Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
5
0
9
Language models can learn new knowledge without forgetting old by dynamically prioritizing replay based on observed forgetting.
End-to-end learned subspace projections shatter prior compression limits, achieving 70% weight reduction in Llama-2-7B with near-dense performance and drastically shrinking KV cache memory.
VisLens achieves a remarkable speedup in visual search for MLLMs, completing the task in a single pass while maintaining high accuracy.
High accuracy in VideoQA can be misleading, as many models perform better without visual input, revealing a dangerous reliance on textual shortcuts.
Unlock CLIP's black box: EZPC reveals the "why" behind zero-shot image recognition by grounding predictions in human-understandable concepts, without sacrificing accuracy.