We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| jiaangli/vlca | canonical | 2 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| CV_ind | Ran | jiaangli/vlca/src/utils/utils_helper.py code served (permissive licence) · get_code("a3fc094103e03dee") |
| normalization | Ran | jiaangli/vlca/src/utils/utils_helper.py code served (permissive licence) · get_code("4dc9bf9e357892c9") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large-scale pretrained language models (LMs) are said to ``lack the ability to connect utterances to the world'' (Bender and Koller, 2020), because they do not have ``mental models of the world' '(Mitchell and Krakauer, 2023). If so, one would expect LM representations to be unrelated to representations induced by vision models. We present an empirical evaluation across four families of LMs (BERT, GPT-2, OPT and LLaMA-2) and three vision model architectures (ResNet, SegFormer, and MAE). Our experiments show that LMs partially converge towards representations isomorphic to those of vision models, subject to dispersion, polysemy and frequency. This has important implications for both multi-modal processing and the LM understanding debate (Mitchell and Krakauer, 2023).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2302.06555")
get_code_for_paper("2302.06555")
have("2302.06555")
Connect an agent — have() is free.