317","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2647f3bda0e06a2bbffa16f54b0cb5bb007820ff41619394b8b60c25a0561cc2","target":"record","created_at":"2026-07-05T09:45:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"94c63090e26cde57f8dcce0ea8168d497c2322296c933a94fd34b6e07f809f59","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T16:34:07Z","title_canon_sha256":"c1bb47a569861980dc3f4a931eea324a6ce674639501a0160e75e23586fea7d3"},"schema_version":"1.0","source":{"id":"2412.04317","kind":"arxiv","version":1}},"canonical_sha256":"1426a319dcb49c739b31b0aa512e69f3f365fc72df40ac48d94ee55ec02525f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1426a319dcb49c739b31b0aa512e69f3f365fc72df40ac48d94ee55ec02525f3","first_computed_at":"2026-07-05T09:45:02.357303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:02.357303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HlbncA2zLWl7OnkLSLPj5YROElPActzTNMtDOO7+wP1pAiVIWGlUZKL9zTD/jjKgqEUuFjwr0EsOHMonVqipBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:02.357783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04317","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2647f3bda0e06a2bbffa16f54b0cb5bb007820ff41619394b8b60c25a0561cc2","sha256:9666be03ececc42a91873545e82817c4736bed1f0003fcdd03b3334629cd589d"],"state_sha256":"19e092c6f000f39a3cbe1fb00fb042c94f2a4c34faefaeb4fe231087d47ec896"}